Release v2.6.2

- Bump praisonai-ts version from 1.2.2 to 1.2.3
- Add 18 new command definitions to CLI spec: query-rewrite, prompt-expand, router, context, handoff, vector, observability, voice, reranker, graph-rag, cache, db, scheduler, jobs, checkpoints, fast-context, autonomy, sandbox, repo-map, git, n8n, external-agents, flow, cost, interactive
- Export FileMemory and AutoMemory classes with factory functions and types from memory module
- Export

README.md

@@ -35,46 +35,108 @@ PraisonAI is a production-ready Multi-AI Agents framework with self-reflection,
 
 ---
 
+> **Quick Paths:**
+> - 🚀 **New here?** → [Quick Start](#-quick-start)
+> - 📦 **Installing?** → [Installation](#-installation)
+> - 💻 **Python SDK?** → [Python Examples](#-using-python-code)
+> - 🎯 **CLI user?** → [CLI Reference](#-cli--no-code-interface)
+> - 🔧 **Need config?** → [Configuration](#-configuration--integration)
+> - 🤝 **Contributing?** → [Development](#-development)
+
+---
+
 ## 📑 Table of Contents
 
+### Getting Started
 - [⚡ Performance](#-performance)
 - [🚀 Quick Start](#-quick-start)
 - [📦 Installation](#-installation)
   - [Python SDK](#python-sdk)
   - [JavaScript SDK](#javascript-sdk)
-- [💻 Usage](#-usage)
-  - [Python Code Examples](#python-code-examples)
-  - [CLI / No-Code Interface](#cli--no-code-interface)
-  - [JavaScript Code Examples](#javascript-code-examples)
+  - [Environment Variables](#environment-variables)
+
+### Core Concepts
 - [✨ Key Features](#-key-features)
 - [🌐 Supported Providers](#-supported-providers)
+
+### Python SDK
+- [📘 Python Examples](#-using-python-code)
+  - [1. Single Agent](#1-single-agent)
+  - [2. Multi Agents](#2-multi-agents)
+  - [3. Planning Mode](#3-agent-with-planning-mode)
+  - [4. Deep Research](#4-deep-research-agent)
+  - [5. Query Rewriter](#5-query-rewriter-agent)
+  - [6. Agent Memory](#6-agent-memory-zero-dependencies)
+  - [7. Rules & Instructions](#7-rules--instructions)
+  - [8. Auto-Generated Memories](#8-auto-generated-memories)
+  - [9. Agentic Workflows](#9-agentic-workflows)
+  - [10. Hooks](#10-hooks)
+  - [11. Shadow Git Checkpoints](#11-shadow-git-checkpoints)
+  - [12. Background Tasks](#12-background-tasks)
+  - [13. Policy Engine](#13-policy-engine)
+  - [14. Thinking Budgets](#14-thinking-budgets)
+  - [15. Output Styles](#15-output-styles)
+  - [16. Context Compaction](#16-context-compaction)
+  - [17. Field Names Reference](#17-field-names-reference-a-i-g-s)
+  - [18. Extended agents.yaml](#18-extended-agentsyaml-with-workflow-patterns)
+  - [19. MCP Protocol](#19-mcp-model-context-protocol)
+  - [20. A2A Protocol](#20-a2a-agent2agent-protocol)
 - [🛠️ Custom Tools](#️-custom-tools)
+
+### JavaScript SDK
+- [💻 JavaScript Examples](#-using-javascript-code)
+
+### CLI Reference
+- [🎯 CLI Overview](#-cli--no-code-interface)
+  - [Auto Mode](#auto-mode)
+  - [Interactive Mode](#interactive-mode-cli)
+  - [Deep Research CLI](#deep-research-cli)
+  - [Planning Mode CLI](#planning-mode-cli)
+  - [Memory CLI](#memory-cli)
+  - [Workflow CLI](#workflow-cli)
+  - [Knowledge CLI](#knowledge-cli)
+  - [Session CLI](#session-cli)
+  - [Tools CLI](#tools-cli)
+  - [MCP Config CLI](#mcp-config-cli)
+  - [External Agents CLI](#external-agents-cli)
+- [CLI Features Summary](#cli-features)
+
+### Configuration
 - [🔧 Configuration & Integration](#-configuration--integration)
   - [Ollama Integration](#ollama-integration)
   - [Groq Integration](#groq-integration)
   - [100+ Models Support](#100-models-support)
-- [📋 Workflows](#-workflows)
-  - [Workflow Patterns](#workflow-patterns)
-  - [YAML Configuration](#yaml-configuration)
-  - [Agents Playbook](#agents-playbook)
-- [🧠 Memory & Context](#-memory--context)
+- [📋 Agents Playbook](#-agents-playbook)
+
+### Advanced Features
 - [🔬 Advanced Features](#-advanced-features)
   - [Research & Intelligence](#research--intelligence)
+  - [Memory & Caching](#memory--caching)
   - [Planning & Workflows](#planning--workflows)
   - [Specialised Agents](#specialised-agents)
   - [MCP Protocol](#mcp-protocol)
   - [A2A & A2UI Protocols](#a2a--a2ui-protocols)
   - [Safety & Control](#safety--control)
   - [Developer Tools](#developer-tools)
+
+### Architecture
 - [📊 Process Types & Patterns](#-process-types--patterns)
   - [Sequential Process](#sequential-process)
   - [Hierarchical Process](#hierarchical-process)
   - [Workflow Process](#workflow-process)
   - [Agentic Patterns](#agentic-patterns)
+
+### Data & Persistence
+- [💾 Persistence (Databases)](#-persistence-databases)
+- [📚 Knowledge & Retrieval (RAG)](#-knowledge--retrieval-rag)
+- [🔧 Tools Table](#-tools-table)
+
+### Learning & Community
 - [🎓 Video Tutorials](#-video-tutorials)
 - [⭐ Star History](#-star-history)
 - [👥 Contributing](#-contributing)
 - [🔧 Development](#-development)
+- [❓ FAQ & Troubleshooting](#-faq--troubleshooting)
 
 ---
 
@@ -143,6 +205,30 @@ pip install praisonai
 npm install praisonai
 ```
 
+### Environment Variables
+
+| Variable | Required | Description |
+|----------|----------|-------------|
+| `OPENAI_API_KEY` | Yes* | OpenAI API key |
+| `ANTHROPIC_API_KEY` | No | Anthropic Claude API key |
+| `GOOGLE_API_KEY` | No | Google Gemini API key |
+| `GROQ_API_KEY` | No | Groq API key |
+| `OPENAI_BASE_URL` | No | Custom API endpoint (for Ollama, Groq, etc.) |
+
+> *At least one LLM provider API key is required.
+
+```bash
+# Set your API key
+export OPENAI_API_KEY=your_key_here
+
+# For Ollama (local models)
+export OPENAI_BASE_URL=http://localhost:11434/v1
+
+# For Groq
+export OPENAI_API_KEY=your_groq_key
+export OPENAI_BASE_URL=https://api.groq.com/openai/v1
+```
+
 ---
 
 ## 💻 Usage
@@ -169,147 +255,263 @@ npm install praisonai
 
 ## ✨ Key Features
 
+<details open>
+<summary><strong>🤖 Core Agents</strong></summary>
+
 | Feature | Code | Docs |
 |---------|:----:|:----:|
-| **🤖 Core Agents** | | |
-| ↳ Single Agent | [Example](examples/python/agents/single-agent.py) | [📖](https://docs.praison.ai/agents/single) |
-| ↳ Multi Agents | [Example](examples/python/general/mini_agents_example.py) | [📖](https://docs.praison.ai/concepts/agents) |
-| ↳ Auto Agents | [Example](examples/python/general/auto_agents_example.py) | [📖](https://docs.praison.ai/features/autoagents) |
-| ↳ Self Reflection AI Agents | [Example](examples/python/concepts/self-reflection-details.py) | [📖](https://docs.praison.ai/features/selfreflection) |
-| ↳ Reasoning AI Agents | [Example](examples/python/concepts/reasoning-extraction.py) | [📖](https://docs.praison.ai/features/reasoning) |
-| ↳ Multi Modal AI Agents | [Example](examples/python/general/multimodal.py) | [📖](https://docs.praison.ai/features/multimodal) |
-| **🔄 Workflows** | | |
-| ↳ Simple Workflow | [Example](examples/python/workflows/simple_workflow.py) | [📖](https://docs.praison.ai/features/workflows) |
-| ↳ Workflow with Agents | [Example](examples/python/workflows/workflow_with_agents.py) | [📖](https://docs.praison.ai/features/workflows) |
-| ↳ Agentic Routing (`route()`) | [Example](examples/python/workflows/workflow_routing.py) | [📖](https://docs.praison.ai/features/routing) |
-| ↳ Parallel Execution (`parallel()`) | [Example](examples/python/workflows/workflow_parallel.py) | [📖](https://docs.praison.ai/features/parallelisation) |
-| ↳ Loop over List/CSV (`loop()`) | [Example](examples/python/workflows/workflow_loop_csv.py) | [📖](https://docs.praison.ai/features/repetitive) |
-| ↳ Evaluator-Optimizer (`repeat()`) | [Example](examples/python/workflows/workflow_repeat.py) | [📖](https://docs.praison.ai/features/evaluator-optimiser) |
-| ↳ Conditional Steps | [Example](examples/python/workflows/workflow_conditional.py) | [📖](https://docs.praison.ai/features/workflows) |
-| ↳ Workflow Branching | [Example](examples/python/workflows/workflow_branching.py) | [📖](https://docs.praison.ai/features/workflows) |
-| ↳ Workflow Early Stop | [Example](examples/python/workflows/workflow_early_stop.py) | [📖](https://docs.praison.ai/features/workflows) |
-| ↳ Workflow Checkpoints | [Example](examples/python/workflows/workflow_checkpoints.py) | [📖](https://docs.praison.ai/features/workflows) |
-| **💻 Code & Development** | | |
-| ↳ Code Interpreter Agents | [Example](examples/python/agents/code-agent.py) | [📖](https://docs.praison.ai/features/codeagent) |
-| ↳ AI Code Editing Tools | [Example](examples/python/code/code_editing_example.py) | [📖](https://docs.praison.ai/code/editing) |
-| ↳ External Agents (All) | [Example](examples/python/code/external_agents_example.py) | [📖](https://docs.praison.ai/code/external-agents) |
-| ↳ Claude Code CLI | [Example](examples/python/code/claude_code_example.py) | [📖](https://docs.praison.ai/code/claude-code) |
-| ↳ Gemini CLI | [Example](examples/python/code/gemini_cli_example.py) | [📖](https://docs.praison.ai/code/gemini-cli) |
-| ↳ Codex CLI | [Example](examples/python/code/codex_cli_example.py) | [📖](https://docs.praison.ai/code/codex-cli) |
-| ↳ Cursor CLI | [Example](examples/python/code/cursor_cli_example.py) | [📖](https://docs.praison.ai/code/cursor-cli) |
-| **🧠 Memory & Knowledge** | | |
-| ↳ Memory (Short & Long Term) | [Example](examples/python/general/memory_example.py) | [📖](https://docs.praison.ai/concepts/memory) |
-| ↳ File-Based Memory | [Example](examples/python/general/memory_example.py) | [📖](https://docs.praison.ai/concepts/memory) |
-| ↳ Claude Memory Tool | [Example](#claude-memory-tool-cli) | [📖](https://docs.praison.ai/features/claude-memory-tool) |
-| ↳ Add Custom Knowledge | [Example](examples/python/concepts/knowledge-agents.py) | [📖](https://docs.praison.ai/features/knowledge) |
-| ↳ RAG Agents | [Example](examples/python/concepts/rag-agents.py) | [📖](https://docs.praison.ai/features/rag) |
-| ↳ Chat with PDF Agents | [Example](examples/python/concepts/chat-with-pdf.py) | [📖](https://docs.praison.ai/features/chat-with-pdf) |
-| ↳ Data Readers (PDF, DOCX, etc.) | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-readers-api) |
-| ↳ Vector Store Selection | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-vector-store-api) |
-| ↳ Retrieval Strategies | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-retrieval-api) |
-| ↳ Rerankers | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-reranker-api) |
-| ↳ Index Types (Vector/Keyword/Hybrid) | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-index-api) |
-| ↳ Query Engines (Sub-Question, etc.) | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-query-engine-api) |
-| **🔬 Research & Intelligence** | | |
-| ↳ Deep Research Agents | [Example](examples/python/agents/research-agent.py) | [📖](https://docs.praison.ai/agents/deep-research) |
-| ↳ Query Rewriter Agent | [Example](#5-query-rewriter-agent) | [📖](https://docs.praison.ai/agents/query-rewriter) |
-| ↳ Native Web Search | [Example](examples/python/agents/websearch-agent.py) | [📖](https://docs.praison.ai/agents/websearch) |
-| ↳ Built-in Search Tools | [Example](examples/python/agents/websearch-agent.py) | [📖](https://docs.praison.ai/tools/tavily) |
-| ↳ Unified Web Search | [Example](src/praisonai-agents/examples/web_search_example.py) | [📖](https://docs.praison.ai/tools/web-search) |
-| ↳ Web Fetch (Anthropic) | [Example](#web-search-web-fetch--prompt-caching) | [📖](https://docs.praison.ai/features/model-capabilities) |
-| **📋 Planning & Execution** | | |
-| ↳ Planning Mode | [Example](examples/python/agents/planning-agent.py) | [📖](https://docs.praison.ai/features/planning-mode) |
-| ↳ Planning Tools | [Example](#3-agent-with-planning-mode) | [📖](https://docs.praison.ai/features/planning-mode) |
-| ↳ Planning Reasoning | [Example](#3-agent-with-planning-mode) | [📖](https://docs.praison.ai/features/planning-mode) |
-| ↳ Prompt Chaining | [Example](examples/python/general/prompt_chaining.py) | [📖](https://docs.praison.ai/features/promptchaining) |
-| ↳ Evaluator Optimiser | [Example](examples/python/general/evaluator-optimiser.py) | [📖](https://docs.praison.ai/features/evaluator-optimiser) |
-| ↳ Orchestrator Workers | [Example](examples/python/general/orchestrator-workers.py) | [📖](https://docs.praison.ai/features/orchestrator-worker) |
-| **👥 Specialized Agents** | | |
-| ↳ Data Analyst Agent | [Example](examples/python/agents/data-analyst-agent.py) | [📖](https://docs.praison.ai/agents/data-analyst) |
-| ↳ Finance Agent | [Example](examples/python/agents/finance-agent.py) | [📖](https://docs.praison.ai/agents/finance) |
-| ↳ Shopping Agent | [Example](examples/python/agents/shopping-agent.py) | [📖](https://docs.praison.ai/agents/shopping) |
-| ↳ Recommendation Agent | [Example](examples/python/agents/recommendation-agent.py) | [📖](https://docs.praison.ai/agents/recommendation) |
-| ↳ Wikipedia Agent | [Example](examples/python/agents/wikipedia-agent.py) | [📖](https://docs.praison.ai/agents/wikipedia) |
-| ↳ Programming Agent | [Example](examples/python/agents/programming-agent.py) | [📖](https://docs.praison.ai/agents/programming) |
-| ↳ Math Agents | [Example](examples/python/agents/math-agent.py) | [📖](https://docs.praison.ai/features/mathagent) |
-| ↳ Markdown Agent | [Example](examples/python/agents/markdown-agent.py) | [📖](https://docs.praison.ai/agents/markdown) |
-| ↳ Prompt Expander Agent | [Example](#prompt-expansion) | [📖](https://docs.praison.ai/agents/prompt-expander) |
-| **🎨 Media & Multimodal** | | |
-| ↳ Image Generation Agent | [Example](examples/python/image/image-agent.py) | [📖](https://docs.praison.ai/features/image-generation) |
-| ↳ Image to Text Agent | [Example](examples/python/agents/image-to-text-agent.py) | [📖](https://docs.praison.ai/agents/image-to-text) |
-| ↳ Video Agent | [Example](examples/python/agents/video-agent.py) | [📖](https://docs.praison.ai/agents/video) |
-| ↳ Camera Integration | [Example](examples/python/camera/) | [📖](https://docs.praison.ai/features/camera-integration) |
-| **🔌 Protocols & Integration** | | |
-| ↳ MCP Transports | [Example](examples/python/mcp/mcp-transports-overview.py) | [📖](https://docs.praison.ai/mcp/transports) |
-| ↳ WebSocket MCP | [Example](examples/python/mcp/websocket-mcp.py) | [📖](https://docs.praison.ai/mcp/sse-transport) |
-| ↳ MCP Security | [Example](examples/python/mcp/mcp-security.py) | [📖](https://docs.praison.ai/mcp/transports) |
-| ↳ MCP Resumability | [Example](examples/python/mcp/mcp-resumability.py) | [📖](https://docs.praison.ai/mcp/sse-transport) |
-| ↳ MCP Config Management | [Example](#mcp-config-cli) | [📖](https://docs.praison.ai/docs/cli/mcp) |
-| ↳ LangChain Integrated Agents | [Example](examples/python/general/langchain_example.py) | [📖](https://docs.praison.ai/features/langchain) |
-| **🛡️ Safety & Control** | | |
-| ↳ Guardrails | [Example](examples/python/guardrails/comprehensive-guardrails-example.py) | [📖](https://docs.praison.ai/features/guardrails) |
-| ↳ Human Approval | [Example](examples/python/general/human_approval_example.py) | [📖](https://docs.praison.ai/features/approval) |
-| ↳ Rules & Instructions | [Example](#6-rules--instructions) | [📖](https://docs.praison.ai/features/rules) |
-| **⚙️ Advanced Features** | | |
-| ↳ Async & Parallel Processing | [Example](examples/python/general/async_example.py) | [📖](https://docs.praison.ai/features/async) |
-| ↳ Parallelisation | [Example](examples/python/general/parallelisation.py) | [📖](https://docs.praison.ai/features/parallelisation) |
-| ↳ Repetitive Agents | [Example](examples/python/concepts/repetitive-agents.py) | [📖](https://docs.praison.ai/features/repetitive) |
-| ↳ Agent Handoffs | [Example](examples/python/handoff/handoff_basic.py) | [📖](https://docs.praison.ai/features/handoffs) |
-| ↳ Stateful Agents | [Example](examples/python/stateful/workflow-state-example.py) | [📖](https://docs.praison.ai/features/stateful-agents) |
-| ↳ Autonomous Workflow | [Example](examples/python/general/autonomous-agent.py) | [📖](https://docs.praison.ai/features/autonomous-workflow) |
-| ↳ Structured Output Agents | [Example](examples/python/general/structured_agents_example.py) | [📖](https://docs.praison.ai/features/structured) |
-| ↳ Model Router | [Example](examples/python/agents/router-agent-cost-optimization.py) | [📖](https://docs.praison.ai/features/model-router) |
-| ↳ Prompt Caching | [Example](#web-search-web-fetch--prompt-caching) | [📖](https://docs.praison.ai/features/model-capabilities) |
-| ↳ Fast Context | [Example](examples/context/00_agent_fast_context_basic.py) | [📖](https://docs.praison.ai/features/fast-context) |
-| **🛠️ Tools & Configuration** | | |
-| ↳ 100+ Custom Tools | [Example](examples/python/general/tools_example.py) | [📖](https://docs.praison.ai/tools/tools) |
-| ↳ YAML Configuration | [Example](examples/cookbooks/yaml/secondary_market_research_agents.yaml) | [📖](https://docs.praison.ai/developers/agents-playbook) |
-| ↳ 100+ LLM Support | [Example](examples/python/providers/openai/openai_gpt4_example.py) | [📖](https://docs.praison.ai/models) |
-| ↳ Callback Agents | [Example](examples/python/general/advanced-callback-systems.py) | [📖](https://docs.praison.ai/features/callbacks) |
-| ↳ Hooks | [Example](#9-hooks) | [📖](https://docs.praison.ai/features/hooks) |
-| ↳ Middleware System | [Example](examples/middleware/basic_middleware.py) | [📖](https://docs.praison.ai/features/middleware) |
-| ↳ Configurable Model | [Example](examples/middleware/configurable_model.py) | [📖](https://docs.praison.ai/features/configurable-model) |
-| ↳ Rate Limiter | [Example](examples/middleware/rate_limiter.py) | [📖](https://docs.praison.ai/features/rate-limiter) |
-| ↳ Injected Tool State | [Example](examples/middleware/injected_state.py) | [📖](https://docs.praison.ai/features/injected-state) |
-| ↳ Shadow Git Checkpoints | [Example](#10-shadow-git-checkpoints) | [📖](https://docs.praison.ai/features/checkpoints) |
-| ↳ Background Tasks | [Example](examples/background/basic_background.py) | [📖](https://docs.praison.ai/features/background-tasks) |
-| ↳ Policy Engine | [Example](examples/policy/basic_policy.py) | [📖](https://docs.praison.ai/features/policy-engine) |
-| ↳ Thinking Budgets | [Example](examples/thinking/basic_thinking.py) | [📖](https://docs.praison.ai/features/thinking-budgets) |
-| ↳ Output Styles | [Example](examples/output/basic_output.py) | [📖](https://docs.praison.ai/features/output-styles) |
-| ↳ Context Compaction | [Example](examples/compaction/basic_compaction.py) | [📖](https://docs.praison.ai/features/context-compaction) |
-| **📊 Monitoring & Management** | | |
-| ↳ Sessions Management | [Example](examples/python/sessions/comprehensive-session-management.py) | [📖](https://docs.praison.ai/features/sessions) |
-| ↳ Auto-Save Sessions | [Example](#session-management-python) | [📖](https://docs.praison.ai/docs/cli/session) |
-| ↳ History in Context | [Example](#session-management-python) | [📖](https://docs.praison.ai/docs/cli/session) |
-| ↳ Telemetry | [Example](examples/python/telemetry/production-telemetry-example.py) | [📖](https://docs.praison.ai/features/telemetry) |
-| ↳ Project Docs (.praison/docs/) | [Example](#docs-cli) | [📖](https://docs.praison.ai/docs/cli/docs) |
-| ↳ AI Commit Messages | [Example](#ai-commit-cli) | [📖](https://docs.praison.ai/docs/cli/commit) |
-| ↳ @Mentions in Prompts | [Example](#mentions-in-prompts) | [📖](https://docs.praison.ai/docs/cli/mentions) |
-| **🖥️ CLI Features** | | |
-| ↳ Slash Commands | [Example](examples/python/cli/slash_commands_example.py) | [📖](https://docs.praison.ai/docs/cli/slash-commands) |
-| ↳ Autonomy Modes | [Example](examples/python/cli/autonomy_modes_example.py) | [📖](https://docs.praison.ai/docs/cli/autonomy-modes) |
-| ↳ Cost Tracking | [Example](examples/python/cli/cost_tracking_example.py) | [📖](https://docs.praison.ai/docs/cli/cost-tracking) |
-| ↳ Repository Map | [Example](examples/python/cli/repo_map_example.py) | [📖](https://docs.praison.ai/docs/cli/repo-map) |
-| ↳ Interactive TUI | [Example](examples/python/cli/interactive_tui_example.py) | [📖](https://docs.praison.ai/docs/cli/interactive-tui) |
-| ↳ Git Integration | [Example](examples/python/cli/git_integration_example.py) | [📖](https://docs.praison.ai/docs/cli/git-integration) |
-| ↳ Sandbox Execution | [Example](examples/python/cli/sandbox_execution_example.py) | [📖](https://docs.praison.ai/docs/cli/sandbox-execution) |
-| ↳ CLI Compare | [Example](examples/compare/cli_compare_basic.py) | [📖](https://docs.praison.ai/docs/cli/compare) |
-| ↳ Profile/Benchmark | [Example](#profile-benchmark) | [📖](https://docs.praison.ai/docs/cli/profile) |
-| ↳ Auto Mode | [Example](#auto-mode) | [📖](https://docs.praison.ai/docs/cli/auto) |
-| ↳ Init | [Example](#init) | [📖](https://docs.praison.ai/docs/cli/init) |
-| ↳ File Input | [Example](#file-input) | [📖](https://docs.praison.ai/docs/cli/file-input) |
-| ↳ Final Agent | [Example](#final-agent) | [📖](https://docs.praison.ai/docs/cli/final-agent) |
-| ↳ Max Tokens | [Example](#max-tokens) | [📖](https://docs.praison.ai/docs/cli/max-tokens) |
-| **🧪 Evaluation** | | |
-| ↳ Accuracy Evaluation | [Example](examples/eval/accuracy_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |
-| ↳ Performance Evaluation | [Example](examples/eval/performance_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |
-| ↳ Reliability Evaluation | [Example](examples/eval/reliability_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |
-| ↳ Criteria Evaluation | [Example](examples/eval/criteria_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |
-| **🎯 Agent Skills** | | |
-| ↳ Skills Management | [Example](examples/skills/basic_skill_usage.py) | [📖](https://docs.praison.ai/features/skills) |
-| ↳ Custom Skills | [Example](examples/skills/custom_skill_example.py) | [📖](https://docs.praison.ai/features/skills) |
-| **⏰ 24/7 Scheduling** | | |
-| ↳ Agent Scheduler | [Example](examples/python/scheduled_agents/news_checker_live.py) | [📖](https://docs.praison.ai/docs/cli/scheduler) |
+| Single Agent | [Example](examples/python/agents/single-agent.py) | [📖](https://docs.praison.ai/agents/single) |
+| Multi Agents | [Example](examples/python/general/mini_agents_example.py) | [📖](https://docs.praison.ai/concepts/agents) |
+| Auto Agents | [Example](examples/python/general/auto_agents_example.py) | [📖](https://docs.praison.ai/features/autoagents) |
+| Self Reflection AI Agents | [Example](examples/python/concepts/self-reflection-details.py) | [📖](https://docs.praison.ai/features/selfreflection) |
+| Reasoning AI Agents | [Example](examples/python/concepts/reasoning-extraction.py) | [📖](https://docs.praison.ai/features/reasoning) |
+| Multi Modal AI Agents | [Example](examples/python/general/multimodal.py) | [📖](https://docs.praison.ai/features/multimodal) |
+
+</details>
+
+<details>
+<summary><strong>🔄 Workflows</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Simple Workflow | [Example](examples/python/workflows/simple_workflow.py) | [📖](https://docs.praison.ai/features/workflows) |
+| Workflow with Agents | [Example](examples/python/workflows/workflow_with_agents.py) | [📖](https://docs.praison.ai/features/workflows) |
+| Agentic Routing (`route()`) | [Example](examples/python/workflows/workflow_routing.py) | [📖](https://docs.praison.ai/features/routing) |
+| Parallel Execution (`parallel()`) | [Example](examples/python/workflows/workflow_parallel.py) | [📖](https://docs.praison.ai/features/parallelisation) |
+| Loop over List/CSV (`loop()`) | [Example](examples/python/workflows/workflow_loop_csv.py) | [📖](https://docs.praison.ai/features/repetitive) |
+| Evaluator-Optimizer (`repeat()`) | [Example](examples/python/workflows/workflow_repeat.py) | [📖](https://docs.praison.ai/features/evaluator-optimiser) |
+| Conditional Steps | [Example](examples/python/workflows/workflow_conditional.py) | [📖](https://docs.praison.ai/features/workflows) |
+| Workflow Branching | [Example](examples/python/workflows/workflow_branching.py) | [📖](https://docs.praison.ai/features/workflows) |
+| Workflow Early Stop | [Example](examples/python/workflows/workflow_early_stop.py) | [📖](https://docs.praison.ai/features/workflows) |
+| Workflow Checkpoints | [Example](examples/python/workflows/workflow_checkpoints.py) | [📖](https://docs.praison.ai/features/workflows) |
+
+</details>
+
+<details>
+<summary><strong>💻 Code & Development</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Code Interpreter Agents | [Example](examples/python/agents/code-agent.py) | [📖](https://docs.praison.ai/features/codeagent) |
+| AI Code Editing Tools | [Example](examples/python/code/code_editing_example.py) | [📖](https://docs.praison.ai/code/editing) |
+| External Agents (All) | [Example](examples/python/code/external_agents_example.py) | [📖](https://docs.praison.ai/code/external-agents) |
+| Claude Code CLI | [Example](examples/python/code/claude_code_example.py) | [📖](https://docs.praison.ai/code/claude-code) |
+| Gemini CLI | [Example](examples/python/code/gemini_cli_example.py) | [📖](https://docs.praison.ai/code/gemini-cli) |
+| Codex CLI | [Example](examples/python/code/codex_cli_example.py) | [📖](https://docs.praison.ai/code/codex-cli) |
+| Cursor CLI | [Example](examples/python/code/cursor_cli_example.py) | [📖](https://docs.praison.ai/code/cursor-cli) |
+
+</details>
+
+<details>
+<summary><strong>🧠 Memory & Knowledge</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Memory (Short & Long Term) | [Example](examples/python/general/memory_example.py) | [📖](https://docs.praison.ai/concepts/memory) |
+| File-Based Memory | [Example](examples/python/general/memory_example.py) | [📖](https://docs.praison.ai/concepts/memory) |
+| Claude Memory Tool | [Example](#claude-memory-tool-cli) | [📖](https://docs.praison.ai/features/claude-memory-tool) |
+| Add Custom Knowledge | [Example](examples/python/concepts/knowledge-agents.py) | [📖](https://docs.praison.ai/features/knowledge) |
+| RAG Agents | [Example](examples/python/concepts/rag-agents.py) | [📖](https://docs.praison.ai/features/rag) |
+| Chat with PDF Agents | [Example](examples/python/concepts/chat-with-pdf.py) | [📖](https://docs.praison.ai/features/chat-with-pdf) |
+| Data Readers (PDF, DOCX, etc.) | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-readers-api) |
+| Vector Store Selection | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-vector-store-api) |
+| Retrieval Strategies | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-retrieval-api) |
+| Rerankers | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-reranker-api) |
+| Index Types (Vector/Keyword/Hybrid) | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-index-api) |
+| Query Engines (Sub-Question, etc.) | [CLI](#knowledge-cli) | [📖](https://docs.praison.ai/api/praisonai/knowledge-query-engine-api) |
+
+</details>
+
+<details>
+<summary><strong>🔬 Research & Intelligence</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Deep Research Agents | [Example](examples/python/agents/research-agent.py) | [📖](https://docs.praison.ai/agents/deep-research) |
+| Query Rewriter Agent | [Example](#5-query-rewriter-agent) | [📖](https://docs.praison.ai/agents/query-rewriter) |
+| Native Web Search | [Example](examples/python/agents/websearch-agent.py) | [📖](https://docs.praison.ai/agents/websearch) |
+| Built-in Search Tools | [Example](examples/python/agents/websearch-agent.py) | [📖](https://docs.praison.ai/tools/tavily) |
+| Unified Web Search | [Example](src/praisonai-agents/examples/web_search_example.py) | [📖](https://docs.praison.ai/tools/web-search) |
+| Web Fetch (Anthropic) | [Example](#web-search-web-fetch--prompt-caching) | [📖](https://docs.praison.ai/features/model-capabilities) |
+
+</details>
+
+<details>
+<summary><strong>📋 Planning & Execution</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Planning Mode | [Example](examples/python/agents/planning-agent.py) | [📖](https://docs.praison.ai/features/planning-mode) |
+| Planning Tools | [Example](#3-agent-with-planning-mode) | [📖](https://docs.praison.ai/features/planning-mode) |
+| Planning Reasoning | [Example](#3-agent-with-planning-mode) | [📖](https://docs.praison.ai/features/planning-mode) |
+| Prompt Chaining | [Example](examples/python/general/prompt_chaining.py) | [📖](https://docs.praison.ai/features/promptchaining) |
+| Evaluator Optimiser | [Example](examples/python/general/evaluator-optimiser.py) | [📖](https://docs.praison.ai/features/evaluator-optimiser) |
+| Orchestrator Workers | [Example](examples/python/general/orchestrator-workers.py) | [📖](https://docs.praison.ai/features/orchestrator-worker) |
+
+</details>
+
+<details>
+<summary><strong>👥 Specialized Agents</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Data Analyst Agent | [Example](examples/python/agents/data-analyst-agent.py) | [📖](https://docs.praison.ai/agents/data-analyst) |
+| Finance Agent | [Example](examples/python/agents/finance-agent.py) | [📖](https://docs.praison.ai/agents/finance) |
+| Shopping Agent | [Example](examples/python/agents/shopping-agent.py) | [📖](https://docs.praison.ai/agents/shopping) |
+| Recommendation Agent | [Example](examples/python/agents/recommendation-agent.py) | [📖](https://docs.praison.ai/agents/recommendation) |
+| Wikipedia Agent | [Example](examples/python/agents/wikipedia-agent.py) | [📖](https://docs.praison.ai/agents/wikipedia) |
+| Programming Agent | [Example](examples/python/agents/programming-agent.py) | [📖](https://docs.praison.ai/agents/programming) |
+| Math Agents | [Example](examples/python/agents/math-agent.py) | [📖](https://docs.praison.ai/features/mathagent) |
+| Markdown Agent | [Example](examples/python/agents/markdown-agent.py) | [📖](https://docs.praison.ai/agents/markdown) |
+| Prompt Expander Agent | [Example](#prompt-expansion) | [📖](https://docs.praison.ai/agents/prompt-expander) |
+
+</details>
+
+<details>
+<summary><strong>🎨 Media & Multimodal</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Image Generation Agent | [Example](examples/python/image/image-agent.py) | [📖](https://docs.praison.ai/features/image-generation) |
+| Image to Text Agent | [Example](examples/python/agents/image-to-text-agent.py) | [📖](https://docs.praison.ai/agents/image-to-text) |
+| Video Agent | [Example](examples/python/agents/video-agent.py) | [📖](https://docs.praison.ai/agents/video) |
+| Camera Integration | [Example](examples/python/camera/) | [📖](https://docs.praison.ai/features/camera-integration) |
+
+</details>
+
+<details>
+<summary><strong>🔌 Protocols & Integration</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| MCP Transports | [Example](examples/python/mcp/mcp-transports-overview.py) | [📖](https://docs.praison.ai/mcp/transports) |
+| WebSocket MCP | [Example](examples/python/mcp/websocket-mcp.py) | [📖](https://docs.praison.ai/mcp/sse-transport) |
+| MCP Security | [Example](examples/python/mcp/mcp-security.py) | [📖](https://docs.praison.ai/mcp/transports) |
+| MCP Resumability | [Example](examples/python/mcp/mcp-resumability.py) | [📖](https://docs.praison.ai/mcp/sse-transport) |
+| MCP Config Management | [Example](#mcp-config-cli) | [📖](https://docs.praison.ai/docs/cli/mcp) |
+| LangChain Integrated Agents | [Example](examples/python/general/langchain_example.py) | [📖](https://docs.praison.ai/features/langchain) |
+
+</details>
+
+<details>
+<summary><strong>🛡️ Safety & Control</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Guardrails | [Example](examples/python/guardrails/comprehensive-guardrails-example.py) | [📖](https://docs.praison.ai/features/guardrails) |
+| Human Approval | [Example](examples/python/general/human_approval_example.py) | [📖](https://docs.praison.ai/features/approval) |
+| Rules & Instructions | [Example](#7-rules--instructions) | [📖](https://docs.praison.ai/features/rules) |
+
+</details>
+
+<details>
+<summary><strong>⚙️ Advanced Features</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Async & Parallel Processing | [Example](examples/python/general/async_example.py) | [📖](https://docs.praison.ai/features/async) |
+| Parallelisation | [Example](examples/python/general/parallelisation.py) | [📖](https://docs.praison.ai/features/parallelisation) |
+| Repetitive Agents | [Example](examples/python/concepts/repetitive-agents.py) | [📖](https://docs.praison.ai/features/repetitive) |
+| Agent Handoffs | [Example](examples/python/handoff/handoff_basic.py) | [📖](https://docs.praison.ai/features/handoffs) |
+| Stateful Agents | [Example](examples/python/stateful/workflow-state-example.py) | [📖](https://docs.praison.ai/features/stateful-agents) |
+| Autonomous Workflow | [Example](examples/python/general/autonomous-agent.py) | [📖](https://docs.praison.ai/features/autonomous-workflow) |
+| Structured Output Agents | [Example](examples/python/general/structured_agents_example.py) | [📖](https://docs.praison.ai/features/structured) |
+| Model Router | [Example](examples/python/agents/router-agent-cost-optimization.py) | [📖](https://docs.praison.ai/features/model-router) |
+| Prompt Caching | [Example](#web-search-web-fetch--prompt-caching) | [📖](https://docs.praison.ai/features/model-capabilities) |
+| Fast Context | [Example](examples/context/00_agent_fast_context_basic.py) | [📖](https://docs.praison.ai/features/fast-context) |
+
+</details>
+
+<details>
+<summary><strong>🛠️ Tools & Configuration</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| 100+ Custom Tools | [Example](examples/python/general/tools_example.py) | [📖](https://docs.praison.ai/tools/tools) |
+| YAML Configuration | [Example](examples/cookbooks/yaml/secondary_market_research_agents.yaml) | [📖](https://docs.praison.ai/developers/agents-playbook) |
+| 100+ LLM Support | [Example](examples/python/providers/openai/openai_gpt4_example.py) | [📖](https://docs.praison.ai/models) |
+| Callback Agents | [Example](examples/python/general/advanced-callback-systems.py) | [📖](https://docs.praison.ai/features/callbacks) |
+| Hooks | [Example](#10-hooks) | [📖](https://docs.praison.ai/features/hooks) |
+| Middleware System | [Example](examples/middleware/basic_middleware.py) | [📖](https://docs.praison.ai/features/middleware) |
+| Configurable Model | [Example](examples/middleware/configurable_model.py) | [📖](https://docs.praison.ai/features/configurable-model) |
+| Rate Limiter | [Example](examples/middleware/rate_limiter.py) | [📖](https://docs.praison.ai/features/rate-limiter) |
+| Injected Tool State | [Example](examples/middleware/injected_state.py) | [📖](https://docs.praison.ai/features/injected-state) |
+| Shadow Git Checkpoints | [Example](#11-shadow-git-checkpoints) | [📖](https://docs.praison.ai/features/checkpoints) |
+| Background Tasks | [Example](examples/background/basic_background.py) | [📖](https://docs.praison.ai/features/background-tasks) |
+| Policy Engine | [Example](examples/policy/basic_policy.py) | [📖](https://docs.praison.ai/features/policy-engine) |
+| Thinking Budgets | [Example](examples/thinking/basic_thinking.py) | [📖](https://docs.praison.ai/features/thinking-budgets) |
+| Output Styles | [Example](examples/output/basic_output.py) | [📖](https://docs.praison.ai/features/output-styles) |
+| Context Compaction | [Example](examples/compaction/basic_compaction.py) | [📖](https://docs.praison.ai/features/context-compaction) |
+
+</details>
+
+<details>
+<summary><strong>📊 Monitoring & Management</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Sessions Management | [Example](examples/python/sessions/comprehensive-session-management.py) | [📖](https://docs.praison.ai/features/sessions) |
+| Auto-Save Sessions | [Example](#session-management-python) | [📖](https://docs.praison.ai/docs/cli/session) |
+| History in Context | [Example](#session-management-python) | [📖](https://docs.praison.ai/docs/cli/session) |
+| Telemetry | [Example](examples/python/telemetry/production-telemetry-example.py) | [📖](https://docs.praison.ai/features/telemetry) |
+| Project Docs (.praison/docs/) | [Example](#docs-cli) | [📖](https://docs.praison.ai/docs/cli/docs) |
+| AI Commit Messages | [Example](#ai-commit-cli) | [📖](https://docs.praison.ai/docs/cli/commit) |
+| @Mentions in Prompts | [Example](#mentions-in-prompts) | [📖](https://docs.praison.ai/docs/cli/mentions) |
+
+</details>
+
+<details>
+<summary><strong>🖥️ CLI Features</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Slash Commands | [Example](examples/python/cli/slash_commands_example.py) | [📖](https://docs.praison.ai/docs/cli/slash-commands) |
+| Autonomy Modes | [Example](examples/python/cli/autonomy_modes_example.py) | [📖](https://docs.praison.ai/docs/cli/autonomy-modes) |
+| Cost Tracking | [Example](examples/python/cli/cost_tracking_example.py) | [📖](https://docs.praison.ai/docs/cli/cost-tracking) |
+| Repository Map | [Example](examples/python/cli/repo_map_example.py) | [📖](https://docs.praison.ai/docs/cli/repo-map) |
+| Interactive TUI | [Example](examples/python/cli/interactive_tui_example.py) | [📖](https://docs.praison.ai/docs/cli/interactive-tui) |
+| Git Integration | [Example](examples/python/cli/git_integration_example.py) | [📖](https://docs.praison.ai/docs/cli/git-integration) |
+| Sandbox Execution | [Example](examples/python/cli/sandbox_execution_example.py) | [📖](https://docs.praison.ai/docs/cli/sandbox-execution) |
+| CLI Compare | [Example](examples/compare/cli_compare_basic.py) | [📖](https://docs.praison.ai/docs/cli/compare) |
+| Profile/Benchmark | [Example](#profile-benchmark) | [📖](https://docs.praison.ai/docs/cli/profile) |
+| Auto Mode | [Example](#auto-mode) | [📖](https://docs.praison.ai/docs/cli/auto) |
+| Init | [Example](#init) | [📖](https://docs.praison.ai/docs/cli/init) |
+| File Input | [Example](#file-input) | [📖](https://docs.praison.ai/docs/cli/file-input) |
+| Final Agent | [Example](#final-agent) | [📖](https://docs.praison.ai/docs/cli/final-agent) |
+| Max Tokens | [Example](#max-tokens) | [📖](https://docs.praison.ai/docs/cli/max-tokens) |
+
+</details>
+
+<details>
+<summary><strong>🧪 Evaluation</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Accuracy Evaluation | [Example](examples/eval/accuracy_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |
+| Performance Evaluation | [Example](examples/eval/performance_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |
+| Reliability Evaluation | [Example](examples/eval/reliability_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |
+| Criteria Evaluation | [Example](examples/eval/criteria_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |
+
+</details>
+
+<details>
+<summary><strong>🎯 Agent Skills</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Skills Management | [Example](examples/skills/basic_skill_usage.py) | [📖](https://docs.praison.ai/features/skills) |
+| Custom Skills | [Example](examples/skills/custom_skill_example.py) | [📖](https://docs.praison.ai/features/skills) |
+
+</details>
+
+<details>
+<summary><strong>⏰ 24/7 Scheduling</strong></summary>
+
+| Feature | Code | Docs |
+|---------|:----:|:----:|
+| Agent Scheduler | [Example](examples/python/scheduled_agents/news_checker_live.py) | [📖](https://docs.praison.ai/docs/cli/scheduler) |
+
+</details>
 
 ---
 
@@ -543,7 +745,7 @@ memory.handle_command("/memory save my_session")
 | `memory="sqlite"` | Built-in | SQLite with indexing |
 | `memory="chromadb"` | chromadb | Vector/semantic search |
 
-### 6. Rules & Instructions
+### 7. Rules & Instructions
 
 PraisonAI auto-discovers instruction files from your project root and git root:
 
@@ -592,7 +794,7 @@ activation: always  # always, glob, manual, ai_decision
 - Follow PEP 8
 ```
 
-### 7. Auto-Generated Memories
+### 8. Auto-Generated Memories
 
 ```python
 from praisonaiagents.memory import FileMemory, AutoMemory
@@ -607,7 +809,7 @@ memories = auto.process_interaction(
 # Extracts: name="John", preference="Python for backend"
 ```
 
-### 8. Agentic Workflows
+### 9. Agentic Workflows
 
 Create powerful multi-agent workflows with the `Workflow` class:
 
@@ -877,7 +1079,7 @@ callbacks:
   on_workflow_complete: log_complete
 ```
 
-### 9. Hooks
+### 10. Hooks
 
 Intercept and modify agent behavior at various lifecycle points:
 
@@ -916,7 +1118,7 @@ praisonai hooks validate hooks.json     # Validate configuration
 ```
 
 
-### 10. Shadow Git Checkpoints
+### 11. Shadow Git Checkpoints
 
 File-level undo/restore using shadow git:
 
@@ -953,7 +1155,7 @@ praisonai checkpoint restore abc123         # Restore to checkpoint
 
 ---
 
-### 11. Background Tasks
+### 12. Background Tasks
 
 Run agent tasks asynchronously without blocking:
 
@@ -991,7 +1193,7 @@ praisonai background clear         # Clear completed tasks
 
 ---
 
-### 12. Policy Engine
+### 13. Policy Engine
 
 Control what agents can and cannot do with policy-based execution:
 
@@ -1032,7 +1234,7 @@ praisonai policy init                  # Create template
 
 ---
 
-### 13. Thinking Budgets
+### 14. Thinking Budgets
 
 Configure token budgets for extended thinking:
 
@@ -1065,7 +1267,7 @@ praisonai thinking stats       # Show usage statistics
 
 ---
 
-### 14. Output Styles
+### 15. Output Styles
 
 Configure how agents format their responses:
 
@@ -1095,7 +1297,7 @@ praisonai output set concise   # Set output style
 
 ---
 
-### 15. Context Compaction
+### 16. Context Compaction
 
 Automatically manage context window size:
 
@@ -1130,7 +1332,7 @@ praisonai compaction stats         # Show statistics
 
 ---
 
-### 16. Field Names Reference (A-I-G-S)
+### 17. Field Names Reference (A-I-G-S)
 
 PraisonAI accepts both old (agents.yaml) and new (workflow.yaml) field names. Use the **canonical names** for new projects:
 
@@ -1164,7 +1366,7 @@ steps:                         # Define steps (not 'tasks')
 
 > **Note:** The parser accepts both old and new names. Run `praisonai workflow validate <file.yaml>` to see suggestions for canonical names.
 
-### 12. Extended agents.yaml with Workflow Patterns
+### 18. Extended agents.yaml with Workflow Patterns
 
 **Feature Parity:** Both `agents.yaml` and `workflow.yaml` now support the same features:
 - All workflow patterns (route, parallel, loop, repeat)
@@ -1240,7 +1442,7 @@ Run with the same simple command:
 praisonai agents.yaml
 ```
 
-### 12. MCP (Model Context Protocol)
+### 19. MCP (Model Context Protocol)
 
 PraisonAI supports MCP Protocol Revision 2025-11-25 with multiple transports.
 
@@ -1316,7 +1518,7 @@ server.run()  # stdio for Claude Desktop
 | Security | Origin validation, DNS rebinding prevention |
 | WebSocket | Auto-reconnect with exponential backoff |
 
-### 13. A2A (Agent2Agent Protocol)
+### 20. A2A (Agent2Agent Protocol)
 
 PraisonAI supports the [A2A Protocol](https://a2a-protocol.org) for agent-to-agent communication, enabling your agents to be discovered and collaborate with other AI agents.
 
@@ -1364,6 +1566,22 @@ app.include_router(a2a.get_router())
 
 PraisonAI provides a powerful CLI for no-code automation and quick prototyping.
 
+### CLI Quick Reference
+
+| Category | Commands |
+|----------|----------|
+| **Execution** | `praisonai`, `--auto`, `--interactive`, `--chat` |
+| **Research** | `research`, `--query-rewrite`, `--deep-research` |
+| **Planning** | `--planning`, `--planning-tools`, `--planning-reasoning` |
+| **Workflows** | `workflow run`, `workflow list`, `workflow auto` |
+| **Memory** | `memory show`, `memory add`, `memory search`, `memory clear` |
+| **Knowledge** | `knowledge add`, `knowledge query`, `knowledge list` |
+| **Sessions** | `session list`, `session resume`, `session delete` |
+| **Tools** | `tools list`, `tools info`, `tools search` |
+| **MCP** | `mcp list`, `mcp create`, `mcp enable` |
+| **Development** | `commit`, `docs`, `checkpoint`, `hooks` |
+| **Scheduling** | `schedule start`, `schedule list`, `schedule stop` |
+
 ### Auto Mode
 ```bash
 pip install praisonai
@@ -3023,6 +3241,119 @@ cd src/praisonai && uv publish
 
 ---
 
+## ❓ FAQ & Troubleshooting
+
+<details>
+<summary><strong>ModuleNotFoundError: No module named 'praisonaiagents'</strong></summary>
+
+Install the package:
+```bash
+pip install praisonaiagents
+```
+
+</details>
+
+<details>
+<summary><strong>API key not found / Authentication error</strong></summary>
+
+Ensure your API key is set:
+```bash
+export OPENAI_API_KEY=your_key_here
+```
+
+For other providers, see [Environment Variables](#environment-variables).
+
+</details>
+
+<details>
+<summary><strong>How do I use a local model (Ollama)?</strong></summary>
+
+```bash
+# Start Ollama server first
+ollama serve
+
+# Set environment variable
+export OPENAI_BASE_URL=http://localhost:11434/v1
+```
+
+See [Ollama Integration](#ollama-integration) for more details.
+
+</details>
+
+<details>
+<summary><strong>How do I persist conversations to a database?</strong></summary>
+
+Use the `db` parameter:
+```python
+from praisonaiagents import Agent, db
+
+agent = Agent(
+    name="Assistant",
+    db=db(database_url="postgresql://localhost/mydb"),
+    session_id="my-session"
+)
+```
+
+See [Persistence (Databases)](#-persistence-databases) for supported databases.
+
+</details>
+
+<details>
+<summary><strong>How do I enable agent memory?</strong></summary>
+
+```python
+from praisonaiagents import Agent
+
+agent = Agent(
+    name="Assistant",
+    memory=True,  # Enables file-based memory (no extra deps!)
+    user_id="user123"
+)
+```
+
+See [Agent Memory](#6-agent-memory-zero-dependencies) for more options.
+
+</details>
+
+<details>
+<summary><strong>How do I run multiple agents together?</strong></summary>
+
+```python
+from praisonaiagents import Agent, PraisonAIAgents
+
+agent1 = Agent(instructions="Research topics")
+agent2 = Agent(instructions="Summarize findings")
+agents = PraisonAIAgents(agents=[agent1, agent2])
+agents.start()
+```
+
+See [Multi Agents](#2-multi-agents) for more examples.
+
+</details>
+
+<details>
+<summary><strong>How do I use MCP tools?</strong></summary>
+
+```python
+from praisonaiagents import Agent, MCP
+
+agent = Agent(
+    tools=MCP("npx @modelcontextprotocol/server-memory")
+)
+```
+
+See [MCP Protocol](#19-mcp-model-context-protocol) for all transport options.
+
+</details>
+
+### Getting Help
+
+- 📚 [Full Documentation](https://docs.praison.ai)
+- 🐛 [Report Issues](https://github.com/MervinPraison/PraisonAI/issues)
+- 💬 [Discussions](https://github.com/MervinPraison/PraisonAI/discussions)
+
+---
+
 <div align="center">
   <p><strong>Made with ❤️ by the PraisonAI Team</strong></p>
   <p>

docker/Dockerfile.chat

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.5.3" \
+    "praisonai>=2.6.2" \
     "praisonai[chat]" \
     "embedchain[github,youtube]"
 

docker/Dockerfile.dev

@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.5.3" \
+    "praisonai>=2.6.2" \
     "praisonai[ui]" \
     "praisonai[chat]" \
     "praisonai[realtime]" \

docker/Dockerfile.ui

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.5.3" \
+    "praisonai>=2.6.2" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

examples/js/agents/basic-agent.ts

@@ -0,0 +1,19 @@
+/**
+ * Basic Agent Example
+ * Demonstrates simple agent usage with OpenAI
+ */
+
+import { Agent } from 'praisonai';
+
+async function main() {
+  const agent = new Agent({
+    name: 'Assistant',
+    instructions: 'You are a helpful assistant. Be concise and informative.',
+    llm: 'openai/gpt-4o-mini'
+  });
+
+  const response = await agent.chat('What is TypeScript?');
+  console.log('Response:', response.text);
+}
+
+main().catch(console.error);

examples/js/agents/context-agent.ts

@@ -0,0 +1,47 @@
+/**
+ * Context Agent Example
+ * Demonstrates RAG-enabled agent with knowledge base
+ */
+
+import { ContextAgent, createContextAgent, KnowledgeBase } from 'praisonai';
+
+async function main() {
+  // Create knowledge base
+  const kb = new KnowledgeBase();
+  
+  // Add documents
+  await kb.add({
+    id: 'doc1',
+    content: 'TypeScript is a strongly typed programming language that builds on JavaScript.',
+    metadata: { topic: 'typescript' }
+  });
+  
+  await kb.add({
+    id: 'doc2',
+    content: 'TypeScript adds optional static typing and class-based object-oriented programming.',
+    metadata: { topic: 'typescript' }
+  });
+
+  await kb.add({
+    id: 'doc3',
+    content: 'PraisonAI is a framework for building AI agents in TypeScript and Python.',
+    metadata: { topic: 'praisonai' }
+  });
+
+  // Create context agent with knowledge base
+  const agent = createContextAgent({
+    name: 'KnowledgeAgent',
+    llm: 'openai/gpt-4o-mini',
+    knowledgeBase: kb,
+    maxContextDocs: 3
+  });
+
+  // Query with context
+  const response = await agent.chat('What is TypeScript?');
+  console.log('Response:', response.text);
+
+  // Check conversation history
+  console.log('\nConversation history:', agent.getHistory().length, 'messages');
+}
+
+main().catch(console.error);

examples/js/agents/image-agent.ts

@@ -0,0 +1,29 @@
+/**
+ * Image Agent Example
+ * Demonstrates image analysis capabilities
+ */
+
+import { ImageAgent, createImageAgent } from 'praisonai';
+
+async function main() {
+  const agent = createImageAgent({
+    name: 'VisionAgent',
+    llm: 'openai/gpt-4o-mini',
+    verbose: true
+  });
+
+  console.log('Image Agent created:', agent.name);
+
+  // Note: For actual image analysis, provide a real image URL
+  // const analysis = await agent.analyze({
+  //   imageUrl: 'https://example.com/image.jpg',
+  //   prompt: 'Describe this image in detail'
+  // });
+  // console.log('Analysis:', analysis);
+
+  // Chat without image
+  const response = await agent.chat('What types of images can you analyze?');
+  console.log('Response:', response);
+}
+
+main().catch(console.error);

examples/js/agents/multi-agent.ts

@@ -0,0 +1,48 @@
+/**
+ * Multi-Agent Example
+ * Demonstrates multiple agents working together
+ */
+
+import { Agent, PraisonAIAgents, Task } from 'praisonai';
+
+async function main() {
+  // Create specialized agents
+  const researcher = new Agent({
+    name: 'Researcher',
+    role: 'Research Specialist',
+    goal: 'Find accurate information on topics',
+    instructions: 'You research topics thoroughly and provide factual information.'
+  });
+
+  const writer = new Agent({
+    name: 'Writer',
+    role: 'Content Writer',
+    goal: 'Create engaging content from research',
+    instructions: 'You write clear, engaging content based on provided research.'
+  });
+
+  // Create tasks
+  const researchTask = new Task({
+    description: 'Research the benefits of TypeScript over JavaScript',
+    expectedOutput: 'A list of key benefits with explanations',
+    agent: researcher
+  });
+
+  const writeTask = new Task({
+    description: 'Write a short article about TypeScript benefits',
+    expectedOutput: 'A 200-word article',
+    agent: writer
+  });
+
+  // Run agents
+  const agents = new PraisonAIAgents({
+    agents: [researcher, writer],
+    tasks: [researchTask, writeTask],
+    process: 'sequential'
+  });
+
+  const result = await agents.start();
+  console.log('Result:', result);
+}
+
+main().catch(console.error);

examples/js/agents/research-agent.ts

@@ -0,0 +1,33 @@
+/**
+ * Deep Research Agent Example
+ * Demonstrates comprehensive research with citations
+ */
+
+import { DeepResearchAgent, createDeepResearchAgent } from 'praisonai';
+
+async function main() {
+  const agent = createDeepResearchAgent({
+    name: 'Scholar',
+    llm: 'openai/gpt-4o-mini',
+    maxIterations: 5,
+    verbose: true
+  });
+
+  console.log('Research Agent:', agent.name);
+
+  // Conduct research
+  const result = await agent.research('What are the key benefits of TypeScript?');
+
+  console.log('\n=== Research Results ===');
+  console.log('Answer:', result.answer.substring(0, 500) + '...');
+  console.log('\nConfidence:', result.confidence);
+  console.log('Reasoning steps:', result.reasoning.length);
+
+  // Show reasoning
+  console.log('\n=== Reasoning Process ===');
+  result.reasoning.forEach(step => {
+    console.log(`Step ${step.step}: ${step.thought}`);
+  });
+}
+
+main().catch(console.error);

examples/js/agents/router-agent.ts

@@ -0,0 +1,57 @@
+/**
+ * Router Agent Example
+ * Demonstrates routing requests to specialized agents
+ */
+
+import { RouterAgent, createRouter, routeConditions, Agent } from 'praisonai';
+
+async function main() {
+  // Create specialized agents
+  const mathAgent = {
+    name: 'MathAgent',
+    chat: async (input: string) => ({ text: `Math answer for: ${input}` })
+  } as any;
+
+  const codeAgent = {
+    name: 'CodeAgent', 
+    chat: async (input: string) => ({ text: `Code solution for: ${input}` })
+  } as any;
+
+  const generalAgent = {
+    name: 'GeneralAgent',
+    chat: async (input: string) => ({ text: `General response: ${input}` })
+  } as any;
+
+  // Create router with conditions
+  const router = createRouter({
+    name: 'SmartRouter',
+    routes: [
+      {
+        agent: mathAgent,
+        condition: routeConditions.keywords(['math', 'calculate', 'number', 'equation']),
+        priority: 10
+      },
+      {
+        agent: codeAgent,
+        condition: routeConditions.keywords(['code', 'program', 'function', 'javascript']),
+        priority: 10
+      }
+    ],
+    defaultAgent: generalAgent
+  });
+
+  // Test routing
+  const queries = [
+    'Calculate 2 + 2',
+    'Write a function to sort an array',
+    'What is the weather today?'
+  ];
+
+  for (const query of queries) {
+    const result = await router.route(query);
+    console.log(`Query: "${query}"`);
+    console.log(`Routed to: ${result?.agent.name || 'default'}\n`);
+  }
+}
+
+main().catch(console.error);

examples/js/auto-agents/auto-generate.ts

@@ -0,0 +1,59 @@
+/**
+ * AutoAgents Example
+ * Demonstrates automatic agent generation from task descriptions
+ */
+
+import { AutoAgents, createAutoAgents } from 'praisonai';
+
+async function main() {
+  const auto = createAutoAgents({
+    pattern: 'sequential',
+    verbose: true
+  });
+
+  // Analyze task complexity
+  console.log('=== Complexity Analysis ===');
+  const tasks = [
+    'Write a hello world function',
+    'Build a web scraper that extracts product data',
+    'Create a multi-step data pipeline with validation, transformation, and multiple output formats'
+  ];
+
+  tasks.forEach(task => {
+    const complexity = auto.analyzeComplexity(task);
+    console.log(`"${task.substring(0, 40)}..." -> ${complexity}`);
+  });
+
+  // Recommend patterns
+  console.log('\n=== Pattern Recommendations ===');
+  const patternTasks = [
+    'Process items in parallel',
+    'Route requests to different handlers',
+    'Orchestrate multiple workers',
+    'Evaluate and optimize results'
+  ];
+
+  patternTasks.forEach(task => {
+    const pattern = auto.recommendPattern(task);
+    console.log(`"${task}" -> ${pattern}`);
+  });
+
+  // Generate agent configuration
+  console.log('\n=== Generate Agent Config ===');
+  console.log('Generating agents for: "Build a web scraper"');
+  
+  const team = await auto.generate('Build a web scraper that extracts product prices from e-commerce sites');
+  
+  console.log('\nGenerated Team:');
+  console.log('Pattern:', team.pattern);
+  console.log('Agents:', team.agents.length);
+  team.agents.forEach(agent => {
+    console.log(`  - ${agent.name}: ${agent.role}`);
+  });
+  console.log('Tasks:', team.tasks.length);
+  team.tasks.forEach(task => {
+    console.log(`  - ${task.description.substring(0, 50)}...`);
+  });
+}
+
+main().catch(console.error);

examples/js/databases/redis-example.ts

@@ -0,0 +1,47 @@
+/**
+ * Redis Database Example
+ */
+
+import { createMemoryRedis } from '../../../src/praisonai-ts/src';
+
+async function main() {
+  // Use in-memory Redis for this example
+  const redis = createMemoryRedis();
+  await redis.connect();
+
+  console.log('Connected to Redis');
+
+  // Basic get/set
+  await redis.set('user:123', { name: 'John', role: 'admin' });
+  const user = await redis.get('user:123');
+  console.log('User:', user);
+
+  // Set with TTL
+  await redis.set('session:abc', { token: 'xyz' }, 60);
+  const ttl = await redis.ttl('session:abc');
+  console.log('Session TTL:', ttl, 'seconds');
+
+  // Hash operations
+  await redis.hset('profile:123', 'email', '[email protected]');
+  await redis.hset('profile:123', 'phone', '555-1234');
+  const profile = await redis.hgetall('profile:123');
+  console.log('Profile:', profile);
+
+  // List operations
+  await redis.rpush('queue:tasks', { id: 1, type: 'process' });
+  await redis.rpush('queue:tasks', { id: 2, type: 'notify' });
+  const tasks = await redis.lrange('queue:tasks', 0, -1);
+  console.log('Tasks:', tasks);
+
+  // Pub/Sub (memory only)
+  await redis.subscribe('events', (message) => {
+    console.log('Received event:', message);
+  });
+  await redis.publish('events', JSON.stringify({ type: 'user_joined' }));
+
+  // Cleanup
+  await redis.disconnect();
+  console.log('Done!');
+}
+
+main().catch(console.error);

examples/js/evaluation/eval-suite.ts

@@ -0,0 +1,64 @@
+/**
+ * Evaluation Framework Example
+ * Demonstrates accuracy, performance, and reliability evaluation
+ */
+
+import { accuracyEval, performanceEval, reliabilityEval, EvalSuite } from 'praisonai';
+
+async function main() {
+  console.log('=== Accuracy Evaluation ===');
+  const accuracyResult = await accuracyEval({
+    input: 'What is 2 + 2?',
+    expectedOutput: '4',
+    actualOutput: 'The answer is 4'
+  });
+  console.log('Passed:', accuracyResult.passed);
+  console.log('Score:', accuracyResult.score);
+  console.log('Duration:', accuracyResult.duration, 'ms');
+
+  console.log('\n=== Performance Evaluation ===');
+  const perfResult = await performanceEval({
+    func: async () => {
+      // Simulate some work
+      await new Promise(r => setTimeout(r, 100));
+      return 'done';
+    },
+    iterations: 5,
+    warmupRuns: 1
+  });
+  console.log('Iterations:', perfResult.times.length);
+  console.log('Avg time:', perfResult.avgTime.toFixed(2), 'ms');
+  console.log('Min time:', perfResult.minTime.toFixed(2), 'ms');
+  console.log('Max time:', perfResult.maxTime.toFixed(2), 'ms');
+
+  console.log('\n=== Reliability Evaluation ===');
+  const reliabilityResult = await reliabilityEval({
+    expectedToolCalls: ['search', 'calculate'],
+    actualToolCalls: ['search', 'calculate']
+  });
+  console.log('Passed:', reliabilityResult.passed);
+  console.log('Score:', reliabilityResult.score);
+
+  console.log('\n=== Eval Suite ===');
+  const suite = new EvalSuite();
+
+  await suite.runAccuracy('test1', {
+    input: 'Hello',
+    expectedOutput: 'Hi',
+    actualOutput: 'Hi there!'
+  });
+
+  await suite.runAccuracy('test2', {
+    input: 'Goodbye',
+    expectedOutput: 'Bye',
+    actualOutput: 'Bye!'
+  });
+
+  const summary = suite.getSummary();
+  console.log('Total tests:', summary.total);
+  console.log('Passed:', summary.passed);
+  console.log('Failed:', summary.failed);
+  console.log('Pass rate:', (summary.passRate * 100).toFixed(1) + '%');
+}
+
+main().catch(console.error);

examples/js/guardrails/content-guardrails.ts

@@ -0,0 +1,67 @@
+/**
+ * Content Guardrails Example
+ * Demonstrates input/output validation
+ */
+
+import { guardrail, GuardrailManager, builtinGuardrails, LLMGuardrail } from 'praisonai';
+
+async function main() {
+  // Create custom guardrail
+  const noSpamGuardrail = guardrail({
+    name: 'no_spam',
+    check: (content) => {
+      const spamWords = ['buy now', 'free money', 'click here'];
+      const hasSpam = spamWords.some(word => 
+        content.toLowerCase().includes(word)
+      );
+      return {
+        status: hasSpam ? 'failed' : 'passed',
+        message: hasSpam ? 'Content contains spam' : undefined
+      };
+    }
+  });
+
+  // Use built-in guardrails
+  const maxLength = builtinGuardrails.maxLength(500);
+  const minLength = builtinGuardrails.minLength(10);
+  const blockedWords = builtinGuardrails.blockedWords(['badword1', 'badword2']);
+
+  // Create manager
+  const manager = new GuardrailManager();
+  manager.add(noSpamGuardrail);
+  manager.add(maxLength);
+  manager.add(minLength);
+  manager.add(blockedWords);
+
+  // Test content
+  const testCases = [
+    'This is a normal, helpful response about programming.',
+    'BUY NOW! Free money if you click here!',
+    'Short',
+    'This is a valid response that provides useful information about TypeScript and its benefits for developers.'
+  ];
+
+  console.log('=== Guardrail Tests ===\n');
+
+  for (const content of testCases) {
+    console.log(`Content: "${content.substring(0, 40)}..."`);
+    const result = await manager.runAll(content);
+    console.log(`  Passed: ${result.passed}`);
+    if (!result.passed) {
+      result.results
+        .filter(r => r.status === 'failed')
+        .forEach(r => console.log(`  Failed: ${r.message}`));
+    }
+    console.log();
+  }
+
+  // LLM Guardrail example
+  console.log('=== LLM Guardrail ===');
+  const llmGuard = new LLMGuardrail({
+    name: 'quality_check',
+    criteria: 'Content must be helpful and professional'
+  });
+  console.log('LLM Guardrail created:', llmGuard.name);
+}
+
+main().catch(console.error);

examples/js/knowledge/rag-example.ts

@@ -0,0 +1,62 @@
+/**
+ * Knowledge Base (RAG) Example
+ * Demonstrates retrieval-augmented generation
+ */
+
+import { KnowledgeBase, createKnowledgeBase, Chunking } from 'praisonai';
+
+async function main() {
+  // Create knowledge base
+  const kb = createKnowledgeBase();
+
+  // Add documents
+  const documents = [
+    {
+      id: 'ts-intro',
+      content: 'TypeScript is a strongly typed programming language that builds on JavaScript, giving you better tooling at any scale.',
+      metadata: { category: 'introduction', language: 'typescript' }
+    },
+    {
+      id: 'ts-types',
+      content: 'TypeScript adds optional static typing and class-based object-oriented programming to the language.',
+      metadata: { category: 'features', language: 'typescript' }
+    },
+    {
+      id: 'ts-benefits',
+      content: 'Benefits of TypeScript include catching errors early, better IDE support, and improved code maintainability.',
+      metadata: { category: 'benefits', language: 'typescript' }
+    },
+    {
+      id: 'js-intro',
+      content: 'JavaScript is a lightweight, interpreted programming language with first-class functions.',
+      metadata: { category: 'introduction', language: 'javascript' }
+    }
+  ];
+
+  for (const doc of documents) {
+    await kb.add(doc);
+  }
+
+  console.log('Documents added:', kb.size);
+
+  // Search
+  console.log('\n=== Search: "TypeScript benefits" ===');
+  const results = await kb.search('TypeScript benefits', 3);
+  results.forEach(r => {
+    console.log(`Score: ${r.score.toFixed(2)} - ${r.document.content.substring(0, 50)}...`);
+  });
+
+  // Build context
+  console.log('\n=== Context for LLM ===');
+  const context = kb.buildContext(results);
+  console.log(context);
+
+  // Chunking example
+  console.log('\n=== Chunking Example ===');
+  const chunker = new Chunking({ chunkSize: 100, overlap: 20 });
+  const longText = 'This is a long document. '.repeat(20);
+  const chunks = chunker.chunk(longText);
+  console.log(`Chunked into ${chunks.length} pieces`);
+}
+
+main().catch(console.error);

examples/js/memory/conversation-memory.ts

@@ -0,0 +1,42 @@
+/**
+ * Conversation Memory Example
+ * Demonstrates memory management for conversations
+ */
+
+import { Memory, createMemory } from 'praisonai';
+
+async function main() {
+  const memory = createMemory({
+    maxEntries: 100,
+    maxTokens: 10000
+  });
+
+  // Simulate a conversation
+  await memory.add('What is TypeScript?', 'user');
+  await memory.add('TypeScript is a strongly typed programming language that builds on JavaScript.', 'assistant');
+  await memory.add('What are its main benefits?', 'user');
+  await memory.add('Key benefits include type safety, better IDE support, and easier refactoring.', 'assistant');
+  await memory.add('Can you give an example?', 'user');
+
+  console.log('Memory size:', memory.size, 'entries\n');
+
+  // Get recent messages
+  console.log('=== Recent Messages ===');
+  const recent = memory.getRecent(3);
+  recent.forEach(entry => {
+    console.log(`[${entry.role}]: ${entry.content.substring(0, 50)}...`);
+  });
+
+  // Search memory
+  console.log('\n=== Search Results for "TypeScript" ===');
+  const results = await memory.search('TypeScript');
+  results.forEach(r => {
+    console.log(`Score: ${r.score.toFixed(2)} - ${r.entry.content.substring(0, 40)}...`);
+  });
+
+  // Build context
+  console.log('\n=== Full Context ===');
+  console.log(memory.buildContext());
+}
+
+main().catch(console.error);

examples/js/observability/tracing.ts

@@ -0,0 +1,60 @@
+/**
+ * Observability Example
+ * Demonstrates tracing and monitoring
+ */
+
+import { MemoryObservabilityAdapter, ConsoleObservabilityAdapter } from 'praisonai';
+
+async function main() {
+  // Memory adapter - stores traces in memory
+  const memoryAdapter = new MemoryObservabilityAdapter();
+
+  // Start a trace
+  const trace = memoryAdapter.startTrace('agent-execution');
+  console.log('Trace started:', trace.traceId);
+
+  // Create spans for different operations
+  const llmSpan = trace.startSpan('llm-call', 'llm');
+  llmSpan.setAttribute('model', 'gpt-4o-mini');
+  llmSpan.setAttribute('tokens', 150);
+  await new Promise(r => setTimeout(r, 100)); // Simulate work
+  llmSpan.end();
+
+  const toolSpan = trace.startSpan('tool-execution', 'tool');
+  toolSpan.setAttribute('tool', 'calculator');
+  toolSpan.addEvent('tool-started', { input: '2+2' });
+  await new Promise(r => setTimeout(r, 50)); // Simulate work
+  toolSpan.addEvent('tool-completed', { output: '4' });
+  toolSpan.end();
+
+  // End trace
+  trace.end();
+
+  // Retrieve trace data
+  const traceData = memoryAdapter.getTrace(trace.traceId);
+  console.log('\n=== Trace Data ===');
+  console.log('Trace ID:', traceData?.traceId);
+  console.log('Spans:', traceData?.spans.length);
+  console.log('Duration:', traceData?.endTime! - traceData?.startTime!, 'ms');
+
+  // Show spans
+  console.log('\n=== Spans ===');
+  traceData?.spans.forEach(span => {
+    console.log(`- ${span.name} (${span.kind}): ${span.endTime! - span.startTime}ms`);
+    if (span.attributes) {
+      Object.entries(span.attributes).forEach(([k, v]) => {
+        console.log(`    ${k}: ${v}`);
+      });
+    }
+  });
+
+  // Console adapter example
+  console.log('\n=== Console Adapter ===');
+  const consoleAdapter = new ConsoleObservabilityAdapter();
+  const trace2 = consoleAdapter.startTrace('demo-trace');
+  const span = trace2.startSpan('demo-span', 'custom');
+  span.end();
+  trace2.end();
+}
+
+main().catch(console.error);

examples/js/planning/task-planning.ts

@@ -0,0 +1,71 @@
+/**
+ * Planning System Example
+ * Demonstrates plans, steps, and todo lists
+ */
+
+import { Plan, PlanStep, TodoList, TodoItem, PlanStorage, createPlan, createTodoList } from 'praisonai';
+
+async function main() {
+  // Create a project plan
+  console.log('=== Project Plan ===');
+  const plan = createPlan({ 
+    name: 'Build AI Agent',
+    description: 'Create a fully functional AI agent'
+  });
+
+  plan.addStep(new PlanStep({ description: 'Design agent architecture' }));
+  plan.addStep(new PlanStep({ description: 'Implement core functionality' }));
+  plan.addStep(new PlanStep({ description: 'Add tool support' }));
+  plan.addStep(new PlanStep({ description: 'Write tests' }));
+  plan.addStep(new PlanStep({ description: 'Deploy to production' }));
+
+  console.log('Plan:', plan.name);
+  console.log('Steps:', plan.steps.length);
+
+  // Execute steps
+  plan.start();
+  plan.steps[0].start();
+  plan.steps[0].complete();
+  plan.steps[1].start();
+  plan.steps[1].complete();
+
+  const progress = plan.getProgress();
+  console.log(`Progress: ${progress.completed}/${progress.total} (${progress.percentage}%)`);
+
+  // Create todo list
+  console.log('\n=== Todo List ===');
+  const todos = createTodoList('Sprint Tasks');
+
+  todos.add(new TodoItem({ content: 'Review PR #123', priority: 'high' }));
+  todos.add(new TodoItem({ content: 'Fix bug in router', priority: 'high' }));
+  todos.add(new TodoItem({ content: 'Update documentation', priority: 'medium' }));
+  todos.add(new TodoItem({ content: 'Refactor tests', priority: 'low' }));
+
+  console.log('Total items:', todos.items.length);
+  console.log('High priority:', todos.getByPriority('high').length);
+
+  // Complete some items
+  todos.items[0].complete();
+  todos.items[1].start();
+
+  console.log('Pending:', todos.getPending().length);
+  console.log('Completed:', todos.getCompleted().length);
+
+  const todoProgress = todos.getProgress();
+  console.log(`Progress: ${todoProgress.completed}/${todoProgress.total} (${todoProgress.percentage}%)`);
+
+  // Use storage
+  console.log('\n=== Plan Storage ===');
+  const storage = new PlanStorage();
+  storage.savePlan(plan);
+  storage.saveTodoList(todos);
+
+  console.log('Saved plans:', storage.listPlans().length);
+  console.log('Saved todo lists:', storage.listTodoLists().length);
+
+  // Retrieve
+  const retrieved = storage.getPlan(plan.id);
+  console.log('Retrieved plan:', retrieved?.name);
+}
+
+main().catch(console.error);

examples/js/skills/skill-manager.ts

@@ -0,0 +1,74 @@
+/**
+ * Skills System Example
+ * Demonstrates skill management and parsing
+ */
+
+import { SkillManager, parseSkillFile, createSkillManager } from 'praisonai';
+
+async function main() {
+  // Parse a skill file
+  const skillContent = `---
+name: code-review
+description: Reviews code for best practices and potential issues
+license: MIT
+metadata:
+  author: praisonai
+  version: "1.0"
+allowed-tools: Read Grep
+---
+
+# Code Review Skill
+
+When reviewing code:
+1. Check for syntax errors
+2. Look for security vulnerabilities
+3. Suggest performance improvements
+4. Ensure proper error handling
+`;
+
+  console.log('=== Parse Skill File ===');
+  const skill = parseSkillFile(skillContent);
+  console.log('Name:', skill.metadata.name);
+  console.log('Description:', skill.metadata.description);
+  console.log('License:', skill.metadata.license);
+  console.log('Instructions preview:', skill.instructions.substring(0, 100) + '...');
+
+  // Create skill manager
+  console.log('\n=== Skill Manager ===');
+  const manager = createSkillManager({ paths: [] });
+
+  // Register skills manually
+  manager.register({
+    metadata: {
+      name: 'typescript-expert',
+      description: 'Expert knowledge in TypeScript development'
+    },
+    instructions: 'You are a TypeScript expert. Help with type definitions, generics, and best practices.'
+  });
+
+  manager.register({
+    metadata: {
+      name: 'api-designer',
+      description: 'Designs RESTful APIs following best practices'
+    },
+    instructions: 'You design clean, RESTful APIs with proper versioning and documentation.'
+  });
+
+  // List skills
+  console.log('Registered skills:');
+  manager.list().forEach(s => {
+    console.log(`- ${s.metadata.name}: ${s.metadata.description}`);
+  });
+
+  // Get specific skill
+  const tsSkill = manager.get('typescript-expert');
+  console.log('\n=== TypeScript Expert Skill ===');
+  console.log('Instructions:', tsSkill?.instructions);
+
+  // Generate prompt
+  console.log('\n=== Generated Prompt ===');
+  const prompt = manager.generatePrompt(['typescript-expert']);
+  console.log(prompt.substring(0, 200) + '...');
+}
+
+main().catch(console.error);

examples/js/tools/basic-tools.ts

@@ -0,0 +1,61 @@
+/**
+ * Basic Tools Example
+ * Demonstrates tool creation and usage
+ */
+
+import { tool, ToolRegistry, getRegistry } from 'praisonai';
+
+async function main() {
+  // Create tools
+  const calculator = tool({
+    name: 'calculator',
+    description: 'Perform basic math calculations',
+    parameters: {
+      type: 'object',
+      properties: {
+        expression: { type: 'string', description: 'Math expression to evaluate' }
+      },
+      required: ['expression']
+    },
+    execute: async ({ expression }) => {
+      try {
+        const result = eval(expression);
+        return `Result: ${result}`;
+      } catch (e) {
+        return 'Error: Invalid expression';
+      }
+    }
+  });
+
+  const greeter = tool({
+    name: 'greeter',
+    description: 'Generate a greeting',
+    parameters: {
+      type: 'object',
+      properties: {
+        name: { type: 'string', description: 'Name to greet' }
+      },
+      required: ['name']
+    },
+    execute: async ({ name }) => `Hello, ${name}! Welcome to PraisonAI.`
+  });
+
+  // Create registry and register tools
+  const registry = new ToolRegistry();
+  registry.register(calculator);
+  registry.register(greeter);
+
+  console.log('Registered tools:', registry.list().map(t => t.name));
+
+  // Execute tools
+  const calcResult = await calculator.execute({ expression: '10 * 5 + 2' });
+  console.log('\nCalculator:', calcResult);
+
+  const greetResult = await greeter.execute({ name: 'Developer' });
+  console.log('Greeter:', greetResult);
+
+  // Get OpenAI format
+  console.log('\nOpenAI tool format:', JSON.stringify(calculator.toOpenAITool(), null, 2));
+}
+
+main().catch(console.error);

examples/js/tools/custom-tool.ts

@@ -0,0 +1,113 @@
+/**
+ * Custom Tool Example
+ * Demonstrates creating custom tools using BaseTool class (plugin pattern)
+ */
+
+import { BaseTool, createTool, tool, ToolRegistry } from 'praisonai';
+
+// Method 1: Extend BaseTool class (recommended for complex tools)
+class WeatherTool extends BaseTool<{ location: string; units?: string }, { temp: number; condition: string }> {
+  name = 'get_weather';
+  description = 'Get current weather for a location';
+  parameters = {
+    type: 'object' as const,
+    properties: {
+      location: { type: 'string', description: 'City name' },
+      units: { type: 'string', description: 'celsius or fahrenheit', default: 'celsius' }
+    },
+    required: ['location']
+  };
+
+  async run(params: { location: string; units?: string }): Promise<{ temp: number; condition: string }> {
+    // Simulate API call
+    console.log(`Getting weather for ${params.location} in ${params.units || 'celsius'}`);
+    return { temp: 22, condition: 'sunny' };
+  }
+}
+
+// Method 2: Use createTool function (quick inline tools)
+const calculatorTool = createTool({
+  name: 'calculator',
+  description: 'Evaluate a math expression',
+  parameters: {
+    type: 'object',
+    properties: {
+      expression: { type: 'string', description: 'Math expression to evaluate' }
+    },
+    required: ['expression']
+  },
+  run: (params: { expression: string }) => {
+    try {
+      return eval(params.expression);
+    } catch {
+      return 'Error: Invalid expression';
+    }
+  }
+});
+
+// Method 3: Use tool() function with config object
+const greeterTool = tool({
+  name: 'greeter',
+  description: 'Generate a personalized greeting',
+  parameters: {
+    type: 'object',
+    properties: {
+      name: { type: 'string', description: 'Name to greet' },
+      style: { type: 'string', description: 'Greeting style: formal or casual' }
+    },
+    required: ['name']
+  },
+  execute: async (params: { name: string; style?: string }) => {
+    if (params.style === 'formal') {
+      return `Good day, ${params.name}. How may I assist you?`;
+    }
+    return `Hey ${params.name}! What's up?`;
+  }
+});
+
+async function main() {
+  console.log('=== Custom Tool Examples ===\n');
+
+  // Test WeatherTool (class-based)
+  console.log('--- WeatherTool (class-based) ---');
+  const weather = new WeatherTool();
+  console.log('Name:', weather.name);
+  console.log('Description:', weather.description);
+  
+  const weatherResult = await weather.run({ location: 'New York' });
+  console.log('Result:', weatherResult);
+  
+  // Safe execution with error handling
+  const safeResult = await weather.safeRun({ location: 'London' });
+  console.log('Safe result:', safeResult);
+
+  // Get OpenAI schema
+  console.log('OpenAI Schema:', JSON.stringify(weather.getSchema(), null, 2));
+
+  // Test calculatorTool (createTool)
+  console.log('\n--- Calculator Tool (createTool) ---');
+  const calcResult = await calculatorTool.run({ expression: '10 * 5 + 2' });
+  console.log('10 * 5 + 2 =', calcResult);
+
+  // Test greeterTool (tool function)
+  console.log('\n--- Greeter Tool (tool function) ---');
+  const greeting1 = await greeterTool.execute({ name: 'Alice' });
+  console.log('Casual:', greeting1);
+  
+  const greeting2 = await greeterTool.execute({ name: 'Mr. Smith', style: 'formal' });
+  console.log('Formal:', greeting2);
+
+  // Register tools in registry
+  console.log('\n--- Tool Registry ---');
+  const registry = new ToolRegistry();
+  registry.register(greeterTool);
+  
+  console.log('Registered tools:', registry.list().map(t => t.name));
+  console.log('OpenAI tools format:', registry.toOpenAITools().length, 'tools');
+
+  // Validate tool
+  console.log('\n--- Validation ---');
+  console.log('WeatherTool valid:', weather.validate());
+}
+
+main().catch(console.error);

examples/js/vector-stores/pinecone-example.ts

@@ -0,0 +1,57 @@
+/**
+ * Pinecone Vector Store Example
+ */
+
+import { createPineconeStore } from 'praisonai';
+
+async function main() {
+  const pinecone = createPineconeStore({
+    apiKey: process.env.PINECONE_API_KEY!
+  });
+
+  const indexName = 'test-index';
+
+  // Create index
+  console.log('Creating index...');
+  await pinecone.createIndex({
+    indexName,
+    dimension: 3,
+    metric: 'cosine'
+  });
+
+  // List indexes
+  const indexes = await pinecone.listIndexes();
+  console.log('Indexes:', indexes);
+
+  // Upsert vectors
+  console.log('Upserting vectors...');
+  await pinecone.upsert({
+    indexName,
+    vectors: [
+      { id: 'vec-1', vector: [0.1, 0.2, 0.3], metadata: { category: 'A' } },
+      { id: 'vec-2', vector: [0.4, 0.5, 0.6], metadata: { category: 'B' } },
+      { id: 'vec-3', vector: [0.7, 0.8, 0.9], metadata: { category: 'A' } }
+    ]
+  });
+
+  // Query
+  console.log('Querying...');
+  const results = await pinecone.query({
+    indexName,
+    vector: [0.1, 0.2, 0.3],
+    topK: 2,
+    includeMetadata: true
+  });
+
+  console.log('Results:');
+  for (const r of results) {
+    console.log(`  ${r.id}: score=${r.score.toFixed(4)}, metadata=${JSON.stringify(r.metadata)}`);
+  }
+
+  // Cleanup
+  console.log('Deleting index...');
+  await pinecone.deleteIndex(indexName);
+  console.log('Done!');
+}
+
+main().catch(console.error);

examples/js/voice/tts-example.ts

@@ -0,0 +1,30 @@
+/**
+ * Voice/TTS Example
+ */
+
+import { createOpenAIVoice } from '../../../src/praisonai-ts/src';
+import { writeFileSync } from 'fs';
+
+async function main() {
+  const voice = createOpenAIVoice({
+    apiKey: process.env.OPENAI_API_KEY
+  });
+
+  // Check available voices
+  const speakers = await voice.getSpeakers();
+  console.log('Available voices:', speakers.map(s => s.name).join(', '));
+
+  // Generate speech
+  console.log('Generating speech...');
+  const audio = await voice.speak('Hello! Welcome to PraisonAI TypeScript SDK.', {
+    voice: 'nova',
+    speed: 1.0,
+    format: 'mp3'
+  });
+
+  // Save to file
+  writeFileSync('output.mp3', audio);
+  console.log('Audio saved to output.mp3');
+}
+
+main().catch(console.error);

examples/js/workflows/basic-workflow.ts

@@ -0,0 +1,29 @@
+/**
+ * Basic Workflow Example
+ * Demonstrates sequential workflow execution
+ */
+
+import { Workflow, parallel, route, loop } from 'praisonai';
+
+async function main() {
+  // Create a simple workflow
+  const workflow = new Workflow<string, string>('DataProcessor')
+    .step('validate', async (input) => {
+      console.log('Step 1: Validating input...');
+      return input.trim();
+    })
+    .step('transform', async (input) => {
+      console.log('Step 2: Transforming...');
+      return input.toUpperCase();
+    })
+    .step('format', async (input) => {
+      console.log('Step 3: Formatting...');
+      return `[PROCESSED] ${input}`;
+    });
+
+  const result = await workflow.run('  hello world  ');
+  console.log('\nFinal output:', result.output);
+  console.log('Steps executed:', result.steps.length);
+}
+
+main().catch(console.error);

examples/js/workflows/conditional-workflow.ts

@@ -0,0 +1,48 @@
+/**
+ * Conditional Workflow Example
+ * Demonstrates routing based on conditions
+ */
+
+import { route } from 'praisonai';
+
+async function main() {
+  const processRequest = async (type: string) => {
+    console.log(`Processing request type: ${type}`);
+
+    const result = await route([
+      {
+        condition: () => type === 'urgent',
+        execute: async () => {
+          console.log('  -> Urgent handler activated');
+          return 'Processed urgently';
+        }
+      },
+      {
+        condition: () => type === 'normal',
+        execute: async () => {
+          console.log('  -> Normal handler activated');
+          return 'Processed normally';
+        }
+      },
+      {
+        condition: () => true, // Default
+        execute: async () => {
+          console.log('  -> Default handler activated');
+          return 'Processed with default handler';
+        }
+      }
+    ]);
+
+    return result;
+  };
+
+  // Test different request types
+  const types = ['urgent', 'normal', 'unknown'];
+  
+  for (const type of types) {
+    const result = await processRequest(type);
+    console.log(`Result: ${result}\n`);
+  }
+}
+
+main().catch(console.error);

examples/js/workflows/parallel-workflow.ts

@@ -0,0 +1,36 @@
+/**
+ * Parallel Workflow Example
+ * Demonstrates parallel execution of tasks
+ */
+
+import { parallel } from 'praisonai';
+
+async function main() {
+  console.log('Starting parallel tasks...\n');
+
+  const results = await parallel([
+    async () => {
+      console.log('Task 1: Starting...');
+      await new Promise(r => setTimeout(r, 1000));
+      console.log('Task 1: Complete');
+      return 'Result 1';
+    },
+    async () => {
+      console.log('Task 2: Starting...');
+      await new Promise(r => setTimeout(r, 500));
+      console.log('Task 2: Complete');
+      return 'Result 2';
+    },
+    async () => {
+      console.log('Task 3: Starting...');
+      await new Promise(r => setTimeout(r, 750));
+      console.log('Task 3: Complete');
+      return 'Result 3';
+    }
+  ]);
+
+  console.log('\nAll tasks complete!');
+  console.log('Results:', results);
+}
+
+main().catch(console.error);

src/praisonai-agents/praisonaiagents/agent/agent.py

@@ -61,6 +61,57 @@ class Agent:
             logging.getLogger("httpx").setLevel(logging.WARNING)
             logging.getLogger("httpcore").setLevel(logging.WARNING)
     
+    @classmethod
+    def from_template(
+        cls,
+        uri: str,
+        config: Optional[Dict[str, Any]] = None,
+        offline: bool = False,
+        **kwargs
+    ) -> 'Agent':
+        """
+        Create an Agent from a template.
+        
+        Args:
+            uri: Template URI (local path, package ref, or github ref)
+                Examples:
+                - "./my-template" (local path)
+                - "transcript-generator" (default recipes repo)
+                - "github:owner/repo/[email protected]" (GitHub with version)
+                - "package:agent_recipes/transcript-generator" (installed package)
+            config: Optional configuration overrides
+            offline: If True, only use cached templates (no network)
+            **kwargs: Additional Agent constructor arguments
+            
+        Returns:
+            Configured Agent instance
+            
+        Example:
+            ```python
+            from praisonaiagents import Agent
+            
+            # From default recipes repo
+            agent = Agent.from_template("transcript-generator")
+            result = agent.chat("Transcribe ./audio.mp3")
+            
+            # With config overrides
+            agent = Agent.from_template(
+                "data-transformer",
+                config={"output_format": "json"},
+                verbose=True
+            )
+            ```
+        """
+        try:
+            # Lazy import to avoid circular dependencies and keep core SDK lean
+            from praisonai.templates.loader import create_agent_from_template
+            return create_agent_from_template(uri, config=config, offline=offline, **kwargs)
+        except ImportError:
+            raise ImportError(
+                "Template support requires the 'praisonai' package. "
+                "Install with: pip install praisonai"
+            )
+    
     def _generate_tool_definition(self, function_name):
         """
         Generate a tool definition from a function name by inspecting the function.

src/praisonai-agents/praisonaiagents/eval/accuracy.py

@@ -89,11 +89,9 @@ class AccuracyEvaluator(BaseEvaluator):
             EvaluationScore with score and reasoning
         """
         try:
-            from openai import OpenAI
+            import litellm
         except ImportError:
-            raise ImportError("OpenAI package required for accuracy evaluation. Install with: pip install openai")
-        
-        client = OpenAI()
+            raise ImportError("litellm package required for accuracy evaluation. Install with: pip install litellm")
         
         prompt = f"""You are an expert evaluator. Compare the actual output against the expected output and provide a score from 1-10.
 
@@ -115,7 +113,8 @@ Respond in this exact format:
 SCORE: [number 1-10]
 REASONING: [brief explanation]"""
 
-        response = client.chat.completions.create(
+        # Use litellm for unified multi-provider support
+        response = litellm.completion(
             model=self.model,
             messages=[{"role": "user", "content": prompt}],
             temperature=0.1,

src/praisonai-agents/praisonaiagents/eval/criteria.py

@@ -99,11 +99,9 @@ class CriteriaEvaluator(BaseEvaluator):
             CriteriaScore with score, passed status, and reasoning
         """
         try:
-            from openai import OpenAI
+            import litellm
         except ImportError:
-            raise ImportError("OpenAI package required for criteria evaluation. Install with: pip install openai")
-        
-        client = OpenAI()
+            raise ImportError("litellm package required for criteria evaluation. Install with: pip install litellm")
         
         if self.scoring_type == "binary":
             prompt = f"""You are an expert evaluator. Evaluate the following output against the given criteria.
@@ -138,7 +136,8 @@ Respond in this exact format:
 SCORE: [number 1-10]
 REASONING: [brief explanation]"""
 
-        response = client.chat.completions.create(
+        # Use litellm for unified multi-provider support
+        response = litellm.completion(
             model=self.model,
             messages=[{"role": "user", "content": prompt}],
             temperature=0.1,

src/praisonai-agents/praisonaiagents/knowledge/knowledge.py

@@ -91,19 +91,20 @@ class MongoDBMemory:
             raise Exception(f"Failed to initialize MongoDB: {e}")
     
     def _init_embedding_model(self):
-        """Initialize embedding model from config."""
+        """Initialize embedding model from config using litellm for unified provider support."""
         try:
             # Set up embedding model based on config
             embedder_config = self.config.get("embedder", {})
-            if embedder_config.get("provider") == "openai":
-                import openai
-                self.embedding_model = openai.OpenAI()
-                self.embedding_model_name = embedder_config.get("config", {}).get("model", "text-embedding-3-small")
-            else:
-                # Default to OpenAI
-                import openai
-                self.embedding_model = openai.OpenAI()
-                self.embedding_model_name = "text-embedding-3-small"
+            provider = embedder_config.get("provider", "openai")
+            model_name = embedder_config.get("config", {}).get("model", "text-embedding-3-small")
+            
+            # Store model name for later use
+            self.embedding_model_name = model_name
+            
+            # Use litellm for embeddings - it handles all providers uniformly
+            # We'll use litellm.embedding() in _get_embeddings() instead of storing a client
+            self.embedding_provider = provider
+            self.embedding_model = None  # Will use litellm.embedding() directly
         except Exception as e:
             raise Exception(f"Failed to initialize embedding model: {e}")
     
@@ -172,13 +173,16 @@ class MongoDBMemory:
             logging.warning(f"Could not create vector search index: {e}")
     
     def _get_embedding(self, text):
-        """Get embedding for text."""
+        """Get embedding for text using litellm for unified provider support."""
         try:
-            response = self.embedding_model.embeddings.create(
-                input=text,
-                model=self.embedding_model_name
+            import litellm
+            
+            # Use litellm.embedding() for unified multi-provider support
+            response = litellm.embedding(
+                model=self.embedding_model_name,
+                input=text
             )
-            return response.data[0].embedding
+            return response.data[0]["embedding"]
         except Exception as e:
             logging.error(f"Error getting embedding: {e}")
             return None

src/praisonai-agents/praisonaiagents/workflows/workflows.py

@@ -313,6 +313,56 @@ class Workflow:
             "planning_llm": self.planning_llm
         }
     
+    @classmethod
+    def from_template(
+        cls,
+        uri: str,
+        config: Optional[Dict[str, Any]] = None,
+        offline: bool = False,
+        **kwargs
+    ) -> 'Workflow':
+        """
+        Create a Workflow from a template.
+        
+        Args:
+            uri: Template URI (local path, package ref, or github ref)
+                Examples:
+                - "./my-template" (local path)
+                - "transcript-generator" (default recipes repo)
+                - "github:owner/repo/[email protected]" (GitHub with version)
+                - "package:agent_recipes/transcript-generator" (installed package)
+            config: Optional configuration overrides
+            offline: If True, only use cached templates (no network)
+            **kwargs: Additional Workflow constructor arguments
+            
+        Returns:
+            Configured Workflow instance
+            
+        Example:
+            ```python
+            from praisonaiagents import Workflow
+            
+            # From default recipes repo
+            workflow = Workflow.from_template("transcript-generator")
+            result = workflow.run("./audio.mp3")
+            
+            # With config overrides
+            workflow = Workflow.from_template(
+                "data-transformer",
+                config={"output_format": "json"}
+            )
+            ```
+        """
+        try:
+            # Lazy import to avoid circular dependencies and keep core SDK lean
+            from praisonai.templates.loader import create_workflow_from_template
+            return create_workflow_from_template(uri, config=config, offline=offline, **kwargs)
+        except ImportError:
+            raise ImportError(
+                "Template support requires the 'praisonai' package. "
+                "Install with: pip install praisonai"
+            )
+    
     def run(
         self,
         input: str = "",

src/praisonai-agents/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "praisonaiagents"
-version = "0.3.3"
+version = "0.4.0"
 description = "Praison AI agents for completing complex tasks with Self Reflection Agents"
 readme = "README.md"
 requires-python = ">=3.10"

src/praisonai-agents/tests/unit/eval/test_evaluators.py

@@ -91,14 +91,11 @@ class TestAccuracyEvaluator:
     
     def test_judge_output(self):
         """Test LLM judging of output."""
-        with patch('openai.OpenAI') as mock_openai_class:
-            mock_client = MagicMock()
-            mock_openai_class.return_value = mock_client
-            
+        with patch('litellm.completion') as mock_completion:
             mock_response = MagicMock()
             mock_response.choices = [MagicMock()]
             mock_response.choices[0].message.content = "SCORE: 8\nREASONING: Good match"
-            mock_client.chat.completions.create.return_value = mock_response
+            mock_completion.return_value = mock_response
             
             def test_func(x):
                 return "4"
@@ -115,14 +112,11 @@ class TestAccuracyEvaluator:
     
     def test_run_returns_accuracy_result(self):
         """Test that run returns AccuracyResult."""
-        with patch('openai.OpenAI') as mock_openai_class:
-            mock_client = MagicMock()
-            mock_openai_class.return_value = mock_client
-            
+        with patch('litellm.completion') as mock_completion:
             mock_response = MagicMock()
             mock_response.choices = [MagicMock()]
             mock_response.choices[0].message.content = "SCORE: 9\nREASONING: Excellent"
-            mock_client.chat.completions.create.return_value = mock_response
+            mock_completion.return_value = mock_response
             
             def test_func(x):
                 return "4"
@@ -140,14 +134,11 @@ class TestAccuracyEvaluator:
     
     def test_evaluate_output(self):
         """Test evaluate_output method for pre-generated outputs."""
-        with patch('openai.OpenAI') as mock_openai_class:
-            mock_client = MagicMock()
-            mock_openai_class.return_value = mock_client
-            
+        with patch('litellm.completion') as mock_completion:
             mock_response = MagicMock()
             mock_response.choices = [MagicMock()]
             mock_response.choices[0].message.content = "SCORE: 10\nREASONING: Perfect"
-            mock_client.chat.completions.create.return_value = mock_response
+            mock_completion.return_value = mock_response
             
             def test_func(x):
                 return "unused"
@@ -325,14 +316,11 @@ class TestCriteriaEvaluator:
     
     def test_judge_output_numeric(self):
         """Test numeric scoring."""
-        with patch('openai.OpenAI') as mock_openai_class:
-            mock_client = MagicMock()
-            mock_openai_class.return_value = mock_client
-            
+        with patch('litellm.completion') as mock_completion:
             mock_response = MagicMock()
             mock_response.choices = [MagicMock()]
             mock_response.choices[0].message.content = "SCORE: 8\nREASONING: Good"
-            mock_client.chat.completions.create.return_value = mock_response
+            mock_completion.return_value = mock_response
             
             def test_func(x):
                 return "test"
@@ -350,14 +338,11 @@ class TestCriteriaEvaluator:
     
     def test_judge_output_binary(self):
         """Test binary scoring."""
-        with patch('openai.OpenAI') as mock_openai_class:
-            mock_client = MagicMock()
-            mock_openai_class.return_value = mock_client
-            
+        with patch('litellm.completion') as mock_completion:
             mock_response = MagicMock()
             mock_response.choices = [MagicMock()]
             mock_response.choices[0].message.content = "RESULT: PASS\nREASONING: Meets criteria"
-            mock_client.chat.completions.create.return_value = mock_response
+            mock_completion.return_value = mock_response
             
             def test_func(x):
                 return "test"
@@ -374,14 +359,11 @@ class TestCriteriaEvaluator:
     
     def test_on_fail_callback(self):
         """Test on_fail callback is called."""
-        with patch('openai.OpenAI') as mock_openai_class:
-            mock_client = MagicMock()
-            mock_openai_class.return_value = mock_client
-            
+        with patch('litellm.completion') as mock_completion:
             mock_response = MagicMock()
             mock_response.choices = [MagicMock()]
             mock_response.choices[0].message.content = "SCORE: 3\nREASONING: Poor"
-            mock_client.chat.completions.create.return_value = mock_response
+            mock_completion.return_value = mock_response
             
             on_fail_called = []
             def on_fail(score):
@@ -403,14 +385,11 @@ class TestCriteriaEvaluator:
     
     def test_evaluate_output_criteria(self):
         """Test evaluate_output method."""
-        with patch('openai.OpenAI') as mock_openai_class:
-            mock_client = MagicMock()
-            mock_openai_class.return_value = mock_client
-            
+        with patch('litellm.completion') as mock_completion:
             mock_response = MagicMock()
             mock_response.choices = [MagicMock()]
             mock_response.choices[0].message.content = "SCORE: 9\nREASONING: Great"
-            mock_client.chat.completions.create.return_value = mock_response
+            mock_completion.return_value = mock_response
             
             def test_func(x):
                 return "unused"

src/praisonai-agents/uv.lock

@@ -2422,7 +2422,7 @@ wheels = [
 
 [[package]]
 name = "praisonaiagents"
-version = "0.3.3"
+version = "0.4.0"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },

src/praisonai-ts/FEATURE_PARITY_TRACKER.json

@@ -0,0 +1,229 @@
+{
+  "version": "1.2.1",
+  "lastUpdated": "2024-12-26",
+  "implementationStatus": "Phase 4 Complete - Full Feature Parity",
+  "summary": {
+    "pythonCoreFeatures": 85,
+    "pythonWrapperFeatures": 45,
+    "typescriptFeatures": 75,
+    "gapCount": 10,
+    "priorityP0": 0,
+    "priorityP1": 3,
+    "priorityP2": 5,
+    "priorityP3": 2
+  },
+  "pythonCoreSDK": {
+    "path": "/Users/praison/praisonai-package/src/praisonai-agents/praisonaiagents",
+    "exports": [
+      "Agent", "ImageAgent", "ContextAgent", "DeepResearchAgent", "QueryRewriterAgent", "PromptExpanderAgent",
+      "PraisonAIAgents", "Agents", "Task", "Tools", "BaseTool", "ToolResult", "tool", "FunctionTool",
+      "ToolRegistry", "get_registry", "register_tool", "get_tool", "AutoAgents", "Session", "Memory",
+      "Knowledge", "Chunking", "db", "obs", "MCP", "Workflow", "Pipeline", "WorkflowStep", "WorkflowContext",
+      "StepResult", "Route", "Parallel", "Loop", "Repeat", "GuardrailResult", "LLMGuardrail",
+      "Handoff", "handoff", "FlowDisplay", "FastContext", "SkillManager", "SkillProperties",
+      "get_telemetry", "enable_telemetry", "MinimalTelemetry", "TelemetryCollector", "AGUI", "A2A"
+    ],
+    "modules": {
+      "agent": ["Agent", "ImageAgent", "ContextAgent", "DeepResearchAgent", "QueryRewriterAgent", "PromptExpanderAgent", "RouterAgent", "Handoff"],
+      "agents": ["PraisonAIAgents", "AutoAgents"],
+      "task": ["Task"],
+      "tools": ["Tools", "BaseTool", "ToolResult", "tool", "FunctionTool", "ToolRegistry", "40+ built-in tools"],
+      "llm": ["LLM", "OpenAIClient", "ModelRouter", "RateLimiter", "ModelCapabilities"],
+      "memory": ["Memory", "AutoMemory", "FileMemory", "RulesManager", "DocsManager", "Hooks"],
+      "knowledge": ["Knowledge", "Chunking", "VectorStore", "QueryEngine", "Readers", "Rerankers"],
+      "db": ["DbAdapter", "AsyncDbAdapter", "DbMessage", "DbToolCall", "DbRun", "DbSpan", "DbTrace"],
+      "obs": ["ObservabilityAdapter", "Span", "Trace", "16 provider integrations"],
+      "mcp": ["MCP", "MCPServer", "MCPSession", "MCPTransport", "MCPWebSocket", "MCPSSE", "MCPHTTPStream"],
+      "workflows": ["Workflow", "Pipeline", "WorkflowStep", "WorkflowContext", "StepResult", "Route", "Parallel", "Loop", "Repeat", "YAMLWorkflowParser"],
+      "guardrails": ["GuardrailResult", "LLMGuardrail"],
+      "eval": ["AccuracyEval", "PerformanceEval", "ReliabilityEval", "CriteriaEval"],
+      "skills": ["SkillManager", "SkillProperties", "SkillLoader", "SkillDiscovery", "SkillValidator"],
+      "telemetry": ["MinimalTelemetry", "TelemetryCollector", "PerformanceMonitor", "TokenCollector"],
+      "context": ["FastContext", "FastContextResult"],
+      "session": ["Session"],
+      "ui": ["AGUI", "A2A"]
+    }
+  },
+  "pythonWrapper": {
+    "path": "/Users/praison/praisonai-package/src/praisonai/praisonai",
+    "exports": ["PraisonAI"],
+    "cliFeatures": [
+      "slash_commands", "autonomy_mode", "cost_tracker", "repo_map", "interactive_tui",
+      "git_integration", "sandbox_executor", "agent_scheduler", "agents", "at_mentions",
+      "auto_memory", "background", "checkpoints", "compare", "eval", "external_agents",
+      "fast_context", "flow_display", "guardrail", "handoff", "hooks", "image", "jobs",
+      "knowledge", "mcp", "message_queue", "metrics", "n8n", "observability", "persistence",
+      "profile", "profiling", "router", "session", "skills", "telemetry", "todo", "tools", "workflow"
+    ]
+  },
+  "typescriptSDK": {
+    "path": "/Users/praison/praisonai-package/src/praisonai-ts/src",
+    "exports": [
+      "Agent", "ImageAgent", "ContextAgent", "DeepResearchAgent", "QueryRewriterAgent", "PromptExpanderAgent",
+      "RouterAgent", "Handoff", "AutoAgents", "Task", "BaseTool", "ToolResult", "tool", "FunctionTool",
+      "ToolRegistry", "createTool", "validateTool", "Session", "SessionManager", "Memory", "KnowledgeBase",
+      "Chunking", "MemoryAdapter", "createDbFactory", "Workflow", "parallel", "route", "Guardrail",
+      "GuardrailManager", "LLMGuardrail", "accuracyEval", "performanceEval", "reliabilityEval", "EvalSuite",
+      "MemoryObservabilityAdapter", "ConsoleObservabilityAdapter", "SkillManager", "TelemetryCollector",
+      "Plan", "PlanStep", "TodoList", "TodoItem", "PlanStorage",
+      "OpenAIProvider", "AnthropicProvider", "GoogleProvider", "createProvider"
+    ],
+    "modules": {
+      "agent": ["Agent", "ImageAgent", "ContextAgent", "DeepResearchAgent", "QueryRewriterAgent", "PromptExpanderAgent", "RouterAgent", "Handoff"],
+      "auto": ["AutoAgents", "createAutoAgents"],
+      "task": ["Task"],
+      "tools": ["BaseTool", "ToolResult", "tool", "FunctionTool", "ToolRegistry", "createTool", "validateTool", "arxivTools", "mcpSse"],
+      "llm": ["OpenAIProvider", "AnthropicProvider", "GoogleProvider", "createProvider", "BaseProvider"],
+      "memory": ["Memory", "createMemory", "MemoryEntry"],
+      "knowledge": ["KnowledgeBase", "Chunking", "GraphRAG", "GraphStore", "BaseReranker", "CohereReranker", "CrossEncoderReranker", "LLMReranker"],
+      "db": ["MemoryAdapter", "createDbFactory", "SQLiteAdapter", "UpstashRedisAdapter", "MemoryRedisAdapter", "NeonPostgresAdapter", "MemoryPostgresAdapter", "PostgresSessionStorage"],
+      "session": ["Session", "SessionManager"],
+      "workflows": ["Workflow", "parallel", "route", "loop", "repeat", "WorkflowStep", "WorkflowContext", "parseYAMLWorkflow", "createWorkflowFromYAML"],
+      "guardrails": ["Guardrail", "GuardrailManager", "LLMGuardrail", "builtInGuardrails"],
+      "eval": ["accuracyEval", "performanceEval", "reliabilityEval", "EvalSuite"],
+      "observability": ["MemoryObservabilityAdapter", "ConsoleObservabilityProvider", "LangfuseObservabilityProvider", "BaseObservabilityProvider"],
+      "skills": ["SkillManager", "parseSkillFile", "createSkillManager"],
+      "telemetry": ["TelemetryCollector", "getTelemetry", "enableTelemetry", "disableTelemetry"],
+      "planning": ["Plan", "PlanStep", "TodoList", "TodoItem", "PlanStorage"],
+      "cache": ["MemoryCache", "FileCache", "BaseCache", "createMemoryCache", "createFileCache"],
+      "events": ["EventEmitterPubSub", "AgentEventBus", "PubSub", "createEventBus", "createPubSub", "AgentEvents"],
+      "vector": ["BaseVectorStore", "MemoryVectorStore", "PineconeVectorStore", "WeaviateVectorStore", "QdrantVectorStore", "ChromaVectorStore"],
+      "voice": ["BaseVoiceProvider", "OpenAIVoiceProvider", "ElevenLabsVoiceProvider"],
+      "cli": ["chat", "listProviders", "version", "help"]
+    }
+  },
+  "gapMatrix": {
+    "P0_CoreParity": [
+      {"feature": "Multi-provider LLM support (OpenAI, Anthropic, Google)", "python": true, "typescript": true, "priority": "P0", "effort": "high", "status": "DONE"},
+      {"feature": "Streaming responses", "python": true, "typescript": true, "priority": "P0", "effort": "medium", "status": "DONE"},
+      {"feature": "Structured outputs (JSON schema)", "python": true, "typescript": true, "priority": "P0", "effort": "medium", "status": "DONE"},
+      {"feature": "Tool/function calling with validation", "python": true, "typescript": true, "priority": "P0", "effort": "medium", "status": "DONE"},
+      {"feature": "Session management (session_id, run_id)", "python": true, "typescript": true, "priority": "P0", "effort": "medium", "status": "DONE"},
+      {"feature": "Multi-agent orchestration patterns", "python": true, "typescript": true, "priority": "P0", "effort": "high", "status": "DONE"},
+      {"feature": "Agent handoff", "python": true, "typescript": true, "priority": "P0", "effort": "medium", "status": "DONE"},
+      {"feature": "Tool decorator (@tool)", "python": true, "typescript": true, "priority": "P0", "effort": "low", "status": "DONE"},
+      {"feature": "Tool registry", "python": true, "typescript": true, "priority": "P0", "effort": "medium", "status": "DONE"},
+      {"feature": "Async agent execution", "python": true, "typescript": true, "priority": "P0", "effort": "low", "status": "DONE"},
+      {"feature": "Error handling and retries", "python": true, "typescript": true, "priority": "P0", "effort": "medium", "status": "DONE"},
+      {"feature": "Verbose/debug logging", "python": true, "typescript": true, "priority": "P0", "effort": "low", "status": "DONE"}
+    ],
+    "P1_Persistence": [
+      {"feature": "Database adapter protocol", "python": true, "typescript": true, "priority": "P1", "effort": "high", "status": "DONE"},
+      {"feature": "SQLite adapter", "python": true, "typescript": false, "priority": "P1", "effort": "medium", "status": "TODO"},
+      {"feature": "PostgreSQL adapter", "python": true, "typescript": false, "priority": "P1", "effort": "medium", "status": "TODO"},
+      {"feature": "Redis adapter", "python": true, "typescript": false, "priority": "P1", "effort": "medium", "status": "TODO"},
+      {"feature": "Message persistence", "python": true, "typescript": true, "priority": "P1", "effort": "medium", "status": "DONE"},
+      {"feature": "Run/trace persistence", "python": true, "typescript": true, "priority": "P1", "effort": "medium", "status": "DONE"},
+      {"feature": "Memory persistence (vector)", "python": true, "typescript": true, "priority": "P1", "effort": "high", "status": "DONE"},
+      {"feature": "Knowledge base (RAG)", "python": true, "typescript": true, "priority": "P1", "effort": "high", "status": "DONE"},
+      {"feature": "Chunking strategies", "python": true, "typescript": true, "priority": "P1", "effort": "medium", "status": "DONE"},
+      {"feature": "Vector store integration", "python": true, "typescript": true, "priority": "P1", "effort": "high", "status": "DONE"},
+      {"feature": "Semantic search/recall", "python": true, "typescript": true, "priority": "P1", "effort": "high", "status": "DONE"},
+      {"feature": "Working memory", "python": true, "typescript": true, "priority": "P1", "effort": "medium", "status": "DONE"},
+      {"feature": "File-based memory", "python": true, "typescript": false, "priority": "P1", "effort": "medium", "status": "TODO"},
+      {"feature": "Auto-memory", "python": true, "typescript": false, "priority": "P1", "effort": "medium", "status": "TODO"},
+      {"feature": "Session export/import", "python": true, "typescript": true, "priority": "P1", "effort": "medium", "status": "DONE"}
+    ],
+    "P2_CLI": [
+      {"feature": "CLI entrypoint", "python": true, "typescript": true, "priority": "P2", "effort": "medium", "status": "DONE"},
+      {"feature": "Slash commands", "python": true, "typescript": false, "priority": "P2", "effort": "medium", "status": "TODO"},
+      {"feature": "Interactive TUI", "python": true, "typescript": false, "priority": "P2", "effort": "high", "status": "TODO"},
+      {"feature": "Cost tracking", "python": true, "typescript": false, "priority": "P2", "effort": "medium", "status": "TODO"},
+      {"feature": "Repo map", "python": true, "typescript": false, "priority": "P2", "effort": "high", "status": "TODO"},
+      {"feature": "Git integration", "python": true, "typescript": false, "priority": "P2", "effort": "medium", "status": "TODO"},
+      {"feature": "Sandbox executor", "python": true, "typescript": false, "priority": "P2", "effort": "medium", "status": "TODO"},
+      {"feature": "Autonomy modes", "python": true, "typescript": false, "priority": "P2", "effort": "medium", "status": "TODO"},
+      {"feature": "Agent scheduler", "python": true, "typescript": false, "priority": "P2", "effort": "high", "status": "TODO"},
+      {"feature": "Background jobs", "python": true, "typescript": false, "priority": "P2", "effort": "medium", "status": "TODO"},
+      {"feature": "Checkpoints", "python": true, "typescript": false, "priority": "P2", "effort": "medium", "status": "TODO"},
+      {"feature": "Flow display", "python": true, "typescript": false, "priority": "P2", "effort": "medium", "status": "TODO"},
+      {"feature": "Profiling", "python": true, "typescript": true, "priority": "P2", "effort": "medium", "status": "DONE"},
+      {"feature": "Metrics", "python": true, "typescript": true, "priority": "P2", "effort": "medium", "status": "DONE"},
+      {"feature": "External agent integrations", "python": true, "typescript": false, "priority": "P2", "effort": "high", "status": "TODO"},
+      {"feature": "N8N integration", "python": true, "typescript": false, "priority": "P2", "effort": "high", "status": "TODO"},
+      {"feature": "MCP CLI support", "python": true, "typescript": true, "priority": "P2", "effort": "medium", "status": "DONE"},
+      {"feature": "Skills CLI", "python": true, "typescript": true, "priority": "P2", "effort": "medium", "status": "DONE"},
+      {"feature": "Eval CLI", "python": true, "typescript": true, "priority": "P2", "effort": "medium", "status": "DONE"},
+      {"feature": "Workflow CLI", "python": true, "typescript": true, "priority": "P2", "effort": "medium", "status": "DONE"}
+    ],
+    "P3_Advanced": [
+      {"feature": "Workflows/Pipelines", "python": true, "typescript": true, "priority": "P3", "effort": "high", "status": "DONE"},
+      {"feature": "Route pattern", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "Parallel pattern", "python": true, "typescript": true, "priority": "P3", "effort": "low", "status": "DONE"},
+      {"feature": "Loop pattern", "python": true, "typescript": false, "priority": "P3", "effort": "medium", "status": "TODO"},
+      {"feature": "Repeat pattern", "python": true, "typescript": false, "priority": "P3", "effort": "medium", "status": "TODO"},
+      {"feature": "YAML workflow parser", "python": true, "typescript": false, "priority": "P3", "effort": "medium", "status": "TODO"},
+      {"feature": "Guardrails", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "LLM Guardrail", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "Evaluation framework", "python": true, "typescript": true, "priority": "P3", "effort": "high", "status": "DONE"},
+      {"feature": "Accuracy eval", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "Performance eval", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "Reliability eval", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "Criteria eval", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "Observability protocol", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "Telemetry", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "Performance monitoring", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "Token tracking", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"},
+      {"feature": "Skills system", "python": true, "typescript": true, "priority": "P3", "effort": "high", "status": "DONE"},
+      {"feature": "Fast context", "python": true, "typescript": false, "priority": "P3", "effort": "medium", "status": "TODO"},
+      {"feature": "Image agent", "python": true, "typescript": true, "priority": "P3", "effort": "medium", "status": "DONE"}
+    ]
+  },
+  "mastraCapabilities": {
+    "implemented": [
+      "Agent core", "Tool calling", "Streaming (partial)", "Multi-agent (partial)"
+    ],
+    "missing": [
+      "Memory with semantic recall", "Working memory", "Thread management", "Resource scoping",
+      "Storage abstraction", "Vector store integration", "Embeddings", "Evaluation scorers",
+      "Workflow engine", "Step execution", "Branching logic", "Event-driven workflows",
+      "MCP integration", "Voice/TTS", "Observability hooks", "Request context",
+      "Tool validation", "Tool suspend/resume", "Provider options per tool"
+    ]
+  },
+  "implementationPlan": {
+    "phase1_P0": {
+      "description": "Core agent parity - streaming, structured outputs, sessions, tool system",
+      "tasks": [
+        "Implement AI SDK provider abstraction (OpenAI, Anthropic, Google)",
+        "Add streaming response support with proper typing",
+        "Implement structured output with JSON schema/Zod",
+        "Add session management (session_id, run_id, trace_id)",
+        "Implement tool decorator and registry",
+        "Add agent handoff support",
+        "Improve error handling and retries"
+      ]
+    },
+    "phase2_P1": {
+      "description": "Persistence layer - db adapters, memory, knowledge",
+      "tasks": [
+        "Implement DbAdapter protocol",
+        "Add SQLite adapter",
+        "Add message/run/trace persistence",
+        "Implement Memory with persistence",
+        "Add Knowledge base (RAG) support",
+        "Implement vector store integration"
+      ]
+    },
+    "phase3_P2": {
+      "description": "CLI parity",
+      "tasks": [
+        "Create CLI entrypoint",
+        "Implement slash commands",
+        "Add cost tracking",
+        "Implement interactive mode"
+      ]
+    },
+    "phase4_P3": {
+      "description": "Advanced features",
+      "tasks": [
+        "Implement Workflow engine",
+        "Add workflow patterns (Route, Parallel, Loop, Repeat)",
+        "Implement Guardrails",
+        "Add Evaluation framework",
+        "Implement Observability hooks",
+        "Add Skills system"
+      ]
+    }
+  }
+}

src/praisonai-ts/jest.config.ts

@@ -4,7 +4,7 @@ const config: Config.InitialOptions = {
   preset: 'ts-jest',
   testEnvironment: 'node',
   roots: ['<rootDir>/tests'],
-  testMatch: ['**/*.main.test.ts', '**/*.spec.ts'],
+  testMatch: ['**/*.test.ts', '**/*.spec.ts'],
   moduleFileExtensions: ['ts', 'js', 'json'],
   coverageDirectory: 'coverage',
   collectCoverageFrom: [

src/praisonai-ts/package.json

@@ -1,9 +1,12 @@
 {
   "name": "praisonai",
-  "version": "1.0.19",
+  "version": "1.2.4",
   "description": "PraisonAI TypeScript AI Agents Framework - Node.js, npm, and Javascript AI Agents Framework",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
+  "bin": {
+    "praisonai-ts": "./dist/cli/index.js"
+  },
   "scripts": {
     "build": "tsc",
     "test": "jest",
@@ -62,7 +65,6 @@
     "fast-xml-parser": "^4.5.1",
     "node-fetch": "^2.6.9",
     "openai": "^4.81.0",
-    "praisonai": "^1.0.19",
     "@modelcontextprotocol/sdk": "^1.12.1"
   },
   "optionalDependencies": {

src/praisonai-ts/specs/cli-spec.v1.yaml

@@ -0,0 +1,266 @@
+# PraisonAI CLI Specification v1.0.0
+# This is the canonical contract for CLI behavior across all runtimes (Python, TypeScript, etc.)
+# Any CLI implementation MUST conform to this spec for parity.
+
+version: "1.0.0"
+spec_name: "praisonai-cli"
+
+# Binary names per ecosystem (NO COLLISION)
+binaries:
+  python: praisonai
+  typescript: praisonai-ts
+
+# Commands (all implementations MUST support)
+commands:
+  chat:
+    description: "Chat with an AI agent"
+    args:
+      - name: prompt
+        type: string
+        required: true
+        position: 0
+    flags:
+      - name: model
+        short: m
+        type: string
+        description: "Model to use (e.g., openai/gpt-4o-mini)"
+      - name: stream
+        short: s
+        type: boolean
+        default: false
+        description: "Enable streaming output"
+      - name: session
+        type: string
+        description: "Session ID for conversation continuity"
+
+  run:
+    description: "Run an agent with a task"
+    args:
+      - name: task
+        type: string
+        required: true
+        position: 0
+    flags:
+      - name: agent
+        short: a
+        type: string
+        description: "Agent configuration file or name"
+      - name: tools
+        short: t
+        type: string
+        description: "Comma-separated list of tools"
+
+  workflow:
+    description: "Execute a multi-agent workflow"
+    args:
+      - name: file
+        type: string
+        required: true
+        position: 0
+        description: "Workflow YAML file path"
+    flags:
+      - name: parallel
+        type: boolean
+        default: false
+        description: "Run workflow steps in parallel where possible"
+
+  eval:
+    description: "Evaluate agent performance"
+    subcommands:
+      accuracy:
+        description: "Run accuracy evaluation"
+        flags:
+          - name: input
+            type: string
+            required: true
+          - name: expected
+            type: string
+            required: true
+          - name: iterations
+            type: integer
+            default: 1
+      performance:
+        description: "Run performance benchmark"
+        flags:
+          - name: iterations
+            type: integer
+            default: 10
+          - name: warmup
+            type: integer
+            default: 2
+      reliability:
+        description: "Run reliability check"
+        flags:
+          - name: expected-tools
+            type: string
+            description: "Comma-separated expected tool calls"
+
+  providers:
+    description: "List available LLM providers"
+    flags: []
+
+  tools:
+    description: "List or manage tools"
+    subcommands:
+      list:
+        description: "List available tools"
+      info:
+        description: "Show tool information"
+        args:
+          - name: name
+            type: string
+            required: true
+            position: 0
+
+  version:
+    description: "Show CLI version"
+    flags: []
+
+  help:
+    description: "Show help information"
+    args:
+      - name: command
+        type: string
+        required: false
+        position: 0
+
+# Global flags (apply to all commands)
+global_flags:
+  - name: verbose
+    short: v
+    type: boolean
+    default: false
+    description: "Enable verbose output"
+  - name: config
+    short: c
+    type: string
+    description: "Path to config file"
+  - name: profile
+    short: p
+    type: string
+    description: "Profile name to use"
+  - name: output
+    short: o
+    type: string
+    enum: [json, text, pretty]
+    default: pretty
+    description: "Output format"
+  - name: json
+    type: boolean
+    default: false
+    description: "Shorthand for --output json"
+
+# Exit codes (MUST be identical across implementations)
+exit_codes:
+  success: 0
+  runtime_error: 1
+  invalid_arguments: 2
+  config_error: 3
+  network_error: 4
+  auth_error: 5
+
+# Output schema for JSON mode (MUST be byte-compatible)
+output_schema:
+  success:
+    type: object
+    properties:
+      success:
+        type: boolean
+        value: true
+      data:
+        type: object
+      meta:
+        type: object
+        properties:
+          duration_ms:
+            type: number
+          model:
+            type: string
+          tokens:
+            type: object
+            properties:
+              input:
+                type: integer
+              output:
+                type: integer
+  error:
+    type: object
+    properties:
+      success:
+        type: boolean
+        value: false
+      error:
+        type: object
+        properties:
+          code:
+            type: string
+          message:
+            type: string
+          details:
+            type: object
+
+# Environment variables (MUST be respected)
+environment:
+  PRAISONAI_MODEL:
+    description: "Default model to use"
+    example: "openai/gpt-4o-mini"
+  PRAISONAI_PROFILE:
+    description: "Default profile name"
+  PRAISONAI_VERBOSE:
+    description: "Enable verbose mode (true/false)"
+  PRAISONAI_CONFIG:
+    description: "Path to config file"
+  OPENAI_API_KEY:
+    description: "OpenAI API key"
+  ANTHROPIC_API_KEY:
+    description: "Anthropic API key"
+  GOOGLE_API_KEY:
+    description: "Google API key"
+
+# Config file schema reference
+config:
+  files:
+    - .praisonai.yaml
+    - .praisonai.json
+  resolution_order:
+    - cli_flags
+    - environment_variables
+    - project_config
+    - user_config
+    - defaults
+  schema:
+    model:
+      type: string
+      default: "openai/gpt-4o-mini"
+    verbose:
+      type: boolean
+      default: false
+    stream:
+      type: boolean
+      default: false
+    profiles:
+      type: object
+      additionalProperties:
+        type: object
+        properties:
+          model:
+            type: string
+          verbose:
+            type: boolean
+          stream:
+            type: boolean
+
+# Tool interface contract
+tool_schema:
+  name:
+    type: string
+    required: true
+  description:
+    type: string
+    required: true
+  inputs:
+    type: object
+    description: "JSON Schema for tool inputs"
+  outputs:
+    type: object
+    description: "JSON Schema for tool outputs"

src/praisonai-ts/specs/tests/chat.json

@@ -0,0 +1,64 @@
+{
+  "command": "chat",
+  "description": "Golden test fixtures for chat command JSON output parity",
+  "test_cases": [
+    {
+      "name": "simple_chat_success",
+      "input": {
+        "args": ["Hello, how are you?"],
+        "options": {
+          "output": "json"
+        }
+      },
+      "expected_schema": {
+        "success": true,
+        "data": {
+          "response": "string"
+        },
+        "meta": {
+          "duration_ms": "number",
+          "model": "string",
+          "tokens": {
+            "input": "number",
+            "output": "number"
+          }
+        }
+      }
+    },
+    {
+      "name": "chat_missing_prompt",
+      "input": {
+        "args": [],
+        "options": {
+          "output": "json"
+        }
+      },
+      "expected": {
+        "success": false,
+        "error": {
+          "code": "MISSING_ARGUMENT",
+          "message": "Please provide a prompt"
+        }
+      }
+    },
+    {
+      "name": "chat_with_model",
+      "input": {
+        "args": ["Test prompt"],
+        "options": {
+          "model": "openai/gpt-4o-mini",
+          "output": "json"
+        }
+      },
+      "expected_schema": {
+        "success": true,
+        "data": {
+          "response": "string"
+        },
+        "meta": {
+          "model": "openai/gpt-4o-mini"
+        }
+      }
+    }
+  ]
+}

src/praisonai-ts/specs/tests/run.json

@@ -0,0 +1,43 @@
+{
+  "command": "run",
+  "description": "Golden test fixtures for run command JSON output parity",
+  "test_cases": [
+    {
+      "name": "run_success",
+      "input": {
+        "args": ["Analyze this data"],
+        "options": {
+          "output": "json"
+        }
+      },
+      "expected_schema": {
+        "success": true,
+        "data": {
+          "result": "string",
+          "agent": "string",
+          "task": "string"
+        },
+        "meta": {
+          "duration_ms": "number",
+          "model": "string"
+        }
+      }
+    },
+    {
+      "name": "run_missing_task",
+      "input": {
+        "args": [],
+        "options": {
+          "output": "json"
+        }
+      },
+      "expected": {
+        "success": false,
+        "error": {
+          "code": "MISSING_ARGUMENT",
+          "message": "Please provide a task"
+        }
+      }
+    }
+  ]
+}

src/praisonai-ts/specs/tests/workflow.json

@@ -0,0 +1,43 @@
+{
+  "command": "workflow",
+  "description": "Golden test fixtures for workflow command JSON output parity",
+  "test_cases": [
+    {
+      "name": "workflow_success",
+      "input": {
+        "args": ["workflow.yaml"],
+        "options": {
+          "output": "json"
+        }
+      },
+      "expected_schema": {
+        "success": true,
+        "data": {
+          "workflow": "string",
+          "steps": "number",
+          "results": "object"
+        },
+        "meta": {
+          "duration_ms": "number",
+          "model": "string"
+        }
+      }
+    },
+    {
+      "name": "workflow_missing_file",
+      "input": {
+        "args": [],
+        "options": {
+          "output": "json"
+        }
+      },
+      "expected": {
+        "success": false,
+        "error": {
+          "code": "MISSING_ARGUMENT",
+          "message": "Please provide a workflow file path"
+        }
+      }
+    }
+  ]
+}

src/praisonai-ts/src/agent/context.ts

@@ -0,0 +1,159 @@
+/**
+ * Context Agent - Agent with enhanced context management
+ */
+
+import { createProvider, type LLMProvider, type Message } from '../llm/providers';
+import { Session } from '../session';
+import { KnowledgeBase, type SearchResult } from '../knowledge/rag';
+
+export interface ContextAgentConfig {
+  name?: string;
+  instructions: string;
+  llm?: string;
+  knowledgeBase?: KnowledgeBase;
+  contextWindow?: number;
+  maxContextTokens?: number;
+  verbose?: boolean;
+}
+
+export interface ContextMessage {
+  role: 'system' | 'user' | 'assistant';
+  content: string;
+  timestamp: number;
+  metadata?: Record<string, any>;
+}
+
+/**
+ * Context Agent - Agent with RAG and context management
+ */
+export class ContextAgent {
+  readonly name: string;
+  readonly instructions: string;
+  
+  private provider: LLMProvider;
+  private knowledgeBase?: KnowledgeBase;
+  private contextWindow: number;
+  private maxContextTokens: number;
+  private messages: ContextMessage[] = [];
+  private verbose: boolean;
+
+  constructor(config: ContextAgentConfig) {
+    this.name = config.name || `ContextAgent_${Math.random().toString(36).substr(2, 9)}`;
+    this.instructions = config.instructions;
+    this.provider = createProvider(config.llm || 'gpt-4o-mini');
+    this.knowledgeBase = config.knowledgeBase;
+    this.contextWindow = config.contextWindow ?? 10;
+    this.maxContextTokens = config.maxContextTokens ?? 4000;
+    this.verbose = config.verbose ?? false;
+  }
+
+  /**
+   * Chat with context awareness
+   */
+  async chat(prompt: string): Promise<{ text: string; context?: SearchResult[] }> {
+    // Add user message
+    this.messages.push({
+      role: 'user',
+      content: prompt,
+      timestamp: Date.now()
+    });
+
+    // Build context from knowledge base
+    let ragContext: SearchResult[] = [];
+    let contextString = '';
+    
+    if (this.knowledgeBase) {
+      ragContext = await this.knowledgeBase.search(prompt);
+      if (ragContext.length > 0) {
+        contextString = this.knowledgeBase.buildContext(ragContext);
+        if (this.verbose) {
+          console.log(`[ContextAgent] Found ${ragContext.length} relevant documents`);
+        }
+      }
+    }
+
+    // Build messages array with context
+    const systemPrompt = contextString
+      ? `${this.instructions}\n\nRelevant context:\n${contextString}`
+      : this.instructions;
+
+    const messages: Message[] = [
+      { role: 'system', content: systemPrompt },
+      ...this.getRecentMessages()
+    ];
+
+    // Generate response
+    const result = await this.provider.generateText({ messages });
+
+    // Add assistant message
+    this.messages.push({
+      role: 'assistant',
+      content: result.text,
+      timestamp: Date.now()
+    });
+
+    return {
+      text: result.text,
+      context: ragContext.length > 0 ? ragContext : undefined
+    };
+  }
+
+  /**
+   * Get recent messages within context window
+   */
+  private getRecentMessages(): Message[] {
+    const recent = this.messages.slice(-this.contextWindow);
+    return recent.map(m => ({
+      role: m.role,
+      content: m.content
+    }));
+  }
+
+  /**
+   * Add document to knowledge base
+   */
+  async addDocument(id: string, content: string, metadata?: Record<string, any>): Promise<void> {
+    if (!this.knowledgeBase) {
+      throw new Error('No knowledge base configured');
+    }
+    await this.knowledgeBase.add({ id, content, metadata });
+  }
+
+  /**
+   * Search knowledge base
+   */
+  async searchKnowledge(query: string, limit?: number): Promise<SearchResult[]> {
+    if (!this.knowledgeBase) {
+      return [];
+    }
+    return this.knowledgeBase.search(query, limit);
+  }
+
+  /**
+   * Clear conversation history
+   */
+  clearHistory(): void {
+    this.messages = [];
+  }
+
+  /**
+   * Get conversation history
+   */
+  getHistory(): ContextMessage[] {
+    return [...this.messages];
+  }
+
+  /**
+   * Set knowledge base
+   */
+  setKnowledgeBase(kb: KnowledgeBase): void {
+    this.knowledgeBase = kb;
+  }
+}
+
+/**
+ * Create a context agent
+ */
+export function createContextAgent(config: ContextAgentConfig): ContextAgent {
+  return new ContextAgent(config);
+}

src/praisonai-ts/src/agent/enhanced.ts

@@ -0,0 +1,337 @@
+/**
+ * Enhanced Agent - Agent with session management, provider abstraction, and tool support
+ */
+
+import { createProvider, type LLMProvider, type Message, type ToolCall, type GenerateTextResult } from '../llm/providers';
+import { Session, Run, Trace, getSessionManager } from '../session';
+import { FunctionTool, ToolRegistry, tool } from '../tools/decorator';
+import { Logger } from '../utils/logger';
+
+export interface EnhancedAgentConfig {
+  name?: string;
+  instructions: string;
+  llm?: string;
+  tools?: Array<FunctionTool | Function | { name: string; description?: string; parameters?: any; execute: Function }>;
+  session?: Session;
+  sessionId?: string;
+  verbose?: boolean;
+  stream?: boolean;
+  maxToolCalls?: number;
+  temperature?: number;
+  maxTokens?: number;
+  outputSchema?: any;
+}
+
+export interface ChatOptions {
+  stream?: boolean;
+  temperature?: number;
+  maxTokens?: number;
+  outputSchema?: any;
+  onToken?: (token: string) => void;
+}
+
+export interface ChatResult {
+  text: string;
+  structured?: any;
+  toolCalls?: ToolCall[];
+  usage: {
+    promptTokens: number;
+    completionTokens: number;
+    totalTokens: number;
+  };
+  runId: string;
+  sessionId: string;
+}
+
+/**
+ * Enhanced Agent with full feature support
+ */
+export class EnhancedAgent {
+  readonly name: string;
+  readonly instructions: string;
+  readonly sessionId: string;
+  
+  private provider: LLMProvider;
+  private session: Session;
+  private toolRegistry: ToolRegistry;
+  private verbose: boolean;
+  private stream: boolean;
+  private maxToolCalls: number;
+  private temperature: number;
+  private maxTokens?: number;
+  private outputSchema?: any;
+
+  constructor(config: EnhancedAgentConfig) {
+    this.name = config.name || `Agent_${Math.random().toString(36).substr(2, 9)}`;
+    this.instructions = config.instructions;
+    this.verbose = config.verbose ?? true;
+    this.stream = config.stream ?? true;
+    this.maxToolCalls = config.maxToolCalls ?? 10;
+    this.temperature = config.temperature ?? 0.7;
+    this.maxTokens = config.maxTokens;
+    this.outputSchema = config.outputSchema;
+
+    // Initialize provider
+    this.provider = createProvider(config.llm || 'gpt-4o-mini');
+
+    // Initialize session
+    if (config.session) {
+      this.session = config.session;
+    } else if (config.sessionId) {
+      this.session = getSessionManager().getOrCreate(config.sessionId);
+    } else {
+      this.session = getSessionManager().create();
+    }
+    this.sessionId = this.session.id;
+
+    // Initialize tool registry
+    this.toolRegistry = new ToolRegistry();
+    if (config.tools) {
+      this.registerTools(config.tools);
+    }
+
+    Logger.setVerbose(this.verbose);
+  }
+
+  private registerTools(tools: EnhancedAgentConfig['tools']): void {
+    if (!tools) return;
+
+    for (const t of tools) {
+      if (t instanceof FunctionTool) {
+        this.toolRegistry.register(t);
+      } else if (typeof t === 'function') {
+        // Convert function to tool
+        const funcName = t.name || `function_${Math.random().toString(36).substr(2, 9)}`;
+        this.toolRegistry.register(tool({
+          name: funcName,
+          description: `Function ${funcName}`,
+          execute: t as any,
+        }));
+      } else if (typeof t === 'object' && 'execute' in t) {
+        // Tool config object
+        this.toolRegistry.register(tool({
+          name: t.name,
+          description: t.description,
+          parameters: t.parameters,
+          execute: t.execute as any,
+        }));
+      }
+    }
+  }
+
+  /**
+   * Add a tool to the agent
+   */
+  addTool(t: FunctionTool | { name: string; description?: string; parameters?: any; execute: Function }): this {
+    if (t instanceof FunctionTool) {
+      this.toolRegistry.register(t);
+    } else {
+      this.toolRegistry.register(tool({
+        name: t.name,
+        description: t.description,
+        parameters: t.parameters,
+        execute: t.execute as any,
+      }));
+    }
+    return this;
+  }
+
+  /**
+   * Get all registered tools
+   */
+  getTools(): FunctionTool[] {
+    return this.toolRegistry.list();
+  }
+
+  /**
+   * Chat with the agent
+   */
+  async chat(prompt: string, options: ChatOptions = {}): Promise<ChatResult> {
+    const run = this.session.createRun().start();
+    const trace = run.createTrace({ name: 'chat' }).start();
+
+    try {
+      // Add user message to session
+      this.session.addMessage({ role: 'user', content: prompt });
+
+      // Build messages array
+      const messages: Message[] = [
+        { role: 'system', content: this.instructions },
+        ...this.session.getMessagesForLLM() as Message[],
+      ];
+
+      // Get tool definitions
+      const tools = this.toolRegistry.list().length > 0
+        ? this.toolRegistry.getDefinitions()
+        : undefined;
+
+      let result: GenerateTextResult;
+      let fullText = '';
+      let allToolCalls: ToolCall[] = [];
+      let iterations = 0;
+
+      // Tool calling loop
+      while (iterations < this.maxToolCalls) {
+        iterations++;
+
+        if (options.stream && !tools && options.onToken) {
+          // Streaming without tools
+          const stream = await this.provider.streamText({
+            messages,
+            temperature: options.temperature ?? this.temperature,
+            maxTokens: options.maxTokens ?? this.maxTokens,
+            onToken: options.onToken,
+          });
+
+          let usage = { promptTokens: 0, completionTokens: 0, totalTokens: 0 };
+          for await (const chunk of stream) {
+            if (chunk.text) fullText += chunk.text;
+            if (chunk.usage) usage = { ...usage, ...chunk.usage };
+          }
+
+          result = {
+            text: fullText,
+            usage,
+            finishReason: 'stop',
+          };
+          break;
+        } else if (options.outputSchema) {
+          // Structured output
+          const objResult = await this.provider.generateObject({
+            messages,
+            schema: options.outputSchema ?? this.outputSchema,
+            temperature: options.temperature ?? this.temperature,
+            maxTokens: options.maxTokens ?? this.maxTokens,
+          });
+
+          result = {
+            text: JSON.stringify(objResult.object),
+            usage: objResult.usage,
+            finishReason: 'stop',
+          };
+          fullText = result.text;
+          break;
+        } else {
+          // Regular generation with potential tool calls
+          result = await this.provider.generateText({
+            messages,
+            temperature: options.temperature ?? this.temperature,
+            maxTokens: options.maxTokens ?? this.maxTokens,
+            tools,
+          });
+
+          if (result.toolCalls && result.toolCalls.length > 0) {
+            allToolCalls.push(...result.toolCalls);
+
+            // Add assistant message with tool calls
+            messages.push({
+              role: 'assistant',
+              content: result.text || null,
+              tool_calls: result.toolCalls,
+            });
+
+            // Execute tool calls
+            for (const tc of result.toolCalls) {
+              const toolTrace = trace.createChild({ name: `tool:${tc.function.name}` }).start();
+              
+              try {
+                const toolFn = this.toolRegistry.get(tc.function.name);
+                if (!toolFn) {
+                  throw new Error(`Tool '${tc.function.name}' not found`);
+                }
+
+                const args = JSON.parse(tc.function.arguments);
+                const toolResult = await toolFn.execute(args, {
+                  agentName: this.name,
+                  sessionId: this.sessionId,
+                  runId: run.id,
+                });
+
+                const resultStr = typeof toolResult === 'string' 
+                  ? toolResult 
+                  : JSON.stringify(toolResult);
+
+                messages.push({
+                  role: 'tool',
+                  content: resultStr,
+                  tool_call_id: tc.id,
+                });
+
+                toolTrace.complete({ result: resultStr });
+              } catch (error: any) {
+                messages.push({
+                  role: 'tool',
+                  content: `Error: ${error.message}`,
+                  tool_call_id: tc.id,
+                });
+                toolTrace.fail(error);
+              }
+            }
+
+            // Continue loop to get final response
+            continue;
+          }
+
+          // No tool calls, we have our final response
+          fullText = result.text;
+          break;
+        }
+      }
+
+      // Add assistant message to session
+      this.session.addMessage({
+        role: 'assistant',
+        content: fullText,
+        tool_calls: allToolCalls.length > 0 ? allToolCalls : undefined,
+      });
+
+      trace.complete({ responseLength: fullText.length });
+      run.complete();
+
+      // Parse structured output if schema was provided
+      let structured: any;
+      if (options.outputSchema) {
+        try {
+          structured = JSON.parse(fullText);
+        } catch {
+          // Not valid JSON
+        }
+      }
+
+      return {
+        text: fullText,
+        structured,
+        toolCalls: allToolCalls.length > 0 ? allToolCalls : undefined,
+        usage: result!.usage,
+        runId: run.id,
+        sessionId: this.sessionId,
+      };
+    } catch (error: any) {
+      trace.fail(error);
+      run.fail(error);
+      throw error;
+    }
+  }
+
+  /**
+   * Start method for compatibility
+   */
+  async start(prompt: string, options?: ChatOptions): Promise<string> {
+    const result = await this.chat(prompt, options);
+    return result.text;
+  }
+
+  /**
+   * Get the session
+   */
+  getSession(): Session {
+    return this.session;
+  }
+
+  /**
+   * Clear conversation history
+   */
+  clearHistory(): void {
+    this.session.clearMessages();
+  }
+}

src/praisonai-ts/src/agent/handoff.ts

@@ -0,0 +1,162 @@
+/**
+ * Agent Handoff - Transfer conversations between agents
+ */
+
+import type { EnhancedAgent } from './enhanced';
+
+export interface HandoffConfig {
+  agent: EnhancedAgent;
+  name?: string;
+  description?: string;
+  condition?: (context: HandoffContext) => boolean;
+  transformContext?: (messages: any[]) => any[];
+}
+
+export interface HandoffContext {
+  messages: any[];
+  lastMessage: string;
+  topic?: string;
+  metadata?: Record<string, any>;
+}
+
+export interface HandoffResult {
+  handedOffTo: string;
+  response: string;
+  context: HandoffContext;
+}
+
+/**
+ * Handoff class - Represents a handoff target
+ */
+export class Handoff {
+  readonly targetAgent: EnhancedAgent;
+  readonly name: string;
+  readonly description: string;
+  readonly condition?: (context: HandoffContext) => boolean;
+  readonly transformContext?: (messages: any[]) => any[];
+
+  constructor(config: HandoffConfig) {
+    this.targetAgent = config.agent;
+    this.name = config.name || `handoff_to_${config.agent.name}`;
+    this.description = config.description || `Transfer conversation to ${config.agent.name}`;
+    this.condition = config.condition;
+    this.transformContext = config.transformContext;
+  }
+
+  /**
+   * Check if handoff should be triggered
+   */
+  shouldTrigger(context: HandoffContext): boolean {
+    if (this.condition) {
+      return this.condition(context);
+    }
+    return true;
+  }
+
+  /**
+   * Execute the handoff
+   */
+  async execute(context: HandoffContext): Promise<HandoffResult> {
+    let messages = context.messages;
+    
+    if (this.transformContext) {
+      messages = this.transformContext(messages);
+    }
+
+    // Transfer context to target agent
+    const response = await this.targetAgent.chat(context.lastMessage);
+
+    return {
+      handedOffTo: this.targetAgent.name,
+      response: response.text,
+      context: {
+        ...context,
+        messages,
+      },
+    };
+  }
+
+  /**
+   * Get tool definition for LLM
+   */
+  getToolDefinition(): { name: string; description: string; parameters: any } {
+    return {
+      name: this.name,
+      description: this.description,
+      parameters: {
+        type: 'object',
+        properties: {
+          reason: {
+            type: 'string',
+            description: 'Reason for the handoff',
+          },
+        },
+        required: [],
+      },
+    };
+  }
+}
+
+/**
+ * Create a handoff configuration
+ */
+export function handoff(config: HandoffConfig): Handoff {
+  return new Handoff(config);
+}
+
+/**
+ * Handoff filters - Common condition functions
+ */
+export const handoffFilters = {
+  /**
+   * Trigger handoff based on topic keywords
+   */
+  topic: (keywords: string | string[]) => {
+    const keywordList = Array.isArray(keywords) ? keywords : [keywords];
+    return (context: HandoffContext): boolean => {
+      const lastMessage = context.lastMessage.toLowerCase();
+      return keywordList.some(kw => lastMessage.includes(kw.toLowerCase()));
+    };
+  },
+
+  /**
+   * Trigger handoff based on metadata
+   */
+  metadata: (key: string, value: any) => {
+    return (context: HandoffContext): boolean => {
+      return context.metadata?.[key] === value;
+    };
+  },
+
+  /**
+   * Always trigger
+   */
+  always: () => {
+    return (): boolean => true;
+  },
+
+  /**
+   * Never trigger (manual only)
+   */
+  never: () => {
+    return (): boolean => false;
+  },
+
+  /**
+   * Combine multiple conditions with AND
+   */
+  and: (...conditions: Array<(context: HandoffContext) => boolean>) => {
+    return (context: HandoffContext): boolean => {
+      return conditions.every(cond => cond(context));
+    };
+  },
+
+  /**
+   * Combine multiple conditions with OR
+   */
+  or: (...conditions: Array<(context: HandoffContext) => boolean>) => {
+    return (context: HandoffContext): boolean => {
+      return conditions.some(cond => cond(context));
+    };
+  },
+};

src/praisonai-ts/src/agent/image.ts

@@ -0,0 +1,130 @@
+/**
+ * ImageAgent - Agent for image generation and analysis
+ */
+
+import { createProvider, type LLMProvider, type Message } from '../llm/providers';
+
+export interface ImageGenerationConfig {
+  prompt: string;
+  size?: '256x256' | '512x512' | '1024x1024' | '1792x1024' | '1024x1792';
+  quality?: 'standard' | 'hd';
+  style?: 'vivid' | 'natural';
+  n?: number;
+}
+
+export interface ImageAnalysisConfig {
+  imageUrl: string;
+  prompt?: string;
+  detail?: 'low' | 'high' | 'auto';
+}
+
+export interface ImageAgentConfig {
+  name?: string;
+  llm?: string;
+  imageModel?: string;
+  verbose?: boolean;
+}
+
+/**
+ * ImageAgent - Agent for image generation and analysis
+ */
+export class ImageAgent {
+  readonly name: string;
+  private provider: LLMProvider;
+  private imageModel: string;
+  private verbose: boolean;
+
+  constructor(config: ImageAgentConfig = {}) {
+    this.name = config.name || `ImageAgent_${Math.random().toString(36).substr(2, 9)}`;
+    this.provider = createProvider(config.llm || 'openai/gpt-4o-mini');
+    this.imageModel = config.imageModel || 'dall-e-3';
+    this.verbose = config.verbose ?? false;
+  }
+
+  /**
+   * Analyze an image
+   */
+  async analyze(config: ImageAnalysisConfig): Promise<string> {
+    const prompt = config.prompt || 'Describe this image in detail.';
+    
+    const messages: Message[] = [
+      {
+        role: 'user',
+        content: [
+          { type: 'text', text: prompt },
+          { 
+            type: 'image_url', 
+            image_url: { 
+              url: config.imageUrl,
+              detail: config.detail || 'auto'
+            } 
+          }
+        ] as any
+      }
+    ];
+
+    const result = await this.provider.generateText({ messages });
+    
+    if (this.verbose) {
+      console.log(`[ImageAgent] Analysis: ${result.text.substring(0, 100)}...`);
+    }
+
+    return result.text;
+  }
+
+  /**
+   * Generate an image (requires OpenAI DALL-E)
+   */
+  async generate(config: ImageGenerationConfig): Promise<string[]> {
+    // This would require direct OpenAI API call for image generation
+    // For now, return a placeholder
+    if (this.verbose) {
+      console.log(`[ImageAgent] Generating image: ${config.prompt}`);
+    }
+
+    throw new Error('Image generation requires direct OpenAI API integration. Use the OpenAI SDK directly for DALL-E.');
+  }
+
+  /**
+   * Chat with image context
+   */
+  async chat(prompt: string, imageUrl?: string): Promise<string> {
+    if (imageUrl) {
+      return this.analyze({ imageUrl, prompt });
+    }
+
+    const result = await this.provider.generateText({
+      messages: [{ role: 'user', content: prompt }]
+    });
+
+    return result.text;
+  }
+
+  /**
+   * Compare two images
+   */
+  async compare(imageUrl1: string, imageUrl2: string, prompt?: string): Promise<string> {
+    const comparePrompt = prompt || 'Compare these two images and describe the differences and similarities.';
+    
+    const messages: Message[] = [
+      {
+        role: 'user',
+        content: [
+          { type: 'text', text: comparePrompt },
+          { type: 'image_url', image_url: { url: imageUrl1 } },
+          { type: 'image_url', image_url: { url: imageUrl2 } }
+        ] as any
+      }
+    ];
+
+    const result = await this.provider.generateText({ messages });
+    return result.text;
+  }
+}
+
+/**
+ * Create an ImageAgent
+ */
+export function createImageAgent(config?: ImageAgentConfig): ImageAgent {
+  return new ImageAgent(config);
+}

src/praisonai-ts/src/agent/prompt-expander.ts

@@ -0,0 +1,112 @@
+/**
+ * PromptExpanderAgent - Expand and enhance prompts
+ */
+
+import { createProvider, type LLMProvider } from '../llm/providers';
+
+export type ExpandStrategy = 'detail' | 'context' | 'examples' | 'constraints' | 'auto';
+
+export interface ExpandResult {
+  original: string;
+  expanded: string;
+  strategy: ExpandStrategy;
+  additions: string[];
+}
+
+export interface PromptExpanderConfig {
+  name?: string;
+  llm?: string;
+  defaultStrategy?: ExpandStrategy;
+  verbose?: boolean;
+}
+
+/**
+ * PromptExpanderAgent - Expand prompts with more detail and context
+ */
+export class PromptExpanderAgent {
+  readonly name: string;
+  private provider: LLMProvider;
+  private defaultStrategy: ExpandStrategy;
+  private verbose: boolean;
+
+  constructor(config: PromptExpanderConfig = {}) {
+    this.name = config.name || `PromptExpander_${Math.random().toString(36).substr(2, 9)}`;
+    this.provider = createProvider(config.llm || 'openai/gpt-4o-mini');
+    this.defaultStrategy = config.defaultStrategy || 'auto';
+    this.verbose = config.verbose ?? false;
+  }
+
+  /**
+   * Expand a prompt
+   */
+  async expand(prompt: string, strategy?: ExpandStrategy): Promise<ExpandResult> {
+    const useStrategy = strategy || this.defaultStrategy;
+    const actualStrategy = useStrategy === 'auto' ? this.detectStrategy(prompt) : useStrategy;
+
+    const systemPrompt = this.getSystemPrompt(actualStrategy);
+    
+    const result = await this.provider.generateText({
+      messages: [
+        { role: 'system', content: systemPrompt },
+        { role: 'user', content: `Expand this prompt: ${prompt}` }
+      ]
+    });
+
+    const expanded = result.text;
+    const additions = this.extractAdditions(prompt, expanded);
+
+    if (this.verbose) {
+      console.log(`[PromptExpander] Strategy: ${actualStrategy}, Added ${additions.length} elements`);
+    }
+
+    return {
+      original: prompt,
+      expanded,
+      strategy: actualStrategy,
+      additions
+    };
+  }
+
+  /**
+   * Detect the best expansion strategy
+   */
+  detectStrategy(prompt: string): ExpandStrategy {
+    const words = prompt.split(/\s+/).length;
+    const lower = prompt.toLowerCase();
+    
+    if (words < 5) return 'detail';
+    if (lower.includes('why') || lower.includes('explain') || lower.includes('context')) return 'context';
+    if (lower.includes('example') || lower.includes('show') || lower.includes('demonstrate')) return 'examples';
+    if (lower.includes('must') || lower.includes('should') || lower.includes('require')) return 'constraints';
+    
+    return 'detail';
+  }
+
+  private getSystemPrompt(strategy: ExpandStrategy): string {
+    const prompts: Record<ExpandStrategy, string> = {
+      detail: 'Expand this prompt by adding specific details, requirements, and clarifications. Make it more precise and actionable.',
+      context: 'Expand this prompt by adding relevant background context, explaining the purpose, and providing necessary information.',
+      examples: 'Expand this prompt by adding concrete examples, sample inputs/outputs, and demonstrations of expected behavior.',
+      constraints: 'Expand this prompt by adding explicit constraints, requirements, limitations, and success criteria.',
+      auto: 'Expand this prompt to make it clearer, more specific, and more actionable. Add relevant details and context.'
+    };
+    return prompts[strategy];
+  }
+
+  private extractAdditions(original: string, expanded: string): string[] {
+    const originalWords = new Set(original.toLowerCase().split(/\s+/));
+    const expandedWords = expanded.toLowerCase().split(/\s+/);
+    
+    const newWords = expandedWords.filter(w => !originalWords.has(w) && w.length > 3);
+    const uniqueNew = [...new Set(newWords)];
+    
+    return uniqueNew.slice(0, 10);
+  }
+}
+
+/**
+ * Create a PromptExpanderAgent
+ */
+export function createPromptExpanderAgent(config?: PromptExpanderConfig): PromptExpanderAgent {
+  return new PromptExpanderAgent(config);
+}

src/praisonai-ts/src/agent/query-rewriter.ts

@@ -0,0 +1,106 @@
+/**
+ * QueryRewriterAgent - Rewrite and optimize queries
+ */
+
+import { createProvider, type LLMProvider } from '../llm/providers';
+
+export type RewriteStrategy = 'expand' | 'simplify' | 'decompose' | 'rephrase' | 'auto';
+
+export interface RewriteResult {
+  original: string;
+  rewritten: string[];
+  strategy: RewriteStrategy;
+  confidence: number;
+}
+
+export interface QueryRewriterConfig {
+  name?: string;
+  llm?: string;
+  defaultStrategy?: RewriteStrategy;
+  verbose?: boolean;
+}
+
+/**
+ * QueryRewriterAgent - Optimize and rewrite queries
+ */
+export class QueryRewriterAgent {
+  readonly name: string;
+  private provider: LLMProvider;
+  private defaultStrategy: RewriteStrategy;
+  private verbose: boolean;
+
+  constructor(config: QueryRewriterConfig = {}) {
+    this.name = config.name || `QueryRewriter_${Math.random().toString(36).substr(2, 9)}`;
+    this.provider = createProvider(config.llm || 'openai/gpt-4o-mini');
+    this.defaultStrategy = config.defaultStrategy || 'auto';
+    this.verbose = config.verbose ?? false;
+  }
+
+  /**
+   * Rewrite a query
+   */
+  async rewrite(query: string, strategy?: RewriteStrategy): Promise<RewriteResult> {
+    const useStrategy = strategy || this.defaultStrategy;
+    const actualStrategy = useStrategy === 'auto' ? this.detectStrategy(query) : useStrategy;
+
+    const prompt = this.buildPrompt(query, actualStrategy);
+    
+    const result = await this.provider.generateText({
+      messages: [
+        { role: 'system', content: this.getSystemPrompt(actualStrategy) },
+        { role: 'user', content: prompt }
+      ]
+    });
+
+    const rewritten = this.parseRewrittenQueries(result.text);
+
+    if (this.verbose) {
+      console.log(`[QueryRewriter] Strategy: ${actualStrategy}, Rewrites: ${rewritten.length}`);
+    }
+
+    return {
+      original: query,
+      rewritten,
+      strategy: actualStrategy,
+      confidence: rewritten.length > 0 ? 0.85 : 0.5
+    };
+  }
+
+  private detectStrategy(query: string): RewriteStrategy {
+    const words = query.split(/\s+/).length;
+    
+    if (words < 3) return 'expand';
+    if (words > 20) return 'simplify';
+    if (query.includes(' and ') || query.includes(' or ')) return 'decompose';
+    return 'rephrase';
+  }
+
+  private getSystemPrompt(strategy: RewriteStrategy): string {
+    const prompts: Record<RewriteStrategy, string> = {
+      expand: 'Expand this query with more context and detail. Generate 3 expanded versions.',
+      simplify: 'Simplify this query to its core intent. Generate 3 simpler versions.',
+      decompose: 'Break this query into smaller, focused sub-queries. Generate 3-5 sub-queries.',
+      rephrase: 'Rephrase this query in different ways while keeping the same meaning. Generate 3 versions.',
+      auto: 'Optimize this query for better search results. Generate 3 improved versions.'
+    };
+    return prompts[strategy] + ' Output one query per line.';
+  }
+
+  private buildPrompt(query: string, strategy: RewriteStrategy): string {
+    return `Query: ${query}\n\nRewrite using ${strategy} strategy:`;
+  }
+
+  private parseRewrittenQueries(response: string): string[] {
+    return response
+      .split('\n')
+      .map(line => line.replace(/^\d+[\.\)]\s*/, '').trim())
+      .filter(line => line.length > 0 && line.length < 500);
+  }
+}
+
+/**
+ * Create a QueryRewriterAgent
+ */
+export function createQueryRewriterAgent(config?: QueryRewriterConfig): QueryRewriterAgent {
+  return new QueryRewriterAgent(config);
+}

src/praisonai-ts/src/agent/research.ts

@@ -0,0 +1,162 @@
+/**
+ * DeepResearchAgent - Agent for comprehensive research tasks
+ */
+
+import { createProvider, type LLMProvider, type Message } from '../llm/providers';
+
+export interface Citation {
+  title: string;
+  url: string;
+  snippet?: string;
+}
+
+export interface ReasoningStep {
+  step: number;
+  thought: string;
+  action?: string;
+  result?: string;
+}
+
+export interface ResearchResponse {
+  answer: string;
+  citations: Citation[];
+  reasoning: ReasoningStep[];
+  confidence: number;
+}
+
+export interface DeepResearchConfig {
+  name?: string;
+  llm?: string;
+  maxIterations?: number;
+  searchTool?: (query: string) => Promise<Citation[]>;
+  verbose?: boolean;
+}
+
+/**
+ * DeepResearchAgent - Comprehensive research with citations
+ */
+export class DeepResearchAgent {
+  readonly name: string;
+  private provider: LLMProvider;
+  private maxIterations: number;
+  private searchTool?: (query: string) => Promise<Citation[]>;
+  private verbose: boolean;
+
+  constructor(config: DeepResearchConfig = {}) {
+    this.name = config.name || `ResearchAgent_${Math.random().toString(36).substr(2, 9)}`;
+    this.provider = createProvider(config.llm || 'openai/gpt-4o-mini');
+    this.maxIterations = config.maxIterations ?? 5;
+    this.searchTool = config.searchTool;
+    this.verbose = config.verbose ?? false;
+  }
+
+  /**
+   * Conduct deep research on a topic
+   */
+  async research(query: string): Promise<ResearchResponse> {
+    const reasoning: ReasoningStep[] = [];
+    const citations: Citation[] = [];
+    let iteration = 0;
+
+    // Step 1: Analyze the query
+    reasoning.push({
+      step: ++iteration,
+      thought: `Analyzing research query: "${query}"`,
+      action: 'query_analysis'
+    });
+
+    // Step 2: Generate search queries
+    const searchQueries = await this.generateSearchQueries(query);
+    reasoning.push({
+      step: ++iteration,
+      thought: `Generated ${searchQueries.length} search queries`,
+      action: 'generate_queries',
+      result: searchQueries.join(', ')
+    });
+
+    // Step 3: Execute searches if tool available
+    if (this.searchTool) {
+      for (const sq of searchQueries.slice(0, 3)) {
+        try {
+          const results = await this.searchTool(sq);
+          citations.push(...results);
+          reasoning.push({
+            step: ++iteration,
+            thought: `Searched for: "${sq}"`,
+            action: 'web_search',
+            result: `Found ${results.length} results`
+          });
+        } catch (error) {
+          if (this.verbose) {
+            console.log(`[Research] Search failed for: ${sq}`);
+          }
+        }
+      }
+    }
+
+    // Step 4: Synthesize answer
+    const answer = await this.synthesizeAnswer(query, citations);
+    reasoning.push({
+      step: ++iteration,
+      thought: 'Synthesizing final answer from gathered information',
+      action: 'synthesize',
+      result: 'Answer generated'
+    });
+
+    // Calculate confidence based on citations
+    const confidence = Math.min(0.5 + (citations.length * 0.1), 0.95);
+
+    return {
+      answer,
+      citations,
+      reasoning,
+      confidence
+    };
+  }
+
+  private async generateSearchQueries(query: string): Promise<string[]> {
+    const result = await this.provider.generateText({
+      messages: [
+        {
+          role: 'system',
+          content: 'Generate 3 search queries to research this topic. Output only the queries, one per line.'
+        },
+        { role: 'user', content: query }
+      ]
+    });
+
+    return result.text.split('\n').filter(q => q.trim().length > 0).slice(0, 3);
+  }
+
+  private async synthesizeAnswer(query: string, citations: Citation[]): Promise<string> {
+    const context = citations.length > 0
+      ? `\n\nRelevant sources:\n${citations.map(c => `- ${c.title}: ${c.snippet || ''}`).join('\n')}`
+      : '';
+
+    const result = await this.provider.generateText({
+      messages: [
+        {
+          role: 'system',
+          content: 'You are a research assistant. Provide a comprehensive, well-structured answer based on the available information. Cite sources when available.'
+        },
+        { role: 'user', content: `${query}${context}` }
+      ]
+    });
+
+    return result.text;
+  }
+
+  /**
+   * Set search tool
+   */
+  setSearchTool(tool: (query: string) => Promise<Citation[]>): void {
+    this.searchTool = tool;
+  }
+}
+
+/**
+ * Create a DeepResearchAgent
+ */
+export function createDeepResearchAgent(config?: DeepResearchConfig): DeepResearchAgent {
+  return new DeepResearchAgent(config);
+}

src/praisonai-ts/src/agent/router.ts

@@ -0,0 +1,146 @@
+/**
+ * Router Agent - Route requests to specialized agents
+ */
+
+import type { EnhancedAgent } from './enhanced';
+
+export interface RouteConfig {
+  agent: EnhancedAgent;
+  condition: (input: string, context?: RouteContext) => boolean | Promise<boolean>;
+  priority?: number;
+}
+
+export interface RouteContext {
+  history?: string[];
+  metadata?: Record<string, any>;
+}
+
+export interface RouterConfig {
+  name?: string;
+  routes: RouteConfig[];
+  defaultAgent?: EnhancedAgent;
+  verbose?: boolean;
+}
+
+/**
+ * Router Agent - Routes requests to the most appropriate agent
+ */
+export class RouterAgent {
+  readonly name: string;
+  private routes: RouteConfig[];
+  private defaultAgent?: EnhancedAgent;
+  private verbose: boolean;
+
+  constructor(config: RouterConfig) {
+    this.name = config.name || 'Router';
+    this.routes = config.routes.sort((a, b) => (b.priority || 0) - (a.priority || 0));
+    this.defaultAgent = config.defaultAgent;
+    this.verbose = config.verbose ?? false;
+  }
+
+  /**
+   * Route a request to the appropriate agent
+   */
+  async route(input: string, context?: RouteContext): Promise<{ agent: EnhancedAgent; response: string } | null> {
+    for (const route of this.routes) {
+      const matches = await route.condition(input, context);
+      if (matches) {
+        if (this.verbose) {
+          console.log(`[Router] Routing to: ${route.agent.name}`);
+        }
+        const response = await route.agent.chat(input);
+        return { agent: route.agent, response: response.text };
+      }
+    }
+
+    if (this.defaultAgent) {
+      if (this.verbose) {
+        console.log(`[Router] Using default agent: ${this.defaultAgent.name}`);
+      }
+      const response = await this.defaultAgent.chat(input);
+      return { agent: this.defaultAgent, response: response.text };
+    }
+
+    return null;
+  }
+
+  /**
+   * Add a route
+   */
+  addRoute(config: RouteConfig): this {
+    this.routes.push(config);
+    this.routes.sort((a, b) => (b.priority || 0) - (a.priority || 0));
+    return this;
+  }
+
+  /**
+   * Get all routes
+   */
+  getRoutes(): RouteConfig[] {
+    return [...this.routes];
+  }
+}
+
+/**
+ * Route condition helpers
+ */
+export const routeConditions = {
+  /**
+   * Match by keywords
+   */
+  keywords: (keywords: string | string[]) => {
+    const keywordList = Array.isArray(keywords) ? keywords : [keywords];
+    return (input: string): boolean => {
+      const lower = input.toLowerCase();
+      return keywordList.some(kw => lower.includes(kw.toLowerCase()));
+    };
+  },
+
+  /**
+   * Match by regex
+   */
+  pattern: (regex: RegExp) => {
+    return (input: string): boolean => regex.test(input);
+  },
+
+  /**
+   * Match by metadata
+   */
+  metadata: (key: string, value: any) => {
+    return (_input: string, context?: RouteContext): boolean => {
+      return context?.metadata?.[key] === value;
+    };
+  },
+
+  /**
+   * Always match (for default routes)
+   */
+  always: () => {
+    return (): boolean => true;
+  },
+
+  /**
+   * Combine conditions with AND
+   */
+  and: (...conditions: Array<(input: string, context?: RouteContext) => boolean>) => {
+    return (input: string, context?: RouteContext): boolean => {
+      return conditions.every(c => c(input, context));
+    };
+  },
+
+  /**
+   * Combine conditions with OR
+   */
+  or: (...conditions: Array<(input: string, context?: RouteContext) => boolean>) => {
+    return (input: string, context?: RouteContext): boolean => {
+      return conditions.some(c => c(input, context));
+    };
+  }
+};
+
+/**
+ * Create a router agent
+ */
+export function createRouter(config: RouterConfig): RouterAgent {
+  return new RouterAgent(config);
+}

src/praisonai-ts/src/agent/simple.ts

@@ -31,7 +31,7 @@ export class Agent {
     this.name = config.name || `Agent_${Math.random().toString(36).substr(2, 9)}`;
     this.verbose = config.verbose ?? process.env.PRAISON_VERBOSE !== 'false';
     this.pretty = config.pretty ?? process.env.PRAISON_PRETTY === 'true';
-    this.llm = config.llm || 'gpt-5-nano';
+    this.llm = config.llm || 'gpt-4o-mini';
     this.markdown = config.markdown ?? true;
     this.stream = config.stream ?? true;
     this.tools = config.tools;

src/praisonai-ts/src/auto/index.ts

@@ -0,0 +1,185 @@
+/**
+ * AutoAgents - Automatic agent generation from task descriptions
+ */
+
+import { createProvider, type LLMProvider, type Message } from '../llm/providers';
+
+export interface AgentConfig {
+  name: string;
+  role: string;
+  goal: string;
+  backstory?: string;
+  instructions?: string;
+  tools?: string[];
+}
+
+export interface TaskConfig {
+  description: string;
+  expectedOutput?: string;
+  agent?: string;
+}
+
+export interface TeamStructure {
+  agents: AgentConfig[];
+  tasks: TaskConfig[];
+  pattern: 'sequential' | 'parallel' | 'hierarchical';
+}
+
+export interface AutoAgentsConfig {
+  llm?: string;
+  pattern?: 'sequential' | 'parallel' | 'routing' | 'orchestrator-workers' | 'evaluator-optimizer';
+  singleAgent?: boolean;
+  verbose?: boolean;
+}
+
+/**
+ * AutoAgents - Generate agent configurations from task descriptions
+ */
+export class AutoAgents {
+  private provider: LLMProvider;
+  private pattern: string;
+  private singleAgent: boolean;
+  private verbose: boolean;
+
+  constructor(config: AutoAgentsConfig = {}) {
+    this.provider = createProvider(config.llm || 'openai/gpt-4o-mini');
+    this.pattern = config.pattern || 'sequential';
+    this.singleAgent = config.singleAgent ?? false;
+    this.verbose = config.verbose ?? false;
+  }
+
+  /**
+   * Generate agent configuration from task description
+   */
+  async generate(taskDescription: string): Promise<TeamStructure> {
+    const prompt = this.buildPrompt(taskDescription);
+    
+    const result = await this.provider.generateText({
+      messages: [
+        { role: 'system', content: this.getSystemPrompt() },
+        { role: 'user', content: prompt }
+      ]
+    });
+
+    return this.parseResponse(result.text);
+  }
+
+  /**
+   * Recommend a pattern for the task
+   */
+  recommendPattern(taskDescription: string): string {
+    const lower = taskDescription.toLowerCase();
+    
+    if (lower.includes('parallel') || lower.includes('concurrent') || lower.includes('simultaneously')) {
+      return 'parallel';
+    }
+    if (lower.includes('route') || lower.includes('classify') || lower.includes('categorize')) {
+      return 'routing';
+    }
+    if (lower.includes('orchestrat') || lower.includes('coordinat') || lower.includes('manage')) {
+      return 'orchestrator-workers';
+    }
+    if (lower.includes('evaluat') || lower.includes('optimi') || lower.includes('improv')) {
+      return 'evaluator-optimizer';
+    }
+    
+    return 'sequential';
+  }
+
+  /**
+   * Analyze task complexity
+   */
+  analyzeComplexity(taskDescription: string): 'simple' | 'moderate' | 'complex' {
+    const words = taskDescription.split(/\s+/).length;
+    const hasMultipleSteps = /step|then|after|before|first|second|third|finally/i.test(taskDescription);
+    const hasMultipleAgents = /team|multiple|several|different|various/i.test(taskDescription);
+    
+    if (words < 20 && !hasMultipleSteps && !hasMultipleAgents) {
+      return 'simple';
+    }
+    if (words > 100 || (hasMultipleSteps && hasMultipleAgents)) {
+      return 'complex';
+    }
+    return 'moderate';
+  }
+
+  private getSystemPrompt(): string {
+    return `You are an AI agent architect. Your job is to analyze task descriptions and generate optimal agent configurations.
+
+Output a JSON object with the following structure:
+{
+  "agents": [
+    {
+      "name": "AgentName",
+      "role": "Role description",
+      "goal": "Agent's goal",
+      "backstory": "Optional backstory",
+      "instructions": "Specific instructions",
+      "tools": ["tool1", "tool2"]
+    }
+  ],
+  "tasks": [
+    {
+      "description": "Task description",
+      "expectedOutput": "What the task should produce",
+      "agent": "AgentName"
+    }
+  ],
+  "pattern": "sequential|parallel|hierarchical"
+}
+
+Guidelines:
+- For simple tasks, use 1 agent
+- For moderate tasks, use 2-3 agents
+- For complex tasks, use 3-5 agents
+- Match the pattern to the task requirements
+- Be specific about roles and goals`;
+  }
+
+  private buildPrompt(taskDescription: string): string {
+    const complexity = this.analyzeComplexity(taskDescription);
+    const recommendedPattern = this.recommendPattern(taskDescription);
+    
+    return `Task Description: ${taskDescription}
+
+Complexity: ${complexity}
+Recommended Pattern: ${this.pattern || recommendedPattern}
+Single Agent Mode: ${this.singleAgent}
+
+Generate an optimal agent configuration for this task.`;
+  }
+
+  private parseResponse(response: string): TeamStructure {
+    try {
+      // Extract JSON from response
+      const jsonMatch = response.match(/\{[\s\S]*\}/);
+      if (jsonMatch) {
+        return JSON.parse(jsonMatch[0]);
+      }
+    } catch (error) {
+      // Fallback to default structure
+    }
+
+    // Default fallback
+    return {
+      agents: [{
+        name: 'GeneralAgent',
+        role: 'General purpose agent',
+        goal: 'Complete the assigned task',
+        instructions: 'Follow the task description carefully'
+      }],
+      tasks: [{
+        description: 'Complete the task',
+        agent: 'GeneralAgent'
+      }],
+      pattern: 'sequential'
+    };
+  }
+}
+
+/**
+ * Create an AutoAgents instance
+ */
+export function createAutoAgents(config?: AutoAgentsConfig): AutoAgents {
+  return new AutoAgents(config);
+}

src/praisonai-ts/src/cache/index.ts

@@ -0,0 +1,253 @@
+/**
+ * Cache System - In-memory and persistent caching for agents
+ * Inspired by mastra's cache module
+ */
+
+export interface CacheConfig {
+  name?: string;
+  ttl?: number; // Time to live in milliseconds
+  maxSize?: number; // Maximum number of entries
+}
+
+export interface CacheEntry<T = any> {
+  value: T;
+  createdAt: number;
+  expiresAt?: number;
+}
+
+/**
+ * Abstract base class for cache implementations
+ */
+export abstract class BaseCache {
+  readonly name: string;
+  
+  constructor(config: CacheConfig = {}) {
+    this.name = config.name || 'cache';
+  }
+
+  abstract get<T = any>(key: string): Promise<T | undefined>;
+  abstract set<T = any>(key: string, value: T, ttl?: number): Promise<void>;
+  abstract delete(key: string): Promise<boolean>;
+  abstract clear(): Promise<void>;
+  abstract has(key: string): Promise<boolean>;
+  abstract keys(): Promise<string[]>;
+  abstract size(): Promise<number>;
+  
+  // List operations
+  abstract listPush<T = any>(key: string, value: T): Promise<void>;
+  abstract listLength(key: string): Promise<number>;
+  abstract listRange<T = any>(key: string, start: number, end?: number): Promise<T[]>;
+}
+
+/**
+ * In-memory cache implementation
+ */
+export class MemoryCache extends BaseCache {
+  private cache: Map<string, CacheEntry> = new Map();
+  private lists: Map<string, any[]> = new Map();
+  private ttl?: number;
+  private maxSize?: number;
+
+  constructor(config: CacheConfig = {}) {
+    super(config);
+    this.ttl = config.ttl;
+    this.maxSize = config.maxSize;
+  }
+
+  async get<T = any>(key: string): Promise<T | undefined> {
+    const entry = this.cache.get(key);
+    if (!entry) return undefined;
+    
+    // Check expiration
+    if (entry.expiresAt && Date.now() > entry.expiresAt) {
+      this.cache.delete(key);
+      return undefined;
+    }
+    
+    return entry.value as T;
+  }
+
+  async set<T = any>(key: string, value: T, ttl?: number): Promise<void> {
+    // Enforce max size
+    if (this.maxSize && this.cache.size >= this.maxSize && !this.cache.has(key)) {
+      // Remove oldest entry
+      const firstKey = this.cache.keys().next().value;
+      if (firstKey) this.cache.delete(firstKey);
+    }
+
+    const effectiveTtl = ttl ?? this.ttl;
+    const entry: CacheEntry<T> = {
+      value,
+      createdAt: Date.now(),
+      expiresAt: effectiveTtl ? Date.now() + effectiveTtl : undefined
+    };
+    
+    this.cache.set(key, entry);
+  }
+
+  async delete(key: string): Promise<boolean> {
+    const existed = this.cache.has(key);
+    this.cache.delete(key);
+    this.lists.delete(key);
+    return existed;
+  }
+
+  async clear(): Promise<void> {
+    this.cache.clear();
+    this.lists.clear();
+  }
+
+  async has(key: string): Promise<boolean> {
+    const entry = this.cache.get(key);
+    if (!entry) return false;
+    if (entry.expiresAt && Date.now() > entry.expiresAt) {
+      this.cache.delete(key);
+      return false;
+    }
+    return true;
+  }
+
+  async keys(): Promise<string[]> {
+    return Array.from(this.cache.keys());
+  }
+
+  async size(): Promise<number> {
+    return this.cache.size;
+  }
+
+  async listPush<T = any>(key: string, value: T): Promise<void> {
+    if (!this.lists.has(key)) {
+      this.lists.set(key, []);
+    }
+    this.lists.get(key)!.push(value);
+  }
+
+  async listLength(key: string): Promise<number> {
+    return this.lists.get(key)?.length ?? 0;
+  }
+
+  async listRange<T = any>(key: string, start: number, end?: number): Promise<T[]> {
+    const list = this.lists.get(key) ?? [];
+    return list.slice(start, end) as T[];
+  }
+}
+
+/**
+ * File-based cache implementation
+ */
+export class FileCache extends BaseCache {
+  private cacheDir: string;
+  private fs: any;
+  private path: any;
+
+  constructor(config: CacheConfig & { cacheDir?: string } = {}) {
+    super(config);
+    this.cacheDir = config.cacheDir || '.cache';
+  }
+
+  private async ensureDir(): Promise<void> {
+    if (!this.fs) {
+      this.fs = await import('fs/promises');
+      this.path = await import('path');
+    }
+    try {
+      await this.fs.mkdir(this.cacheDir, { recursive: true });
+    } catch {}
+  }
+
+  private getFilePath(key: string): string {
+    const safeKey = key.replace(/[^a-zA-Z0-9-_]/g, '_');
+    return this.path.join(this.cacheDir, `${safeKey}.json`);
+  }
+
+  async get<T = any>(key: string): Promise<T | undefined> {
+    await this.ensureDir();
+    try {
+      const data = await this.fs.readFile(this.getFilePath(key), 'utf-8');
+      const entry: CacheEntry<T> = JSON.parse(data);
+      if (entry.expiresAt && Date.now() > entry.expiresAt) {
+        await this.delete(key);
+        return undefined;
+      }
+      return entry.value;
+    } catch {
+      return undefined;
+    }
+  }
+
+  async set<T = any>(key: string, value: T, ttl?: number): Promise<void> {
+    await this.ensureDir();
+    const entry: CacheEntry<T> = {
+      value,
+      createdAt: Date.now(),
+      expiresAt: ttl ? Date.now() + ttl : undefined
+    };
+    await this.fs.writeFile(this.getFilePath(key), JSON.stringify(entry));
+  }
+
+  async delete(key: string): Promise<boolean> {
+    await this.ensureDir();
+    try {
+      await this.fs.unlink(this.getFilePath(key));
+      return true;
+    } catch {
+      return false;
+    }
+  }
+
+  async clear(): Promise<void> {
+    await this.ensureDir();
+    try {
+      const files = await this.fs.readdir(this.cacheDir);
+      await Promise.all(
+        files.filter((f: string) => f.endsWith('.json'))
+          .map((f: string) => this.fs.unlink(this.path.join(this.cacheDir, f)))
+      );
+    } catch {}
+  }
+
+  async has(key: string): Promise<boolean> {
+    return (await this.get(key)) !== undefined;
+  }
+
+  async keys(): Promise<string[]> {
+    await this.ensureDir();
+    try {
+      const files = await this.fs.readdir(this.cacheDir);
+      return files
+        .filter((f: string) => f.endsWith('.json'))
+        .map((f: string) => f.replace('.json', ''));
+    } catch {
+      return [];
+    }
+  }
+
+  async size(): Promise<number> {
+    return (await this.keys()).length;
+  }
+
+  async listPush<T = any>(key: string, value: T): Promise<void> {
+    const list = (await this.get<T[]>(`list_${key}`)) || [];
+    list.push(value);
+    await this.set(`list_${key}`, list);
+  }
+
+  async listLength(key: string): Promise<number> {
+    const list = (await this.get<any[]>(`list_${key}`)) || [];
+    return list.length;
+  }
+
+  async listRange<T = any>(key: string, start: number, end?: number): Promise<T[]> {
+    const list = (await this.get<T[]>(`list_${key}`)) || [];
+    return list.slice(start, end);
+  }
+}
+
+// Factory functions
+export function createMemoryCache(config?: CacheConfig): MemoryCache {
+  return new MemoryCache(config);
+}
+
+export function createFileCache(config?: CacheConfig & { cacheDir?: string }): FileCache {
+  return new FileCache(config);
+}

src/praisonai-ts/src/cli/commands/auto.ts

@@ -0,0 +1,90 @@
+/**
+ * Auto command - AutoAgents for automatic agent generation
+ */
+
+import { AutoAgents, createAutoAgents } from '../../auto';
+import { resolveConfig } from '../config/resolve';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface AutoOptions {
+  model?: string;
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  pattern?: string;
+  agents?: number;
+}
+
+export async function execute(args: string[], options: AutoOptions): Promise<void> {
+  const topic = args.join(' ');
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+  const config = resolveConfig(options);
+
+  if (!topic) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a topic for auto-generation'));
+    } else {
+      await pretty.error('Please provide a topic for auto-generation');
+      await pretty.dim('Usage: praisonai-ts auto "Create a research team"');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const startTime = Date.now();
+
+  try {
+    if (outputFormat !== 'json') {
+      await pretty.info(`Generating agents for: "${topic}"`);
+    }
+
+    const autoAgents = createAutoAgents({
+      llm: config.model,
+      pattern: options.pattern as any,
+      verbose: options.verbose
+    });
+
+    const result = await autoAgents.generate(topic);
+
+    const duration = Date.now() - startTime;
+
+    if (outputFormat === 'json') {
+      outputJson(formatSuccess({
+        topic,
+        agents: result.agents,
+        tasks: result.tasks,
+        pattern: result.pattern
+      }, {
+        duration_ms: duration,
+        model: config.model
+      }));
+    } else {
+      await pretty.heading('Generated Team');
+      await pretty.plain(`Pattern: ${result.pattern}`);
+      await pretty.newline();
+      
+      await pretty.plain('Agents:');
+      for (const agent of result.agents) {
+        await pretty.plain(`  • ${agent.name}: ${agent.role}`);
+      }
+      
+      await pretty.newline();
+      await pretty.plain('Tasks:');
+      for (const task of result.tasks) {
+        await pretty.plain(`  • ${task.description?.substring(0, 60)}...`);
+      }
+      
+      await pretty.newline();
+      await pretty.success(`Generated in ${duration}ms`);
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}

src/praisonai-ts/src/cli/commands/autonomy.ts

@@ -0,0 +1,163 @@
+/**
+ * CLI command: autonomy
+ * Autonomy mode management for agent actions
+ */
+
+import { AutonomyManager, createAutonomyManager, MODE_POLICIES, type AutonomyMode } from '../features/autonomy-mode';
+
+let manager: AutonomyManager | null = null;
+
+function getManager(): AutonomyManager {
+  if (!manager) {
+    manager = createAutonomyManager();
+  }
+  return manager;
+}
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+
+  switch (subcommand) {
+    case 'status':
+      await handleStatus(isJson);
+      break;
+    case 'set':
+      await handleSet(args.slice(1), isJson);
+      break;
+    case 'policies':
+      await handlePolicies(args.slice(1), isJson);
+      break;
+    case 'reset':
+      await handleReset(isJson);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+async function handleStatus(isJson: boolean): Promise<void> {
+  const mgr = getManager();
+  const summary = mgr.getSummary();
+  const mode = mgr.getMode();
+  const actionCount = mgr.getActionCount();
+
+  if (isJson) {
+    console.log(JSON.stringify({
+      success: true,
+      mode,
+      actionCount,
+      policies: MODE_POLICIES[mode]
+    }, null, 2));
+  } else {
+    console.log(summary);
+  }
+}
+
+async function handleSet(args: string[], isJson: boolean): Promise<void> {
+  const mode = args[0] as AutonomyMode;
+  
+  if (!mode || !['suggest', 'auto_edit', 'full_auto'].includes(mode)) {
+    console.error('Error: Valid mode required (suggest, auto_edit, full_auto)');
+    process.exit(1);
+  }
+
+  const mgr = getManager();
+  mgr.setMode(mode);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, mode }));
+  } else {
+    console.log(`✓ Autonomy mode set to: ${mode}`);
+    console.log('\nPolicies for this mode:');
+    for (const policy of MODE_POLICIES[mode]) {
+      const status = policy.requiresApproval ? '⚠️ requires approval' : '✓ auto-approved';
+      console.log(`  ${policy.action}: ${status}`);
+    }
+  }
+}
+
+async function handlePolicies(args: string[], isJson: boolean): Promise<void> {
+  const mode = (args[0] as AutonomyMode) || 'suggest';
+  
+  if (!['suggest', 'auto_edit', 'full_auto'].includes(mode)) {
+    console.error('Error: Valid mode required (suggest, auto_edit, full_auto)');
+    process.exit(1);
+  }
+
+  const policies = MODE_POLICIES[mode];
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, mode, policies }, null, 2));
+  } else {
+    console.log(`Policies for mode: ${mode}\n`);
+    for (const policy of policies) {
+      const status = policy.requiresApproval ? '⚠️ requires approval' : '✓ auto-approved';
+      console.log(`  ${policy.action.padEnd(20)} ${status}`);
+    }
+  }
+}
+
+async function handleReset(isJson: boolean): Promise<void> {
+  const mgr = getManager();
+  mgr.clearRemembered();
+  mgr.resetActionCount();
+  mgr.setMode('suggest');
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, message: 'Autonomy state reset' }));
+  } else {
+    console.log('✓ Autonomy state reset');
+    console.log('  Mode: suggest');
+    console.log('  Remembered decisions: cleared');
+    console.log('  Action count: 0');
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'autonomy',
+    description: 'Autonomy mode management for agent actions',
+    subcommands: {
+      status: 'Show current autonomy status',
+      set: 'Set autonomy mode',
+      policies: 'Show policies for a mode',
+      reset: 'Reset autonomy state'
+    },
+    modes: {
+      suggest: 'Requires approval for most actions (default)',
+      auto_edit: 'Auto-approves file edits, requires approval for others',
+      full_auto: 'Auto-approves most actions (use with caution)'
+    },
+    flags: {
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts autonomy status',
+      'praisonai-ts autonomy set suggest',
+      'praisonai-ts autonomy set auto_edit',
+      'praisonai-ts autonomy set full_auto',
+      'praisonai-ts autonomy policies suggest',
+      'praisonai-ts autonomy reset'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('Autonomy - Agent action approval management\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nModes:');
+    for (const [mode, desc] of Object.entries(help.modes)) {
+      console.log(`  ${mode.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/cache.ts

@@ -0,0 +1,117 @@
+/**
+ * Cache command - Caching management
+ */
+
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface CacheOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: CacheOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'info':
+        await showInfo(outputFormat);
+        break;
+      case 'providers':
+        await listProviders(outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function showInfo(outputFormat: string): Promise<void> {
+  const info = {
+    feature: 'Cache',
+    description: 'Caching system for LLM responses and computations',
+    providers: [
+      { name: 'MemoryCache', description: 'In-memory cache (default)' },
+      { name: 'FileCache', description: 'File-based persistent cache' }
+    ],
+    capabilities: [
+      'Cache LLM responses',
+      'Reduce API costs',
+      'Improve response times',
+      'TTL-based expiration',
+      'Configurable cache keys'
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(info));
+  } else {
+    await pretty.heading('Cache');
+    await pretty.plain(info.description);
+    await pretty.newline();
+    await pretty.plain('Providers:');
+    for (const p of info.providers) {
+      await pretty.plain(`  • ${p.name}: ${p.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Capabilities:');
+    for (const cap of info.capabilities) {
+      await pretty.plain(`  • ${cap}`);
+    }
+  }
+}
+
+async function listProviders(outputFormat: string): Promise<void> {
+  const providers = [
+    { name: 'memory', description: 'In-memory cache', available: true },
+    { name: 'file', description: 'File-based cache', available: true }
+  ];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ providers }));
+  } else {
+    await pretty.heading('Cache Providers');
+    for (const p of providers) {
+      const status = p.available ? '✓' : '✗';
+      await pretty.plain(`  ${status} ${p.name.padEnd(15)} ${p.description}`);
+    }
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'cache',
+    description: 'Caching management for LLM responses',
+    subcommands: [
+      { name: 'info', description: 'Show cache feature information' },
+      { name: 'providers', description: 'List available cache providers' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Cache Command');
+    await pretty.plain(help.description);
+    await pretty.newline();
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(20)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/chat.ts

@@ -0,0 +1,114 @@
+/**
+ * Chat command - Chat with an AI agent
+ */
+
+import { createProvider } from '../../llm/providers';
+import { Session } from '../../session';
+import { resolveConfig } from '../config/resolve';
+import { printSuccess, printError, outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES, normalizeError } from '../output/errors';
+
+export interface ChatOptions {
+  model?: string;
+  stream?: boolean;
+  session?: string;
+  verbose?: boolean;
+  profile?: string;
+  config?: string;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: ChatOptions): Promise<void> {
+  const prompt = args[0];
+  
+  if (!prompt) {
+    if (options.json || options.output === 'json') {
+      printError(ERROR_CODES.MISSING_ARG, 'Please provide a prompt');
+    } else {
+      await pretty.error('Please provide a prompt');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  // Resolve config with precedence
+  const config = resolveConfig({
+    configPath: options.config,
+    profile: options.profile,
+    model: options.model,
+    verbose: options.verbose,
+    stream: options.stream
+  });
+
+  const startTime = Date.now();
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    const provider = createProvider(config.model);
+    const session = new Session({ id: options.session });
+    session.addMessage({ role: 'user', content: prompt });
+
+    let responseText = '';
+    let inputTokens = 0;
+    let outputTokens = 0;
+
+    if (config.stream && outputFormat !== 'json') {
+      // Streaming mode (only for non-JSON output)
+      const stream = await provider.streamText({
+        messages: [{ role: 'user', content: prompt }],
+        onToken: (token: string) => {
+          process.stdout.write(token);
+          responseText += token;
+        }
+      });
+
+      for await (const chunk of stream) {
+        // Stream is consumed by onToken
+      }
+      console.log(); // New line after streaming
+    } else {
+      // Non-streaming mode
+      const result = await provider.generateText({
+        messages: [{ role: 'user', content: prompt }]
+      });
+      responseText = result.text;
+      inputTokens = result.usage?.promptTokens || 0;
+      outputTokens = result.usage?.completionTokens || 0;
+
+      if (outputFormat === 'json') {
+        const duration = Date.now() - startTime;
+        outputJson(formatSuccess(
+          { response: responseText },
+          {
+            duration_ms: duration,
+            model: config.model,
+            tokens: {
+              input: inputTokens,
+              output: outputTokens
+            }
+          }
+        ));
+      } else {
+        console.log(responseText);
+      }
+    }
+
+    session.addMessage({ role: 'assistant', content: responseText });
+
+  } catch (error) {
+    const cliError = normalizeError(error);
+    
+    if (outputFormat === 'json') {
+      outputJson(formatError(cliError.code, cliError.message, cliError.details));
+    } else {
+      await pretty.error(cliError.message);
+      if (config.verbose && error instanceof Error && error.stack) {
+        await pretty.dim(error.stack);
+      }
+    }
+    
+    process.exit(cliError.exitCode);
+  }
+}

src/praisonai-ts/src/cli/commands/checkpoints.ts

@@ -0,0 +1,252 @@
+/**
+ * CLI command: checkpoints
+ * Session state checkpointing and recovery
+ */
+
+import { CheckpointManager, createCheckpointManager, createFileCheckpointStorage } from '../features/checkpoints';
+
+let manager: CheckpointManager | null = null;
+
+function getManager(storagePath?: string): CheckpointManager {
+  if (!manager) {
+    const storage = storagePath ? createFileCheckpointStorage(storagePath) : undefined;
+    manager = createCheckpointManager({ storage });
+  }
+  return manager;
+}
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+  const storagePath = options.storage as string | undefined;
+
+  switch (subcommand) {
+    case 'create':
+      await handleCreate(args.slice(1), options, isJson, storagePath);
+      break;
+    case 'list':
+      await handleList(isJson, storagePath);
+      break;
+    case 'get':
+      await handleGet(args.slice(1), isJson, storagePath);
+      break;
+    case 'restore':
+      await handleRestore(args.slice(1), isJson, storagePath);
+      break;
+    case 'delete':
+      await handleDelete(args.slice(1), isJson, storagePath);
+      break;
+    case 'export':
+      await handleExport(args.slice(1), isJson, storagePath);
+      break;
+    case 'import':
+      await handleImport(args.slice(1), isJson, storagePath);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+async function handleCreate(args: string[], options: Record<string, unknown>, isJson: boolean, storagePath?: string): Promise<void> {
+  const name = args[0] || `checkpoint-${Date.now()}`;
+  const mgr = getManager(storagePath);
+  
+  // Set state from options if provided
+  const state = options.state ? JSON.parse(options.state as string) : {};
+  mgr.setState(state);
+  
+  const checkpoint = await mgr.create(name, {
+    sessionId: options.session as string,
+    metadata: options.metadata ? JSON.parse(options.metadata as string) : undefined
+  });
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, checkpoint }, null, 2));
+  } else {
+    console.log(`✓ Checkpoint created: ${checkpoint.id}`);
+    console.log(`  Name: ${checkpoint.name}`);
+    console.log(`  Time: ${checkpoint.timestamp.toISOString()}`);
+  }
+}
+
+async function handleList(isJson: boolean, storagePath?: string): Promise<void> {
+  const mgr = getManager(storagePath);
+  const checkpoints = await mgr.list();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, checkpoints }, null, 2));
+  } else {
+    if (checkpoints.length === 0) {
+      console.log('No checkpoints found');
+    } else {
+      console.log('Checkpoints:');
+      for (const cp of checkpoints) {
+        console.log(`  ${cp.name} (${cp.id})`);
+        console.log(`    Created: ${cp.timestamp.toISOString()}`);
+        if (cp.sessionId) console.log(`    Session: ${cp.sessionId}`);
+      }
+    }
+  }
+}
+
+async function handleGet(args: string[], isJson: boolean, storagePath?: string): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Checkpoint ID is required');
+    process.exit(1);
+  }
+
+  const mgr = getManager(storagePath);
+  const checkpoint = await mgr.get(id);
+
+  if (!checkpoint) {
+    if (isJson) {
+      console.log(JSON.stringify({ success: false, error: 'Checkpoint not found' }));
+    } else {
+      console.error(`Checkpoint ${id} not found`);
+    }
+    process.exit(1);
+  }
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, checkpoint }, null, 2));
+  } else {
+    console.log(`Checkpoint: ${checkpoint.id}`);
+    console.log(`  Name: ${checkpoint.name}`);
+    console.log(`  Created: ${checkpoint.timestamp.toISOString()}`);
+    console.log(`  State: ${JSON.stringify(checkpoint.state, null, 2)}`);
+  }
+}
+
+async function handleRestore(args: string[], isJson: boolean, storagePath?: string): Promise<void> {
+  const id = args[0];
+  const mgr = getManager(storagePath);
+  
+  let checkpoint;
+  if (id) {
+    checkpoint = await mgr.restore(id);
+  } else {
+    checkpoint = await mgr.restoreLatest();
+  }
+
+  if (!checkpoint) {
+    if (isJson) {
+      console.log(JSON.stringify({ success: false, error: 'No checkpoint to restore' }));
+    } else {
+      console.error('No checkpoint to restore');
+    }
+    process.exit(1);
+  }
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, restored: checkpoint }, null, 2));
+  } else {
+    console.log(`✓ Restored checkpoint: ${checkpoint.id}`);
+    console.log(`  Name: ${checkpoint.name}`);
+    console.log(`  State keys: ${Object.keys(checkpoint.state).join(', ') || 'none'}`);
+  }
+}
+
+async function handleDelete(args: string[], isJson: boolean, storagePath?: string): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Checkpoint ID is required');
+    process.exit(1);
+  }
+
+  const mgr = getManager(storagePath);
+  await mgr.delete(id);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, deleted: id }));
+  } else {
+    console.log(`✓ Checkpoint ${id} deleted`);
+  }
+}
+
+async function handleExport(args: string[], isJson: boolean, storagePath?: string): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Checkpoint ID is required');
+    process.exit(1);
+  }
+
+  const mgr = getManager(storagePath);
+  const exported = await mgr.export(id);
+
+  if (!exported) {
+    console.error(`Checkpoint ${id} not found`);
+    process.exit(1);
+  }
+
+  console.log(exported);
+}
+
+async function handleImport(args: string[], isJson: boolean, storagePath?: string): Promise<void> {
+  const jsonData = args[0];
+  if (!jsonData) {
+    console.error('Error: JSON data is required');
+    process.exit(1);
+  }
+
+  const mgr = getManager(storagePath);
+  const checkpoint = await mgr.import(jsonData);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, imported: checkpoint }, null, 2));
+  } else {
+    console.log(`✓ Checkpoint imported: ${checkpoint.id}`);
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'checkpoints',
+    description: 'Session state checkpointing and recovery',
+    subcommands: {
+      create: 'Create a new checkpoint',
+      list: 'List all checkpoints',
+      get: 'Get checkpoint details',
+      restore: 'Restore from a checkpoint',
+      delete: 'Delete a checkpoint',
+      export: 'Export checkpoint as JSON',
+      import: 'Import checkpoint from JSON'
+    },
+    flags: {
+      '--storage': 'Path to checkpoint storage directory',
+      '--state': 'JSON state to save with checkpoint',
+      '--session': 'Session ID to associate',
+      '--metadata': 'JSON metadata',
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts checkpoints create my-checkpoint',
+      'praisonai-ts checkpoints create --state \'{"key": "value"}\'',
+      'praisonai-ts checkpoints list',
+      'praisonai-ts checkpoints restore <id>',
+      'praisonai-ts checkpoints restore  # restores latest',
+      'praisonai-ts checkpoints export <id> > checkpoint.json',
+      'praisonai-ts checkpoints import \'{"name": "imported"}\'',
+      'praisonai-ts checkpoints delete <id>'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('Checkpoints - Session state checkpointing\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nFlags:');
+    for (const [flag, desc] of Object.entries(help.flags)) {
+      console.log(`  ${flag.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/context.ts

@@ -0,0 +1,164 @@
+/**
+ * Context command - Manage conversation context
+ */
+
+import { createContextAgent } from '../../agent/context';
+import { resolveConfig } from '../config/resolve';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface ContextOptions {
+  model?: string;
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  maxMessages?: number;
+}
+
+export async function execute(args: string[], options: ContextOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const actionArgs = args.slice(1);
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+  const config = resolveConfig(options);
+
+  try {
+    switch (action) {
+      case 'chat':
+        await chatWithContext(actionArgs, options, config, outputFormat);
+        break;
+      case 'summarize':
+        await summarizeContext(actionArgs, options, config, outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function chatWithContext(args: string[], options: ContextOptions, config: any, outputFormat: string): Promise<void> {
+  const message = args.join(' ');
+  if (!message) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a message'));
+    } else {
+      await pretty.error('Please provide a message');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const startTime = Date.now();
+
+  if (outputFormat !== 'json') {
+    await pretty.info('Processing with context...');
+  }
+
+  const agent = createContextAgent({
+    llm: config.model,
+    instructions: 'You are a helpful assistant with context awareness.',
+    contextWindow: options.maxMessages || 10,
+    verbose: options.verbose
+  });
+
+  const result = await agent.chat(message);
+  const duration = Date.now() - startTime;
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      message,
+      response: result.text
+    }, {
+      duration_ms: duration,
+      model: config.model
+    }));
+  } else {
+    await pretty.heading('Response');
+    await pretty.plain(result.text);
+    await pretty.newline();
+    await pretty.success(`Completed in ${duration}ms`);
+  }
+}
+
+async function summarizeContext(args: string[], options: ContextOptions, config: any, outputFormat: string): Promise<void> {
+  const context = args.join(' ');
+  if (!context) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide context to summarize'));
+    } else {
+      await pretty.error('Please provide context to summarize');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const startTime = Date.now();
+
+  if (outputFormat !== 'json') {
+    await pretty.info('Summarizing context...');
+  }
+
+  const agent = createContextAgent({
+    llm: config.model,
+    instructions: 'You are a summarization assistant. Provide concise summaries.',
+    verbose: options.verbose
+  });
+
+  // Use chat to summarize
+  const result = await agent.chat(`Please summarize the following text concisely:\n\n${context}`);
+  const duration = Date.now() - startTime;
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      originalLength: context.length,
+      summary: result.text
+    }, {
+      duration_ms: duration,
+      model: config.model
+    }));
+  } else {
+    await pretty.heading('Summary');
+    await pretty.plain(result.text);
+    await pretty.newline();
+    await pretty.dim(`Original: ${context.length} chars`);
+    await pretty.success(`Summarized in ${duration}ms`);
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'context',
+    subcommands: [
+      { name: 'chat <message>', description: 'Chat with context management' },
+      { name: 'summarize <text>', description: 'Summarize context' },
+      { name: 'help', description: 'Show this help' }
+    ],
+    flags: [
+      { name: '--max-messages', description: 'Maximum messages to keep in context' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Context Command');
+    await pretty.plain('Manage conversation context\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(25)} ${cmd.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Flags:');
+    for (const flag of help.flags) {
+      await pretty.plain(`  ${flag.name.padEnd(20)} ${flag.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/cost.ts

@@ -0,0 +1,153 @@
+/**
+ * CLI command: cost
+ * Token usage and cost tracking
+ */
+
+import { CostTracker, createCostTracker, MODEL_PRICING, formatCost } from '../features/cost-tracker';
+
+let tracker: CostTracker | null = null;
+
+function getTracker(): CostTracker {
+  if (!tracker) {
+    tracker = createCostTracker();
+  }
+  return tracker;
+}
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+
+  switch (subcommand) {
+    case 'summary':
+      await handleSummary(isJson);
+      break;
+    case 'add':
+      await handleAdd(args.slice(1), options, isJson);
+      break;
+    case 'reset':
+      await handleReset(isJson);
+      break;
+    case 'pricing':
+      await handlePricing(args.slice(1), isJson);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+async function handleSummary(isJson: boolean): Promise<void> {
+  const t = getTracker();
+  const stats = t.getStats();
+  const breakdown = t.getBreakdownByModel();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, stats, breakdown }, null, 2));
+  } else {
+    console.log(t.getSummary());
+    
+    if (Object.keys(breakdown).length > 0) {
+      console.log('\nBreakdown by model:');
+      for (const [model, data] of Object.entries(breakdown)) {
+        console.log(`  ${model}: ${data.tokens} tokens, ${formatCost(data.cost)}, ${data.requests} requests`);
+      }
+    }
+  }
+}
+
+async function handleAdd(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const model = args[0] || 'gpt-4o-mini';
+  const inputTokens = parseInt(args[1] || '0');
+  const outputTokens = parseInt(args[2] || '0');
+
+  if (isNaN(inputTokens) || isNaN(outputTokens)) {
+    console.error('Error: Invalid token counts');
+    process.exit(1);
+  }
+
+  const t = getTracker();
+  const request = t.addUsage(model, inputTokens, outputTokens);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, request }, null, 2));
+  } else {
+    console.log(`✓ Added usage: ${model}`);
+    console.log(`  Input: ${inputTokens} tokens`);
+    console.log(`  Output: ${outputTokens} tokens`);
+    console.log(`  Cost: ${formatCost(request.cost)}`);
+  }
+}
+
+async function handleReset(isJson: boolean): Promise<void> {
+  const t = getTracker();
+  t.reset();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, message: 'Cost tracker reset' }));
+  } else {
+    console.log('✓ Cost tracker reset');
+  }
+}
+
+async function handlePricing(args: string[], isJson: boolean): Promise<void> {
+  const model = args[0];
+
+  if (model) {
+    const pricing = MODEL_PRICING[model] || MODEL_PRICING['default'];
+    if (isJson) {
+      console.log(JSON.stringify({ success: true, model, pricing }, null, 2));
+    } else {
+      console.log(`Pricing for ${model}:`);
+      console.log(`  Input: $${pricing.inputCostPer1k}/1K tokens`);
+      console.log(`  Output: $${pricing.outputCostPer1k}/1K tokens`);
+    }
+  } else {
+    if (isJson) {
+      console.log(JSON.stringify({ success: true, pricing: MODEL_PRICING }, null, 2));
+    } else {
+      console.log('Model Pricing (per 1K tokens):\n');
+      for (const [name, pricing] of Object.entries(MODEL_PRICING)) {
+        if (name === 'default') continue;
+        console.log(`  ${name.padEnd(30)} in: $${pricing.inputCostPer1k.toFixed(5)}  out: $${pricing.outputCostPer1k.toFixed(5)}`);
+      }
+    }
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'cost',
+    description: 'Token usage and cost tracking',
+    subcommands: {
+      summary: 'Show cost summary',
+      add: 'Add token usage',
+      reset: 'Reset cost tracker',
+      pricing: 'Show model pricing'
+    },
+    flags: {
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts cost summary',
+      'praisonai-ts cost add gpt-4o 1000 500',
+      'praisonai-ts cost pricing',
+      'praisonai-ts cost pricing gpt-4o',
+      'praisonai-ts cost reset'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('Cost - Token usage and cost tracking\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/db.ts

@@ -0,0 +1,123 @@
+/**
+ * DB command - Database adapter management
+ */
+
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface DbOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: DbOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'info':
+        await showInfo(outputFormat);
+        break;
+      case 'adapters':
+        await listAdapters(outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function showInfo(outputFormat: string): Promise<void> {
+  const info = {
+    feature: 'Database Adapters',
+    description: 'Database adapters for persistence and session storage',
+    adapters: [
+      { name: 'SQLiteAdapter', description: 'SQLite database adapter' },
+      { name: 'UpstashRedisAdapter', description: 'Upstash Redis adapter' },
+      { name: 'MemoryRedisAdapter', description: 'In-memory Redis-compatible adapter' },
+      { name: 'NeonPostgresAdapter', description: 'Neon PostgreSQL adapter' },
+      { name: 'MemoryPostgresAdapter', description: 'In-memory PostgreSQL-compatible adapter' },
+      { name: 'PostgresSessionStorage', description: 'PostgreSQL session storage' }
+    ],
+    capabilities: [
+      'Store conversation history',
+      'Persist agent state',
+      'Session management',
+      'Message storage and retrieval',
+      'Trace logging'
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(info));
+  } else {
+    await pretty.heading('Database Adapters');
+    await pretty.plain(info.description);
+    await pretty.newline();
+    await pretty.plain('Available Adapters:');
+    for (const a of info.adapters) {
+      await pretty.plain(`  • ${a.name}: ${a.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Capabilities:');
+    for (const cap of info.capabilities) {
+      await pretty.plain(`  • ${cap}`);
+    }
+  }
+}
+
+async function listAdapters(outputFormat: string): Promise<void> {
+  const adapters = [
+    { name: 'sqlite', description: 'SQLite database', available: true },
+    { name: 'redis', description: 'Redis (Upstash)', available: true },
+    { name: 'postgres', description: 'PostgreSQL (Neon)', available: true },
+    { name: 'memory', description: 'In-memory adapters', available: true }
+  ];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ adapters }));
+  } else {
+    await pretty.heading('Database Adapters');
+    for (const a of adapters) {
+      const status = a.available ? '✓' : '✗';
+      await pretty.plain(`  ${status} ${a.name.padEnd(15)} ${a.description}`);
+    }
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'db',
+    description: 'Database adapter management',
+    subcommands: [
+      { name: 'info', description: 'Show database adapter information' },
+      { name: 'adapters', description: 'List available database adapters' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Database Command');
+    await pretty.plain(help.description);
+    await pretty.newline();
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(20)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/eval.ts

@@ -0,0 +1,283 @@
+/**
+ * Eval command - Evaluate agent performance
+ */
+
+import { Agent } from '../../agent';
+import { resolveConfig } from '../config/resolve';
+import { printSuccess, printError, outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES, normalizeError } from '../output/errors';
+
+export interface EvalOptions {
+  // Accuracy subcommand
+  input?: string;
+  expected?: string;
+  iterations?: number;
+  // Performance subcommand
+  warmup?: number;
+  // Reliability subcommand
+  'expected-tools'?: string;
+  // Common
+  model?: string;
+  verbose?: boolean;
+  profile?: string;
+  config?: string;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+interface AccuracyResult {
+  iteration: number;
+  output: string;
+  score: number;
+  passed: boolean;
+}
+
+interface PerformanceResult {
+  iteration: number;
+  duration_ms: number;
+}
+
+export async function execute(args: string[], options: EvalOptions): Promise<void> {
+  const subcommand = args[0];
+  
+  if (!subcommand || !['accuracy', 'performance', 'reliability'].includes(subcommand)) {
+    if (options.json || options.output === 'json') {
+      printError(ERROR_CODES.INVALID_ARGS, 'Please specify a subcommand: accuracy, performance, or reliability');
+    } else {
+      await pretty.error('Please specify a subcommand: accuracy, performance, or reliability');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const config = resolveConfig({
+    configPath: options.config,
+    profile: options.profile,
+    model: options.model,
+    verbose: options.verbose
+  });
+
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (subcommand) {
+      case 'accuracy':
+        await runAccuracyEval(options, config, outputFormat);
+        break;
+      case 'performance':
+        await runPerformanceEval(options, config, outputFormat);
+        break;
+      case 'reliability':
+        await runReliabilityEval(options, config, outputFormat);
+        break;
+    }
+  } catch (error) {
+    const cliError = normalizeError(error);
+    
+    if (outputFormat === 'json') {
+      outputJson(formatError(cliError.code, cliError.message, cliError.details));
+    } else {
+      await pretty.error(cliError.message);
+      if (config.verbose && error instanceof Error && error.stack) {
+        await pretty.dim(error.stack);
+      }
+    }
+    
+    process.exit(cliError.exitCode);
+  }
+}
+
+async function runAccuracyEval(
+  options: EvalOptions,
+  config: { model: string; verbose: boolean },
+  outputFormat: string
+): Promise<void> {
+  if (!options.input) {
+    throw new Error('--input is required for accuracy evaluation');
+  }
+  if (!options.expected) {
+    throw new Error('--expected is required for accuracy evaluation');
+  }
+
+  const iterations = options.iterations || 1;
+  const results: AccuracyResult[] = [];
+  const startTime = Date.now();
+
+  const agent = new Agent({
+    name: 'Eval Agent',
+    instructions: 'You are a helpful AI assistant.',
+    llm: config.model,
+    verbose: config.verbose
+  });
+
+  for (let i = 0; i < iterations; i++) {
+    const output = await agent.start(options.input);
+    
+    // Simple similarity check (in production, use LLM-as-judge)
+    const similarity = calculateSimilarity(output, options.expected);
+    const score = Math.round(similarity * 10);
+    
+    results.push({
+      iteration: i + 1,
+      output,
+      score,
+      passed: score >= 7
+    });
+  }
+
+  const duration = Date.now() - startTime;
+  const avgScore = results.reduce((sum, r) => sum + r.score, 0) / results.length;
+  const passRate = results.filter(r => r.passed).length / results.length;
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(
+      {
+        type: 'accuracy',
+        results,
+        summary: {
+          avg_score: avgScore,
+          pass_rate: passRate,
+          iterations
+        }
+      },
+      { duration_ms: duration, model: config.model }
+    ));
+  } else {
+    await pretty.heading('Accuracy Evaluation Results');
+    await pretty.keyValue({
+      'Iterations': iterations,
+      'Average Score': avgScore.toFixed(2),
+      'Pass Rate': `${(passRate * 100).toFixed(1)}%`,
+      'Duration': `${duration}ms`
+    });
+  }
+}
+
+async function runPerformanceEval(
+  options: EvalOptions,
+  config: { model: string; verbose: boolean },
+  outputFormat: string
+): Promise<void> {
+  const iterations = options.iterations || 10;
+  const warmup = options.warmup || 2;
+  const results: PerformanceResult[] = [];
+
+  const agent = new Agent({
+    name: 'Perf Agent',
+    instructions: 'You are a helpful AI assistant.',
+    llm: config.model,
+    verbose: false // Disable verbose for performance testing
+  });
+
+  const testPrompt = 'Say "hello" and nothing else.';
+
+  // Warmup runs
+  for (let i = 0; i < warmup; i++) {
+    await agent.start(testPrompt);
+  }
+
+  // Actual runs
+  for (let i = 0; i < iterations; i++) {
+    const start = Date.now();
+    await agent.start(testPrompt);
+    const duration = Date.now() - start;
+    
+    results.push({
+      iteration: i + 1,
+      duration_ms: duration
+    });
+  }
+
+  const durations = results.map(r => r.duration_ms);
+  const avg = durations.reduce((a, b) => a + b, 0) / durations.length;
+  const min = Math.min(...durations);
+  const max = Math.max(...durations);
+  const sorted = [...durations].sort((a, b) => a - b);
+  const p95 = sorted[Math.floor(sorted.length * 0.95)];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(
+      {
+        type: 'performance',
+        results,
+        summary: {
+          avg_ms: avg,
+          min_ms: min,
+          max_ms: max,
+          p95_ms: p95,
+          iterations,
+          warmup_runs: warmup
+        }
+      },
+      { model: config.model }
+    ));
+  } else {
+    await pretty.heading('Performance Evaluation Results');
+    await pretty.keyValue({
+      'Iterations': iterations,
+      'Warmup Runs': warmup,
+      'Avg Duration': `${avg.toFixed(2)}ms`,
+      'Min Duration': `${min}ms`,
+      'Max Duration': `${max}ms`,
+      'P95 Duration': `${p95}ms`
+    });
+  }
+}
+
+async function runReliabilityEval(
+  options: EvalOptions,
+  config: { model: string; verbose: boolean },
+  outputFormat: string
+): Promise<void> {
+  const expectedTools = options['expected-tools']?.split(',').map(t => t.trim()) || [];
+
+  if (expectedTools.length === 0) {
+    throw new Error('--expected-tools is required for reliability evaluation');
+  }
+
+  // For now, simulate reliability check
+  // In production, this would track actual tool calls
+  const results = {
+    expected: expectedTools,
+    called: expectedTools, // Simulated
+    missing: [] as string[],
+    unexpected: [] as string[]
+  };
+
+  const passed = results.missing.length === 0;
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      type: 'reliability',
+      status: passed ? 'PASSED' : 'FAILED',
+      results
+    }));
+  } else {
+    await pretty.heading('Reliability Evaluation Results');
+    if (passed) {
+      await pretty.success('All expected tools were called');
+    } else {
+      await pretty.error(`Missing tool calls: ${results.missing.join(', ')}`);
+    }
+  }
+}
+
+/**
+ * Simple string similarity calculation
+ */
+function calculateSimilarity(str1: string, str2: string): number {
+  const s1 = str1.toLowerCase().trim();
+  const s2 = str2.toLowerCase().trim();
+  
+  if (s1 === s2) return 1;
+  if (s1.includes(s2) || s2.includes(s1)) return 0.9;
+  
+  // Simple word overlap
+  const words1 = new Set(s1.split(/\s+/));
+  const words2 = new Set(s2.split(/\s+/));
+  const intersection = [...words1].filter(w => words2.has(w));
+  const union = new Set([...words1, ...words2]);
+  
+  return intersection.length / union.size;
+}

src/praisonai-ts/src/cli/commands/external-agents.ts

@@ -0,0 +1,185 @@
+/**
+ * CLI command: external-agents
+ * Integration with external AI CLI tools
+ */
+
+import { 
+  getExternalAgentRegistry, 
+  createExternalAgent,
+  ClaudeCodeAgent,
+  GeminiCliAgent,
+  CodexCliAgent,
+  AiderAgent
+} from '../features/external-agents';
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+
+  switch (subcommand) {
+    case 'list':
+      await handleList(isJson);
+      break;
+    case 'check':
+      await handleCheck(args.slice(1), isJson);
+      break;
+    case 'run':
+      await handleRun(args.slice(1), options, isJson);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+async function handleList(isJson: boolean): Promise<void> {
+  const registry = getExternalAgentRegistry();
+  const all = registry.list();
+  const available = await registry.getAvailable();
+
+  if (isJson) {
+    console.log(JSON.stringify({
+      success: true,
+      agents: all,
+      available
+    }, null, 2));
+  } else {
+    console.log('External Agents:\n');
+    for (const name of all) {
+      const status = available.includes(name) ? '✓' : '✗';
+      console.log(`  ${status} ${name}`);
+    }
+    console.log(`\n${available.length}/${all.length} available`);
+  }
+}
+
+async function handleCheck(args: string[], isJson: boolean): Promise<void> {
+  const name = args[0];
+  
+  if (!name) {
+    console.error('Error: Agent name is required');
+    process.exit(1);
+  }
+
+  const agent = createExternalAgent(name);
+  
+  if (!agent) {
+    if (isJson) {
+      console.log(JSON.stringify({ success: false, error: `Unknown agent: ${name}` }));
+    } else {
+      console.error(`Unknown agent: ${name}`);
+    }
+    process.exit(1);
+  }
+
+  const available = await agent.isAvailable();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, agent: name, available }));
+  } else {
+    if (available) {
+      console.log(`✓ ${name} is available`);
+    } else {
+      console.log(`✗ ${name} is not available (CLI not found)`);
+    }
+  }
+}
+
+async function handleRun(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const name = args[0];
+  const prompt = args.slice(1).join(' ');
+
+  if (!name) {
+    console.error('Error: Agent name is required');
+    process.exit(1);
+  }
+
+  if (!prompt) {
+    console.error('Error: Prompt is required');
+    process.exit(1);
+  }
+
+  const cwd = options.cwd as string | undefined;
+  const agent = createExternalAgent(name, cwd);
+
+  if (!agent) {
+    if (isJson) {
+      console.log(JSON.stringify({ success: false, error: `Unknown agent: ${name}` }));
+    } else {
+      console.error(`Unknown agent: ${name}`);
+    }
+    process.exit(1);
+  }
+
+  if (!await agent.isAvailable()) {
+    if (isJson) {
+      console.log(JSON.stringify({ success: false, error: `${name} CLI not available` }));
+    } else {
+      console.error(`${name} CLI not available`);
+    }
+    process.exit(1);
+  }
+
+  const result = await agent.execute(prompt);
+
+  if (isJson) {
+    console.log(JSON.stringify(result, null, 2));
+  } else {
+    if (result.success) {
+      console.log(result.output);
+    } else {
+      console.error(`Error: ${result.error}`);
+      process.exit(result.exitCode);
+    }
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'external-agents',
+    description: 'Integration with external AI CLI tools',
+    subcommands: {
+      list: 'List all external agents and availability',
+      check: 'Check if an agent is available',
+      run: 'Run a prompt with an external agent'
+    },
+    agents: {
+      claude: 'Claude Code CLI',
+      gemini: 'Gemini CLI',
+      codex: 'OpenAI Codex CLI',
+      aider: 'Aider CLI'
+    },
+    flags: {
+      '--cwd': 'Working directory for the agent',
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts external-agents list',
+      'praisonai-ts external-agents check claude',
+      'praisonai-ts external-agents run claude "Explain this code"',
+      'praisonai-ts external-agents run gemini "Refactor this function" --cwd ./src'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('External Agents - AI CLI tool integration\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nSupported Agents:');
+    for (const [agent, desc] of Object.entries(help.agents)) {
+      console.log(`  ${agent.padEnd(12)} ${desc}`);
+    }
+    console.log('\nFlags:');
+    for (const [flag, desc] of Object.entries(help.flags)) {
+      console.log(`  ${flag.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/fast-context.ts

@@ -0,0 +1,136 @@
+/**
+ * CLI command: fast-context
+ * Fast context retrieval and summarization
+ */
+
+import { FastContext, createFastContext, getQuickContext } from '../features/fast-context';
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+
+  switch (subcommand) {
+    case 'query':
+      await handleQuery(args.slice(1), options, isJson);
+      break;
+    case 'stats':
+      await handleStats(isJson);
+      break;
+    case 'clear':
+      await handleClear(isJson);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+let globalContext: FastContext | null = null;
+
+function getContext(maxTokens?: number): FastContext {
+  if (!globalContext) {
+    globalContext = createFastContext({ maxTokens, cacheEnabled: true });
+  }
+  return globalContext;
+}
+
+async function handleQuery(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const query = args.join(' ');
+  if (!query) {
+    console.error('Error: Query is required');
+    process.exit(1);
+  }
+
+  const maxTokens = options['max-tokens'] as number | undefined;
+  const sources = options.sources as string | undefined;
+  
+  const fc = getContext(maxTokens);
+  
+  // Add sources if provided
+  if (sources) {
+    const sourceList = sources.split(',').map(s => s.trim());
+    fc.registerSource('cli-sources', 'custom', sourceList);
+  }
+
+  const result = await fc.getContext(query);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, ...result }, null, 2));
+  } else {
+    console.log('Fast Context Result:');
+    console.log(`  Query: ${query}`);
+    console.log(`  Token count: ${result.tokenCount}`);
+    console.log(`  Sources used: ${result.sources.length}`);
+    console.log(`  Cached: ${result.cached}`);
+    console.log(`  Latency: ${result.latencyMs}ms`);
+    console.log('\nContext:');
+    console.log(result.context || '(empty)');
+  }
+}
+
+async function handleStats(isJson: boolean): Promise<void> {
+  const fc = getContext();
+  const stats = fc.getCacheStats();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, stats }, null, 2));
+  } else {
+    console.log('Fast Context Cache Stats:');
+    console.log(`  Cache size: ${stats.size}`);
+    console.log(`  Total hits: ${stats.totalHits}`);
+  }
+}
+
+async function handleClear(isJson: boolean): Promise<void> {
+  const fc = getContext();
+  fc.clearCache();
+  fc.clearSources();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, message: 'Cache and sources cleared' }));
+  } else {
+    console.log('✓ Cache and sources cleared');
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'fast-context',
+    description: 'Fast context retrieval and summarization',
+    subcommands: {
+      query: 'Query for relevant context',
+      stats: 'Show cache statistics',
+      clear: 'Clear cache and sources'
+    },
+    flags: {
+      '--max-tokens': 'Maximum tokens in context (default: 4000)',
+      '--sources': 'Comma-separated source texts',
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts fast-context query "What is the main topic?"',
+      'praisonai-ts fast-context query "summarize" --sources "text1,text2,text3"',
+      'praisonai-ts fast-context query "find relevant" --max-tokens 2000',
+      'praisonai-ts fast-context stats',
+      'praisonai-ts fast-context clear'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('Fast Context - Fast context retrieval\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nFlags:');
+    for (const [flag, desc] of Object.entries(help.flags)) {
+      console.log(`  ${flag.padEnd(14)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/flow.ts

@@ -0,0 +1,146 @@
+/**
+ * CLI command: flow
+ * Workflow flow visualization
+ */
+
+import { FlowDisplay, createFlowDisplay, renderWorkflow } from '../features/flow-display';
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+
+  switch (subcommand) {
+    case 'show':
+      await handleShow(args.slice(1), options, isJson);
+      break;
+    case 'dot':
+      await handleDot(args.slice(1), options, isJson);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+async function handleShow(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const stepsStr = args[0] || options.steps as string;
+  
+  let steps: Array<{ name: string; type?: string }> = [];
+  
+  if (stepsStr) {
+    try {
+      steps = JSON.parse(stepsStr);
+    } catch {
+      // Parse simple format: "step1,step2,step3"
+      steps = stepsStr.split(',').map(s => {
+        const [name, type] = s.split(':');
+        return { name: name.trim(), type: type?.trim() };
+      });
+    }
+  } else {
+    // Default example
+    steps = [
+      { name: 'Input', type: 'start' },
+      { name: 'Process', type: 'agent' },
+      { name: 'Validate', type: 'condition' },
+      { name: 'Output', type: 'end' }
+    ];
+  }
+
+  const display = createFlowDisplay({
+    showStatus: Boolean(options.status),
+    compact: Boolean(options.compact)
+  });
+  
+  display.fromWorkflowSteps(steps);
+
+  if (isJson) {
+    const graph = display.getGraph();
+    console.log(JSON.stringify({
+      success: true,
+      nodes: Array.from(graph.nodes.values()),
+      edges: graph.edges
+    }, null, 2));
+  } else {
+    if (options.boxes) {
+      console.log(display.renderBoxes());
+    } else {
+      console.log(display.render());
+    }
+  }
+}
+
+async function handleDot(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const stepsStr = args[0] || options.steps as string;
+  
+  let steps: Array<{ name: string; type?: string }> = [];
+  
+  if (stepsStr) {
+    try {
+      steps = JSON.parse(stepsStr);
+    } catch {
+      steps = stepsStr.split(',').map(s => {
+        const [name, type] = s.split(':');
+        return { name: name.trim(), type: type?.trim() };
+      });
+    }
+  } else {
+    steps = [
+      { name: 'Start', type: 'start' },
+      { name: 'Agent', type: 'agent' },
+      { name: 'End', type: 'end' }
+    ];
+  }
+
+  const display = createFlowDisplay();
+  display.fromWorkflowSteps(steps);
+  const dot = display.toDot();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, dot }));
+  } else {
+    console.log(dot);
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'flow',
+    description: 'Workflow flow visualization',
+    subcommands: {
+      show: 'Display workflow as text tree or boxes',
+      dot: 'Export workflow as DOT format (for Graphviz)'
+    },
+    flags: {
+      '--steps': 'Steps as JSON or "name:type,name:type"',
+      '--status': 'Show status indicators',
+      '--compact': 'Compact display mode',
+      '--boxes': 'Display as ASCII boxes',
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts flow show "Input,Process,Output"',
+      'praisonai-ts flow show "Start:start,Agent:agent,End:end"',
+      'praisonai-ts flow show --boxes',
+      'praisonai-ts flow dot "Step1,Step2,Step3" > workflow.dot'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('Flow - Workflow visualization\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nFlags:');
+    for (const [flag, desc] of Object.entries(help.flags)) {
+      console.log(`  ${flag.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/git.ts

@@ -0,0 +1,192 @@
+/**
+ * CLI command: git
+ * Git integration for repository operations
+ */
+
+import { GitManager, createGitManager, DiffViewer, createDiffViewer } from '../features/git-integration';
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+  const cwd = (options.cwd as string) || process.cwd();
+
+  switch (subcommand) {
+    case 'status':
+      await handleStatus(cwd, isJson);
+      break;
+    case 'diff':
+      await handleDiff(options, cwd, isJson);
+      break;
+    case 'log':
+      await handleLog(options, cwd, isJson);
+      break;
+    case 'branches':
+      await handleBranches(cwd, isJson);
+      break;
+    case 'stash':
+      await handleStash(args.slice(1), cwd, isJson);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+async function handleStatus(cwd: string, isJson: boolean): Promise<void> {
+  const git = createGitManager({ cwd, safe: true });
+
+  if (!await git.isRepo()) {
+    console.error('Error: Not a git repository');
+    process.exit(1);
+  }
+
+  const status = await git.getStatus();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, ...status }, null, 2));
+  } else {
+    console.log(await git.getStatusString());
+  }
+}
+
+async function handleDiff(options: Record<string, unknown>, cwd: string, isJson: boolean): Promise<void> {
+  const git = createGitManager({ cwd, safe: true });
+  const staged = Boolean(options.staged);
+
+  if (!await git.isRepo()) {
+    console.error('Error: Not a git repository');
+    process.exit(1);
+  }
+
+  const diff = await git.getDiff(staged);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, ...diff }, null, 2));
+  } else {
+    if (diff.files.length === 0) {
+      console.log(staged ? 'No staged changes' : 'No changes');
+    } else {
+      console.log(`Changes (${diff.files.length} files):\n`);
+      for (const file of diff.files) {
+        console.log(`  ${file.path} (+${file.additions}/-${file.deletions})`);
+      }
+      if (options.full) {
+        console.log('\n' + diff.summary);
+      }
+    }
+  }
+}
+
+async function handleLog(options: Record<string, unknown>, cwd: string, isJson: boolean): Promise<void> {
+  const git = createGitManager({ cwd, safe: true });
+  const limit = (options.limit as number) || 10;
+
+  if (!await git.isRepo()) {
+    console.error('Error: Not a git repository');
+    process.exit(1);
+  }
+
+  const commits = await git.getLog(limit);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, commits }, null, 2));
+  } else {
+    console.log('Recent commits:\n');
+    for (const commit of commits) {
+      console.log(`  ${commit.shortHash} ${commit.message}`);
+      console.log(`    by ${commit.author} on ${commit.date.toLocaleDateString()}`);
+    }
+  }
+}
+
+async function handleBranches(cwd: string, isJson: boolean): Promise<void> {
+  const git = createGitManager({ cwd, safe: true });
+
+  if (!await git.isRepo()) {
+    console.error('Error: Not a git repository');
+    process.exit(1);
+  }
+
+  const branches = await git.getBranches();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, branches }, null, 2));
+  } else {
+    console.log('Branches:\n');
+    for (const branch of branches) {
+      const marker = branch.current ? '* ' : '  ';
+      console.log(`${marker}${branch.name}`);
+    }
+  }
+}
+
+async function handleStash(args: string[], cwd: string, isJson: boolean): Promise<void> {
+  const git = createGitManager({ cwd, safe: true });
+
+  if (!await git.isRepo()) {
+    console.error('Error: Not a git repository');
+    process.exit(1);
+  }
+
+  const stashes = await git.getStashList();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, stashes }, null, 2));
+  } else {
+    if (stashes.length === 0) {
+      console.log('No stashes');
+    } else {
+      console.log('Stashes:\n');
+      for (const stash of stashes) {
+        console.log(`  ${stash}`);
+      }
+    }
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'git',
+    description: 'Git integration for repository operations (read-only by default)',
+    subcommands: {
+      status: 'Show repository status',
+      diff: 'Show changes',
+      log: 'Show recent commits',
+      branches: 'List branches',
+      stash: 'List stashes'
+    },
+    flags: {
+      '--cwd': 'Working directory (default: current)',
+      '--staged': 'Show staged changes only (for diff)',
+      '--full': 'Show full diff output',
+      '--limit': 'Number of commits to show (default: 10)',
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts git status',
+      'praisonai-ts git diff',
+      'praisonai-ts git diff --staged',
+      'praisonai-ts git log --limit 5',
+      'praisonai-ts git branches',
+      'praisonai-ts git stash'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('Git - Repository operations (read-only)\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nFlags:');
+    for (const [flag, desc] of Object.entries(help.flags)) {
+      console.log(`  ${flag.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/graph-rag.ts

@@ -0,0 +1,104 @@
+/**
+ * Graph RAG command - Graph-based retrieval augmented generation
+ */
+
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface GraphRagOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: GraphRagOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'info':
+        await showInfo(outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function showInfo(outputFormat: string): Promise<void> {
+  const info = {
+    feature: 'Graph RAG',
+    description: 'Graph-based retrieval augmented generation for complex knowledge queries',
+    capabilities: [
+      'Build knowledge graphs from documents',
+      'Query relationships between entities',
+      'Combine graph traversal with vector search',
+      'Extract entities and relationships',
+      'Support for complex multi-hop queries'
+    ],
+    sdkUsage: `
+import { createGraphRAG, GraphStore } from 'praisonai';
+
+// Create a graph RAG instance
+const graphRag = createGraphRAG({
+  llm: 'openai/gpt-4o-mini',
+  graphStore: new GraphStore()
+});
+
+// Add documents
+await graphRag.addDocument('Document content...');
+
+// Query with graph context
+const result = await graphRag.query('What is the relationship between X and Y?');
+`
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(info));
+  } else {
+    await pretty.heading('Graph RAG');
+    await pretty.plain(info.description);
+    await pretty.newline();
+    await pretty.plain('Capabilities:');
+    for (const cap of info.capabilities) {
+      await pretty.plain(`  • ${cap}`);
+    }
+    await pretty.newline();
+    await pretty.dim('Use the SDK for full Graph RAG functionality');
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'graph-rag',
+    description: 'Graph-based retrieval augmented generation',
+    subcommands: [
+      { name: 'info', description: 'Show Graph RAG feature information' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Graph RAG Command');
+    await pretty.plain(help.description);
+    await pretty.newline();
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(20)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/guardrail.ts

@@ -0,0 +1,132 @@
+/**
+ * Guardrail command - Content validation and safety
+ */
+
+import { createLLMGuardrail } from '../../guardrails/llm-guardrail';
+import { resolveConfig } from '../config/resolve';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface GuardrailOptions {
+  model?: string;
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  criteria?: string;
+}
+
+export async function execute(args: string[], options: GuardrailOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const actionArgs = args.slice(1);
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+  const config = resolveConfig(options);
+
+  try {
+    switch (action) {
+      case 'check':
+        await checkContent(actionArgs, options, config, outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function checkContent(args: string[], options: GuardrailOptions, config: any, outputFormat: string): Promise<void> {
+  const content = args.join(' ');
+  if (!content) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide content to check'));
+    } else {
+      await pretty.error('Please provide content to check');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const startTime = Date.now();
+
+  if (outputFormat !== 'json') {
+    await pretty.info('Checking content...');
+  }
+
+  const guardrail = createLLMGuardrail({
+    name: 'cli-guardrail',
+    llm: config.model,
+    criteria: options.criteria || 'Content should be safe, appropriate, and helpful',
+    verbose: options.verbose
+  });
+
+  const result = await guardrail.check(content);
+  const duration = Date.now() - startTime;
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      content: content.substring(0, 100) + (content.length > 100 ? '...' : ''),
+      status: result.status,
+      score: result.score,
+      message: result.message,
+      reasoning: result.reasoning
+    }, {
+      duration_ms: duration,
+      model: config.model
+    }));
+  } else {
+    await pretty.heading('Guardrail Check');
+    if (result.status === 'passed') {
+      await pretty.success('Content passed guardrail check');
+    } else if (result.status === 'warning') {
+      await pretty.warn('Content has warnings');
+    } else {
+      await pretty.error('Content failed guardrail check');
+    }
+    await pretty.plain(`Score: ${(result.score * 10).toFixed(1)}/10`);
+    if (result.message) {
+      await pretty.plain(`Message: ${result.message}`);
+    }
+    if (result.reasoning) {
+      await pretty.dim(`Reasoning: ${result.reasoning}`);
+    }
+    await pretty.newline();
+    await pretty.dim(`Checked in ${duration}ms`);
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'guardrail',
+    subcommands: [
+      { name: 'check <content>', description: 'Check content against guardrails' },
+      { name: 'help', description: 'Show this help' }
+    ],
+    flags: [
+      { name: '--criteria', description: 'Custom criteria for validation' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Guardrail Command');
+    await pretty.plain('Content validation and safety checks\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(25)} ${cmd.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Flags:');
+    for (const flag of help.flags) {
+      await pretty.plain(`  ${flag.name.padEnd(20)} ${flag.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/handoff.ts

@@ -0,0 +1,106 @@
+/**
+ * Handoff command - Agent handoff management
+ */
+
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface HandoffOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: HandoffOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'info':
+        await showInfo(outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function showInfo(outputFormat: string): Promise<void> {
+  const info = {
+    feature: 'Handoff',
+    description: 'Agent handoff allows seamless transfer of conversation context between agents',
+    capabilities: [
+      'Transfer conversation to specialized agents',
+      'Preserve context during handoff',
+      'Filter handoffs based on conditions',
+      'Chain multiple agent handoffs'
+    ],
+    sdkUsage: `
+import { Handoff, handoff, handoffFilters } from 'praisonai';
+
+// Create a handoff
+const myHandoff = handoff({
+  target: specialistAgent,
+  condition: (ctx) => ctx.input.includes('technical'),
+  onHandoff: (ctx) => console.log('Handing off...')
+});
+
+// Use with an agent
+const agent = new Agent({
+  handoffs: [myHandoff]
+});
+`
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(info));
+  } else {
+    await pretty.heading('Handoff Feature');
+    await pretty.plain(info.description);
+    await pretty.newline();
+    await pretty.plain('Capabilities:');
+    for (const cap of info.capabilities) {
+      await pretty.plain(`  • ${cap}`);
+    }
+    await pretty.newline();
+    await pretty.dim('Use the SDK for programmatic handoff configuration');
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'handoff',
+    description: 'Agent handoff management - transfer conversations between agents',
+    subcommands: [
+      { name: 'info', description: 'Show handoff feature information' },
+      { name: 'help', description: 'Show this help' }
+    ],
+    note: 'Handoff is primarily a programmatic SDK feature. Use the SDK for full functionality.'
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Handoff Command');
+    await pretty.plain(help.description);
+    await pretty.newline();
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(20)} ${cmd.description}`);
+    }
+    await pretty.newline();
+    await pretty.dim(help.note);
+  }
+}

src/praisonai-ts/src/cli/commands/help.ts

@@ -0,0 +1,151 @@
+/**
+ * Help command - Show help information
+ */
+
+import { COMMANDS, GLOBAL_FLAGS, CLI_SPEC_VERSION, getCommandSpec } from '../spec/cli-spec';
+import { outputJson, formatSuccess } from '../output/json';
+import * as pretty from '../output/pretty';
+
+export interface HelpOptions {
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: HelpOptions): Promise<void> {
+  const command = args[0];
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  if (command) {
+    await showCommandHelp(command, outputFormat);
+  } else {
+    await showGeneralHelp(outputFormat);
+  }
+}
+
+async function showGeneralHelp(outputFormat: string): Promise<void> {
+  const commands = Object.entries(COMMANDS).map(([name, spec]) => ({
+    name,
+    description: spec.description
+  }));
+
+  const flags = GLOBAL_FLAGS.map(f => ({
+    name: f.short ? `-${f.short}, --${f.name}` : `--${f.name}`,
+    description: f.description,
+    default: f.default
+  }));
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      cli_spec_version: CLI_SPEC_VERSION,
+      commands,
+      global_flags: flags
+    }));
+  } else {
+    await pretty.plain(`
+PraisonAI TypeScript CLI v${CLI_SPEC_VERSION}
+
+Usage:
+  praisonai-ts <command> [options]
+
+Commands:`);
+
+    for (const cmd of commands) {
+      await pretty.plain(`  ${cmd.name.padEnd(12)} ${cmd.description}`);
+    }
+
+    await pretty.plain(`
+Global Options:`);
+
+    for (const flag of flags) {
+      const defaultStr = flag.default !== undefined ? ` (default: ${flag.default})` : '';
+      await pretty.plain(`  ${flag.name.padEnd(20)} ${flag.description}${defaultStr}`);
+    }
+
+    await pretty.plain(`
+Environment Variables:
+  OPENAI_API_KEY       OpenAI API key
+  ANTHROPIC_API_KEY    Anthropic API key
+  GOOGLE_API_KEY       Google API key
+  PRAISONAI_MODEL      Default model
+
+Examples:
+  praisonai-ts chat "Hello, how are you?"
+  praisonai-ts chat "Write a poem" --stream
+  praisonai-ts run "Analyze this data" --agent my-agent.yaml
+  praisonai-ts providers
+  praisonai-ts help chat
+`);
+  }
+}
+
+async function showCommandHelp(command: string, outputFormat: string): Promise<void> {
+  const spec = getCommandSpec(command);
+
+  if (!spec) {
+    await pretty.error(`Unknown command: ${command}`);
+    await pretty.info('Run "praisonai-ts help" to see available commands');
+    return;
+  }
+
+  const args = spec.args || [];
+  const flags = [...GLOBAL_FLAGS, ...(spec.flags || [])];
+  const subcommands = spec.subcommands ? Object.entries(spec.subcommands) : [];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      command,
+      description: spec.description,
+      args: args.map(a => ({
+        name: a.name,
+        type: a.type,
+        required: a.required,
+        description: a.description
+      })),
+      flags: flags.map(f => ({
+        name: f.name,
+        short: f.short,
+        type: f.type,
+        default: f.default,
+        description: f.description
+      })),
+      subcommands: subcommands.map(([name, sub]) => ({
+        name,
+        description: sub.description
+      }))
+    }));
+  } else {
+    await pretty.plain(`
+Command: ${command}
+${spec.description}
+
+Usage:
+  praisonai-ts ${command}${args.length ? ' ' + args.map(a => a.required ? `<${a.name}>` : `[${a.name}]`).join(' ') : ''} [options]`);
+
+    if (args.length > 0) {
+      await pretty.plain(`
+Arguments:`);
+      for (const arg of args) {
+        const reqStr = arg.required ? ' (required)' : '';
+        await pretty.plain(`  ${arg.name.padEnd(15)} ${arg.description || arg.type}${reqStr}`);
+      }
+    }
+
+    if (subcommands.length > 0) {
+      await pretty.plain(`
+Subcommands:`);
+      for (const [name, sub] of subcommands) {
+        await pretty.plain(`  ${name.padEnd(15)} ${sub.description}`);
+      }
+    }
+
+    await pretty.plain(`
+Options:`);
+    for (const flag of flags) {
+      const shortStr = flag.short ? `-${flag.short}, ` : '    ';
+      const defaultStr = flag.default !== undefined ? ` (default: ${flag.default})` : '';
+      await pretty.plain(`  ${shortStr}--${flag.name.padEnd(14)} ${flag.description || ''}${defaultStr}`);
+    }
+
+    await pretty.plain('');
+  }
+}

src/praisonai-ts/src/cli/commands/image.ts

@@ -0,0 +1,179 @@
+/**
+ * Image command - Image generation and analysis
+ */
+
+import { createImageAgent } from '../../agent/image';
+import { resolveConfig } from '../config/resolve';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface ImageOptions {
+  model?: string;
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  size?: string;
+  quality?: string;
+  style?: string;
+}
+
+export async function execute(args: string[], options: ImageOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const actionArgs = args.slice(1);
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+  const config = resolveConfig(options);
+
+  try {
+    switch (action) {
+      case 'generate':
+        await generateImage(actionArgs, options, config, outputFormat);
+        break;
+      case 'analyze':
+        await analyzeImage(actionArgs, options, config, outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function generateImage(args: string[], options: ImageOptions, config: any, outputFormat: string): Promise<void> {
+  const prompt = args.join(' ');
+  if (!prompt) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a prompt for image generation'));
+    } else {
+      await pretty.error('Please provide a prompt for image generation');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const startTime = Date.now();
+
+  if (outputFormat !== 'json') {
+    await pretty.info(`Generating image: "${prompt}"`);
+  }
+
+  const agent = createImageAgent({
+    llm: config.model,
+    verbose: options.verbose
+  });
+
+  const result = await agent.generate({
+    prompt,
+    size: options.size as any,
+    quality: options.quality as any,
+    style: options.style as any
+  });
+
+  const duration = Date.now() - startTime;
+  const urls = Array.isArray(result) ? result : [result];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      prompt,
+      urls
+    }, {
+      duration_ms: duration,
+      model: config.model
+    }));
+  } else {
+    await pretty.heading('Generated Image');
+    for (const url of urls) {
+      await pretty.plain(`URL: ${url}`);
+    }
+    await pretty.newline();
+    await pretty.success(`Generated in ${duration}ms`);
+  }
+}
+
+async function analyzeImage(args: string[], options: ImageOptions, config: any, outputFormat: string): Promise<void> {
+  const imageUrl = args[0];
+  const prompt = args.slice(1).join(' ') || 'Describe this image';
+
+  if (!imageUrl) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide an image URL'));
+    } else {
+      await pretty.error('Please provide an image URL');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const startTime = Date.now();
+
+  if (outputFormat !== 'json') {
+    await pretty.info(`Analyzing image: ${imageUrl}`);
+  }
+
+  const agent = createImageAgent({
+    llm: config.model,
+    verbose: options.verbose
+  });
+
+  const result = await agent.analyze({
+    imageUrl,
+    prompt
+  });
+
+  const duration = Date.now() - startTime;
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      imageUrl,
+      prompt,
+      analysis: result
+    }, {
+      duration_ms: duration,
+      model: config.model
+    }));
+  } else {
+    await pretty.heading('Image Analysis');
+    await pretty.plain(result);
+    await pretty.newline();
+    await pretty.success(`Analyzed in ${duration}ms`);
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'image',
+    subcommands: [
+      { name: 'generate <prompt>', description: 'Generate an image from text' },
+      { name: 'analyze <url> [question]', description: 'Analyze an image' },
+      { name: 'help', description: 'Show this help' }
+    ],
+    flags: [
+      { name: '--size', description: 'Image size (1024x1024, 1792x1024, 1024x1792)' },
+      { name: '--quality', description: 'Image quality (standard, hd)' },
+      { name: '--style', description: 'Image style (vivid, natural)' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Image Command');
+    await pretty.plain('Generate and analyze images\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(30)} ${cmd.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Flags:');
+    for (const flag of help.flags) {
+      await pretty.plain(`  ${flag.name.padEnd(20)} ${flag.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/interactive.ts

@@ -0,0 +1,84 @@
+/**
+ * CLI command: interactive
+ * Interactive TUI mode with slash commands
+ */
+
+import { InteractiveTUI, createInteractiveTUI } from '../features/interactive-tui';
+import { createCostTracker } from '../features/cost-tracker';
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const isJson = Boolean(options.output === 'json' || options.json);
+
+  if (isJson) {
+    console.log(JSON.stringify({
+      success: false,
+      error: 'Interactive mode does not support JSON output'
+    }));
+    process.exit(1);
+  }
+
+  const historyFile = options.history as string | undefined;
+  const model = options.model as string | undefined;
+
+  console.log('Starting interactive mode...');
+  console.log('Type /help for available commands, /exit to quit.\n');
+
+  const tui = createInteractiveTUI({
+    prompt: options.prompt as string || '> ',
+    historyFile,
+    welcomeMessage: `PraisonAI Interactive Mode
+Model: ${model || 'default'}
+Type /help for commands, /exit to quit.`,
+    onMessage: async (message) => {
+      // Simple echo for now - in real usage this would call the agent
+      return `You said: ${message}`;
+    },
+    onExit: () => {
+      console.log('\nGoodbye!');
+    }
+  });
+
+  // Update context with model if provided
+  if (model) {
+    tui.updateContext({ model });
+  }
+
+  try {
+    await tui.start();
+  } catch (error: any) {
+    console.error(`Error: ${error.message}`);
+    process.exit(1);
+  }
+}
+
+export function showHelp(): void {
+  console.log(`Interactive - Interactive TUI mode
+
+Usage:
+  praisonai-ts interactive [options]
+
+Options:
+  --model, -m     Model to use
+  --prompt        Custom prompt string (default: "> ")
+  --history       Path to history file
+
+Slash Commands (in interactive mode):
+  /help           Show available commands
+  /cost           Show token usage and cost
+  /clear          Clear conversation history
+  /model [name]   Show or change model
+  /tokens         Show token count
+  /plan           Manage task plan
+  /undo           Undo last action
+  /diff           Show pending changes
+  /commit         Commit pending changes
+  /settings       Show or modify settings
+  /map            Show repository map
+  /exit           Exit interactive mode
+
+Examples:
+  praisonai-ts interactive
+  praisonai-ts interactive --model gpt-4o
+  praisonai-ts interactive --history ~/.praisonai_history
+`);
+}

src/praisonai-ts/src/cli/commands/jobs.ts

@@ -0,0 +1,295 @@
+/**
+ * CLI command: jobs
+ * Background job queue management
+ */
+
+import { JobQueue, createJobQueue, createFileJobStorage } from '../features/background-jobs';
+
+let globalQueue: JobQueue | null = null;
+
+function getQueue(storagePath?: string): JobQueue {
+  if (!globalQueue) {
+    const storage = storagePath ? createFileJobStorage(storagePath) : undefined;
+    globalQueue = createJobQueue({ storage });
+  }
+  return globalQueue;
+}
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+  const storagePath = options.storage as string | undefined;
+
+  switch (subcommand) {
+    case 'add':
+      await handleAdd(args.slice(1), options, isJson, storagePath);
+      break;
+    case 'list':
+      await handleList(options, isJson, storagePath);
+      break;
+    case 'get':
+      await handleGet(args.slice(1), isJson, storagePath);
+      break;
+    case 'cancel':
+      await handleCancel(args.slice(1), isJson, storagePath);
+      break;
+    case 'retry':
+      await handleRetry(args.slice(1), isJson, storagePath);
+      break;
+    case 'process':
+      await handleProcess(args.slice(1), isJson, storagePath);
+      break;
+    case 'stats':
+      await handleStats(isJson, storagePath);
+      break;
+    case 'cleanup':
+      await handleCleanup(options, isJson, storagePath);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+async function handleAdd(args: string[], options: Record<string, unknown>, isJson: boolean, storagePath?: string): Promise<void> {
+  const name = args[0];
+  const dataStr = args[1] || '{}';
+
+  if (!name) {
+    console.error('Error: Job name is required');
+    process.exit(1);
+  }
+
+  let data: Record<string, unknown>;
+  try {
+    data = JSON.parse(dataStr);
+  } catch {
+    data = { input: dataStr };
+  }
+
+  const priority = (options.priority as string) || 'normal';
+  const queue = getQueue(storagePath);
+  
+  const job = await queue.add(name, data, {
+    priority: priority as 'low' | 'normal' | 'high' | 'critical'
+  });
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, job }, null, 2));
+  } else {
+    console.log(`✓ Job created: ${job.id}`);
+    console.log(`  Name: ${job.name}`);
+    console.log(`  Priority: ${job.priority}`);
+    console.log(`  Status: ${job.status}`);
+  }
+}
+
+async function handleList(options: Record<string, unknown>, isJson: boolean, storagePath?: string): Promise<void> {
+  const queue = getQueue(storagePath);
+  const status = options.status as string | undefined;
+  
+  let jobs = await queue.getAll();
+  if (status) {
+    jobs = jobs.filter(j => j.status === status);
+  }
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, jobs }, null, 2));
+  } else {
+    if (jobs.length === 0) {
+      console.log('No jobs found');
+    } else {
+      console.log('Jobs:');
+      for (const job of jobs) {
+        console.log(`  ${job.id}`);
+        console.log(`    Name: ${job.name}`);
+        console.log(`    Status: ${job.status}`);
+        console.log(`    Priority: ${job.priority}`);
+        console.log(`    Attempts: ${job.attempts}/${job.maxAttempts}`);
+        if (job.error) console.log(`    Error: ${job.error}`);
+      }
+    }
+  }
+}
+
+async function handleGet(args: string[], isJson: boolean, storagePath?: string): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Job ID is required');
+    process.exit(1);
+  }
+
+  const queue = getQueue(storagePath);
+  const job = await queue.get(id);
+
+  if (!job) {
+    if (isJson) {
+      console.log(JSON.stringify({ success: false, error: 'Job not found' }));
+    } else {
+      console.error(`Job ${id} not found`);
+    }
+    process.exit(1);
+  }
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, job }, null, 2));
+  } else {
+    console.log(`Job: ${job.id}`);
+    console.log(`  Name: ${job.name}`);
+    console.log(`  Status: ${job.status}`);
+    console.log(`  Priority: ${job.priority}`);
+    console.log(`  Attempts: ${job.attempts}/${job.maxAttempts}`);
+    console.log(`  Created: ${job.createdAt}`);
+    if (job.startedAt) console.log(`  Started: ${job.startedAt}`);
+    if (job.completedAt) console.log(`  Completed: ${job.completedAt}`);
+    if (job.error) console.log(`  Error: ${job.error}`);
+    if (job.result) console.log(`  Result: ${JSON.stringify(job.result)}`);
+  }
+}
+
+async function handleCancel(args: string[], isJson: boolean, storagePath?: string): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Job ID is required');
+    process.exit(1);
+  }
+
+  const queue = getQueue(storagePath);
+  const cancelled = await queue.cancel(id);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: cancelled, id }));
+  } else {
+    console.log(cancelled ? `✓ Job ${id} cancelled` : `Could not cancel job ${id}`);
+  }
+}
+
+async function handleRetry(args: string[], isJson: boolean, storagePath?: string): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Job ID is required');
+    process.exit(1);
+  }
+
+  const queue = getQueue(storagePath);
+  const retried = await queue.retry(id);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: retried, id }));
+  } else {
+    console.log(retried ? `✓ Job ${id} queued for retry` : `Could not retry job ${id}`);
+  }
+}
+
+async function handleProcess(args: string[], isJson: boolean, storagePath?: string): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Job ID is required');
+    process.exit(1);
+  }
+
+  const queue = getQueue(storagePath);
+  
+  // Register a simple handler
+  queue.register('default', async (job) => {
+    return { processed: true, data: job.data };
+  });
+
+  try {
+    const result = await queue.processNow(id);
+    if (isJson) {
+      console.log(JSON.stringify({ success: true, result }, null, 2));
+    } else {
+      console.log(`✓ Job ${id} processed`);
+      console.log(`  Result: ${JSON.stringify(result)}`);
+    }
+  } catch (error: any) {
+    if (isJson) {
+      console.log(JSON.stringify({ success: false, error: error.message }));
+    } else {
+      console.error(`Error: ${error.message}`);
+    }
+    process.exit(1);
+  }
+}
+
+async function handleStats(isJson: boolean, storagePath?: string): Promise<void> {
+  const queue = getQueue(storagePath);
+  const stats = await queue.getStats();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, stats }, null, 2));
+  } else {
+    console.log('Job Queue Stats:');
+    console.log(`  Pending: ${stats.pending}`);
+    console.log(`  Running: ${stats.running}`);
+    console.log(`  Completed: ${stats.completed}`);
+    console.log(`  Failed: ${stats.failed}`);
+    console.log(`  Cancelled: ${stats.cancelled}`);
+  }
+}
+
+async function handleCleanup(options: Record<string, unknown>, isJson: boolean, storagePath?: string): Promise<void> {
+  const queue = getQueue(storagePath);
+  const days = (options.days as number) || 7;
+  const olderThan = new Date(Date.now() - days * 24 * 60 * 60 * 1000);
+  
+  const count = await queue.cleanup(olderThan);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, cleaned: count }));
+  } else {
+    console.log(`✓ Cleaned up ${count} jobs older than ${days} days`);
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'jobs',
+    description: 'Background job queue management',
+    subcommands: {
+      add: 'Add a new job to the queue',
+      list: 'List all jobs',
+      get: 'Get job details',
+      cancel: 'Cancel a pending job',
+      retry: 'Retry a failed job',
+      process: 'Process a job immediately',
+      stats: 'Show queue statistics',
+      cleanup: 'Clean up old completed/failed jobs'
+    },
+    flags: {
+      '--storage': 'Path to job storage file',
+      '--priority': 'Job priority (low, normal, high, critical)',
+      '--status': 'Filter by status',
+      '--days': 'Days for cleanup threshold',
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts jobs add my-job \'{"input": "data"}\'',
+      'praisonai-ts jobs add task --priority high',
+      'praisonai-ts jobs list --status pending',
+      'praisonai-ts jobs get <job-id>',
+      'praisonai-ts jobs cancel <job-id>',
+      'praisonai-ts jobs stats',
+      'praisonai-ts jobs cleanup --days 30'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('Jobs - Background job queue management\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nFlags:');
+    for (const [flag, desc] of Object.entries(help.flags)) {
+      console.log(`  ${flag.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/knowledge.ts

@@ -0,0 +1,203 @@
+/**
+ * Knowledge command - Manage knowledge base
+ */
+
+import { BaseKnowledgeBase, Knowledge } from '../../knowledge';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+import * as fs from 'fs';
+import * as path from 'path';
+import { randomUUID } from 'crypto';
+
+export interface KnowledgeOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+// Singleton knowledge base instance
+let kbInstance: BaseKnowledgeBase | null = null;
+function getKnowledgeBase(): BaseKnowledgeBase {
+  if (!kbInstance) {
+    kbInstance = new BaseKnowledgeBase();
+  }
+  return kbInstance;
+}
+
+export async function execute(args: string[], options: KnowledgeOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const actionArgs = args.slice(1);
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    const kb = getKnowledgeBase();
+
+    switch (action) {
+      case 'add':
+        await addKnowledge(kb, actionArgs, outputFormat);
+        break;
+      case 'search':
+        await searchKnowledge(kb, actionArgs, outputFormat);
+        break;
+      case 'list':
+        await listKnowledge(kb, outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function addKnowledge(kb: BaseKnowledgeBase, args: string[], outputFormat: string): Promise<void> {
+  const source = args[0];
+  if (!source) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a file path or text content'));
+    } else {
+      await pretty.error('Please provide a file path or text content');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  let content: string;
+  let sourceName: string;
+
+  // Check if it's a file path
+  if (fs.existsSync(source)) {
+    content = fs.readFileSync(source, 'utf-8');
+    sourceName = path.basename(source);
+  } else {
+    // Treat as direct text content
+    content = args.join(' ');
+    sourceName = 'text-input';
+  }
+
+  const knowledge: Knowledge = {
+    id: randomUUID(),
+    type: 'text',
+    content,
+    metadata: { source: sourceName, addedAt: new Date().toISOString() }
+  };
+  
+  kb.addKnowledge(knowledge);
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ 
+      added: true, 
+      id: knowledge.id,
+      source: sourceName,
+      contentLength: content.length 
+    }));
+  } else {
+    await pretty.success(`Knowledge added from: ${sourceName}`);
+    await pretty.dim(`Content length: ${content.length} characters`);
+  }
+}
+
+async function searchKnowledge(kb: BaseKnowledgeBase, args: string[], outputFormat: string): Promise<void> {
+  const query = args.join(' ');
+  if (!query) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a search query'));
+    } else {
+      await pretty.error('Please provide a search query');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const results = kb.searchKnowledge(query);
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      query,
+      results: results.map(r => ({
+        id: r.id,
+        content: r.content,
+        metadata: r.metadata
+      })),
+      count: results.length
+    }));
+  } else {
+    await pretty.heading(`Search Results for: "${query}"`);
+    if (results.length === 0) {
+      await pretty.info('No matching knowledge found');
+    } else {
+      for (const result of results) {
+        const contentStr = typeof result.content === 'string' ? result.content : JSON.stringify(result.content);
+        await pretty.plain(`  • ${contentStr.substring(0, 100)}${contentStr.length > 100 ? '...' : ''}`);
+        if (result.metadata?.source) {
+          await pretty.dim(`    Source: ${result.metadata.source}`);
+        }
+      }
+    }
+    await pretty.newline();
+    await pretty.info(`Found: ${results.length} results`);
+  }
+}
+
+async function listKnowledge(kb: BaseKnowledgeBase, outputFormat: string): Promise<void> {
+  // Search with empty string to get all
+  const entries = kb.searchKnowledge('');
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      entries: entries.map((e: Knowledge) => ({
+        id: e.id,
+        type: e.type,
+        contentPreview: typeof e.content === 'string' ? e.content.substring(0, 100) : JSON.stringify(e.content).substring(0, 100),
+        source: e.metadata?.source
+      })),
+      count: entries.length
+    }));
+  } else {
+    await pretty.heading('Knowledge Base Entries');
+    if (entries.length === 0) {
+      await pretty.info('No knowledge entries found');
+    } else {
+      for (const entry of entries) {
+        const contentStr = typeof entry.content === 'string' ? entry.content : JSON.stringify(entry.content);
+        await pretty.plain(`  • ${contentStr.substring(0, 80)}${contentStr.length > 80 ? '...' : ''}`);
+        if (entry.metadata?.source) {
+          await pretty.dim(`    Source: ${entry.metadata.source}`);
+        }
+      }
+    }
+    await pretty.newline();
+    await pretty.info(`Total: ${entries.length} entries`);
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'knowledge',
+    subcommands: [
+      { name: 'add <file|text>', description: 'Add knowledge from file or text' },
+      { name: 'search <query>', description: 'Search knowledge base' },
+      { name: 'list', description: 'List all knowledge entries' },
+      { name: 'clear', description: 'Clear all knowledge' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Knowledge Command');
+    await pretty.plain('Manage knowledge base for RAG\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(25)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/mcp.ts

@@ -0,0 +1,230 @@
+/**
+ * MCP command - Model Context Protocol management
+ */
+
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface MCPOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+// MCP server registry (in-memory for now)
+interface MCPServer {
+  name: string;
+  command: string;
+  args?: string[];
+  env?: Record<string, string>;
+  status: 'stopped' | 'running';
+}
+
+const mcpServers: Map<string, MCPServer> = new Map();
+
+export async function execute(args: string[], options: MCPOptions): Promise<void> {
+  const action = args[0] || 'list';
+  const actionArgs = args.slice(1);
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'list':
+        await listServers(outputFormat);
+        break;
+      case 'add':
+        await addServer(actionArgs, outputFormat);
+        break;
+      case 'remove':
+        await removeServer(actionArgs, outputFormat);
+        break;
+      case 'start':
+        await startServer(actionArgs, outputFormat);
+        break;
+      case 'stop':
+        await stopServer(actionArgs, outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function listServers(outputFormat: string): Promise<void> {
+  const servers = Array.from(mcpServers.values());
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      servers,
+      count: servers.length
+    }));
+  } else {
+    await pretty.heading('MCP Servers');
+    if (servers.length === 0) {
+      await pretty.info('No MCP servers registered');
+      await pretty.dim('Run "praisonai-ts mcp add <name> <command>" to add a server');
+    } else {
+      for (const server of servers) {
+        const statusIcon = server.status === 'running' ? '🟢' : '⚪';
+        await pretty.plain(`  ${statusIcon} ${server.name}`);
+        await pretty.dim(`    Command: ${server.command} ${(server.args || []).join(' ')}`);
+      }
+    }
+    await pretty.newline();
+    await pretty.info(`Total: ${servers.length} servers`);
+  }
+}
+
+async function addServer(args: string[], outputFormat: string): Promise<void> {
+  const name = args[0];
+  const command = args[1];
+  const serverArgs = args.slice(2);
+
+  if (!name || !command) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide server name and command'));
+    } else {
+      await pretty.error('Please provide server name and command');
+      await pretty.dim('Usage: praisonai-ts mcp add <name> <command> [args...]');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const server: MCPServer = {
+    name,
+    command,
+    args: serverArgs.length > 0 ? serverArgs : undefined,
+    status: 'stopped'
+  };
+
+  mcpServers.set(name, server);
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ added: true, server }));
+  } else {
+    await pretty.success(`MCP server added: ${name}`);
+    await pretty.dim(`Command: ${command} ${serverArgs.join(' ')}`);
+  }
+}
+
+async function removeServer(args: string[], outputFormat: string): Promise<void> {
+  const name = args[0];
+  if (!name) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide server name'));
+    } else {
+      await pretty.error('Please provide server name');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const removed = mcpServers.delete(name);
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ removed, name }));
+  } else {
+    if (removed) {
+      await pretty.success(`MCP server removed: ${name}`);
+    } else {
+      await pretty.warn(`Server not found: ${name}`);
+    }
+  }
+}
+
+async function startServer(args: string[], outputFormat: string): Promise<void> {
+  const name = args[0];
+  if (!name) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide server name'));
+    } else {
+      await pretty.error('Please provide server name');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const server = mcpServers.get(name);
+  if (!server) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, `Server not found: ${name}`));
+    } else {
+      await pretty.error(`Server not found: ${name}`);
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+
+  // Mark as running (actual process management would be more complex)
+  server.status = 'running';
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ started: true, server }));
+  } else {
+    await pretty.success(`MCP server started: ${name}`);
+  }
+}
+
+async function stopServer(args: string[], outputFormat: string): Promise<void> {
+  const name = args[0];
+  if (!name) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide server name'));
+    } else {
+      await pretty.error('Please provide server name');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const server = mcpServers.get(name);
+  if (!server) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, `Server not found: ${name}`));
+    } else {
+      await pretty.error(`Server not found: ${name}`);
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+
+  server.status = 'stopped';
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ stopped: true, server }));
+  } else {
+    await pretty.success(`MCP server stopped: ${name}`);
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'mcp',
+    description: 'Model Context Protocol server management',
+    subcommands: [
+      { name: 'list', description: 'List registered MCP servers' },
+      { name: 'add <name> <cmd> [args]', description: 'Add an MCP server' },
+      { name: 'remove <name>', description: 'Remove an MCP server' },
+      { name: 'start <name>', description: 'Start an MCP server' },
+      { name: 'stop <name>', description: 'Stop an MCP server' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('MCP Command');
+    await pretty.plain('Model Context Protocol server management\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(25)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/memory.ts

@@ -0,0 +1,174 @@
+/**
+ * Memory command - Manage agent memory
+ */
+
+import { Memory, createMemory, MemoryEntry, SearchResult } from '../../memory/memory';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface MemoryOptions {
+  userId?: string;
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: MemoryOptions): Promise<void> {
+  const action = args[0] || 'list';
+  const actionArgs = args.slice(1);
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    const memory = createMemory();
+
+    switch (action) {
+      case 'list':
+        await listMemories(memory, outputFormat);
+        break;
+      case 'add':
+        await addMemory(memory, actionArgs, outputFormat);
+        break;
+      case 'search':
+        await searchMemory(memory, actionArgs, outputFormat);
+        break;
+      case 'clear':
+        await clearMemory(memory, outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function listMemories(memory: Memory, outputFormat: string): Promise<void> {
+  const entries = memory.getAll();
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      memories: entries,
+      count: entries.length
+    }));
+  } else {
+    await pretty.heading('Memory Entries');
+    if (entries.length === 0) {
+      await pretty.info('No memories stored');
+    } else {
+      for (const entry of entries) {
+        await pretty.plain(`  • ${entry.content.substring(0, 100)}${entry.content.length > 100 ? '...' : ''}`);
+        if (entry.metadata) {
+          await pretty.dim(`    Created: ${new Date(entry.timestamp).toISOString()}`);
+        }
+      }
+    }
+    await pretty.newline();
+    await pretty.info(`Total: ${entries.length} memories`);
+  }
+}
+
+async function addMemory(memory: Memory, args: string[], outputFormat: string): Promise<void> {
+  const content = args.join(' ');
+  if (!content) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide content to add'));
+    } else {
+      await pretty.error('Please provide content to add');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  await memory.add(content, 'user');
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ added: content }));
+  } else {
+    await pretty.success('Memory added successfully');
+  }
+}
+
+async function searchMemory(memory: Memory, args: string[], outputFormat: string): Promise<void> {
+  const query = args.join(' ');
+  if (!query) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a search query'));
+    } else {
+      await pretty.error('Please provide a search query');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const results = await memory.search(query);
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      query,
+      results,
+      count: results.length
+    }));
+  } else {
+    await pretty.heading(`Search Results for: "${query}"`);
+    if (results.length === 0) {
+      await pretty.info('No matching memories found');
+    } else {
+      for (const result of results) {
+        const content = result.entry.content;
+        await pretty.plain(`  • ${content.substring(0, 100)}${content.length > 100 ? '...' : ''}`);
+        await pretty.dim(`    Score: ${result.score.toFixed(3)}`);
+      }
+    }
+    await pretty.newline();
+    await pretty.info(`Found: ${results.length} results`);
+  }
+}
+
+async function clearMemory(memory: Memory, outputFormat: string): Promise<void> {
+  memory.clear();
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ cleared: true }));
+  } else {
+    await pretty.success('Memory cleared successfully');
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'memory',
+    subcommands: [
+      { name: 'list', description: 'List all memories' },
+      { name: 'add <content>', description: 'Add a new memory' },
+      { name: 'search <query>', description: 'Search memories' },
+      { name: 'clear', description: 'Clear all memories' },
+      { name: 'help', description: 'Show this help' }
+    ],
+    options: [
+      { name: '--user-id', description: 'User ID for memory isolation' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Memory Command');
+    await pretty.plain('Manage agent memory storage\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(20)} ${cmd.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Options:');
+    for (const opt of help.options) {
+      await pretty.plain(`  ${opt.name.padEnd(20)} ${opt.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/n8n.ts

@@ -0,0 +1,143 @@
+/**
+ * CLI command: n8n
+ * N8N workflow integration
+ */
+
+import { N8NIntegration, createN8NIntegration } from '../features/n8n-integration';
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+
+  switch (subcommand) {
+    case 'trigger':
+      await handleTrigger(args.slice(1), options, isJson);
+      break;
+    case 'export':
+      await handleExport(args.slice(1), options, isJson);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+async function handleTrigger(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const webhookId = args[0];
+  const payloadStr = args[1] || '{}';
+
+  if (!webhookId) {
+    console.error('Error: Webhook ID is required');
+    process.exit(1);
+  }
+
+  let payload: Record<string, unknown>;
+  try {
+    payload = JSON.parse(payloadStr);
+  } catch {
+    payload = { data: payloadStr };
+  }
+
+  const baseUrl = options['base-url'] as string | undefined;
+  const apiKey = options['api-key'] as string | undefined;
+
+  const n8n = createN8NIntegration({ baseUrl, apiKey });
+  const result = await n8n.triggerWebhook(webhookId, payload);
+
+  if (isJson) {
+    console.log(JSON.stringify(result, null, 2));
+  } else {
+    if (result.success) {
+      console.log(`✓ Webhook triggered: ${webhookId}`);
+      if (result.response) {
+        console.log('Response:', JSON.stringify(result.response, null, 2));
+      }
+    } else {
+      console.error(`✗ Webhook failed: ${result.error}`);
+      process.exit(1);
+    }
+  }
+}
+
+async function handleExport(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const name = args[0] || 'workflow';
+  const stepsStr = options.steps as string | undefined;
+
+  let steps: Array<{ name: string; type: 'agent' | 'tool' | 'condition' }> = [];
+  
+  if (stepsStr) {
+    try {
+      steps = JSON.parse(stepsStr);
+    } catch {
+      // Parse simple format: "step1:agent,step2:tool"
+      steps = stepsStr.split(',').map(s => {
+        const [stepName, type] = s.split(':');
+        return { name: stepName, type: (type || 'agent') as 'agent' | 'tool' | 'condition' };
+      });
+    }
+  } else {
+    // Default example workflow
+    steps = [
+      { name: 'Process Input', type: 'agent' },
+      { name: 'Validate', type: 'condition' },
+      { name: 'Execute', type: 'tool' }
+    ];
+  }
+
+  const n8n = createN8NIntegration();
+  const workflow = n8n.exportWorkflowJSON(name, steps);
+
+  if (isJson || !options.pretty) {
+    console.log(workflow);
+  } else {
+    console.log(`N8N Workflow: ${name}\n`);
+    console.log('Steps:');
+    for (const step of steps) {
+      console.log(`  - ${step.name} (${step.type})`);
+    }
+    console.log('\nExported workflow JSON:');
+    console.log(workflow);
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'n8n',
+    description: 'N8N workflow integration',
+    subcommands: {
+      trigger: 'Trigger an N8N webhook',
+      export: 'Export workflow to N8N format'
+    },
+    flags: {
+      '--base-url': 'N8N base URL (default: http://localhost:5678)',
+      '--api-key': 'N8N API key',
+      '--steps': 'Workflow steps as JSON or "name:type,name:type"',
+      '--pretty': 'Pretty print export',
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts n8n trigger my-webhook \'{"data": "test"}\'',
+      'praisonai-ts n8n trigger webhook-id --base-url https://n8n.example.com',
+      'praisonai-ts n8n export my-workflow',
+      'praisonai-ts n8n export workflow --steps "Process:agent,Validate:condition"'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('N8N - Workflow integration\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nFlags:');
+    for (const [flag, desc] of Object.entries(help.flags)) {
+      console.log(`  ${flag.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/observability.ts

@@ -0,0 +1,119 @@
+/**
+ * Observability command - Monitoring and tracing
+ */
+
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface ObservabilityOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: ObservabilityOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'providers':
+        await listProviders(outputFormat);
+        break;
+      case 'info':
+        await showInfo(outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function showInfo(outputFormat: string): Promise<void> {
+  const info = {
+    feature: 'Observability',
+    description: 'Monitoring, tracing, and logging for agent operations',
+    providers: [
+      { name: 'ConsoleObservabilityProvider', description: 'Console-based logging' },
+      { name: 'MemoryObservabilityProvider', description: 'In-memory trace storage' },
+      { name: 'LangfuseObservabilityProvider', description: 'Langfuse integration' }
+    ],
+    capabilities: [
+      'Trace agent executions',
+      'Log LLM calls and responses',
+      'Track tool invocations',
+      'Measure performance metrics',
+      'Export traces to external systems'
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(info));
+  } else {
+    await pretty.heading('Observability');
+    await pretty.plain(info.description);
+    await pretty.newline();
+    await pretty.plain('Providers:');
+    for (const p of info.providers) {
+      await pretty.plain(`  • ${p.name}: ${p.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Capabilities:');
+    for (const cap of info.capabilities) {
+      await pretty.plain(`  • ${cap}`);
+    }
+  }
+}
+
+async function listProviders(outputFormat: string): Promise<void> {
+  const providers = [
+    { name: 'console', description: 'Console logging (default)', available: true },
+    { name: 'memory', description: 'In-memory storage', available: true },
+    { name: 'langfuse', description: 'Langfuse observability platform', available: true }
+  ];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ providers }));
+  } else {
+    await pretty.heading('Observability Providers');
+    for (const p of providers) {
+      const status = p.available ? '✓' : '✗';
+      await pretty.plain(`  ${status} ${p.name.padEnd(15)} ${p.description}`);
+    }
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'observability',
+    description: 'Monitoring and tracing for agent operations',
+    subcommands: [
+      { name: 'info', description: 'Show observability feature information' },
+      { name: 'providers', description: 'List available observability providers' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Observability Command');
+    await pretty.plain(help.description);
+    await pretty.newline();
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(20)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/planning.ts

@@ -0,0 +1,139 @@
+/**
+ * Planning command - Task planning and todo management
+ */
+
+import { createPlan, createTodoList, TodoItem, type PlanConfig, type TodoItemConfig } from '../../planning';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface PlanningOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: PlanningOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const actionArgs = args.slice(1);
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'create':
+        await createNewPlan(actionArgs, outputFormat);
+        break;
+      case 'todo':
+        await manageTodo(actionArgs, outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function createNewPlan(args: string[], outputFormat: string): Promise<void> {
+  const name = args.join(' ');
+  if (!name) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a name for the plan'));
+    } else {
+      await pretty.error('Please provide a name for the plan');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const plan = createPlan({
+    name,
+    description: name
+  });
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      id: plan.id,
+      name: plan.name,
+      status: plan.status
+    }));
+  } else {
+    await pretty.success(`Plan created: ${plan.id}`);
+    await pretty.plain(`Name: ${name}`);
+  }
+}
+
+async function manageTodo(args: string[], outputFormat: string): Promise<void> {
+  const subAction = args[0] || 'list';
+  const todoArgs = args.slice(1);
+
+  const todoList = createTodoList();
+
+  switch (subAction) {
+    case 'add':
+      const content = todoArgs.join(' ');
+      if (!content) {
+        if (outputFormat === 'json') {
+          outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide todo content'));
+        } else {
+          await pretty.error('Please provide todo content');
+        }
+        process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+      }
+      const newItem = new TodoItem({ content });
+      todoList.add(newItem);
+      if (outputFormat === 'json') {
+        outputJson(formatSuccess({ added: true, id: newItem.id, content: newItem.content }));
+      } else {
+        await pretty.success(`Todo added: ${content}`);
+      }
+      break;
+    case 'list':
+    default:
+      const items = todoList.items;
+      if (outputFormat === 'json') {
+        outputJson(formatSuccess({ items, count: items.length }));
+      } else {
+        await pretty.heading('Todo List');
+        if (items.length === 0) {
+          await pretty.info('No todos');
+        } else {
+          for (const todo of items) {
+            const status = todo.status === 'completed' ? '✓' : '○';
+            await pretty.plain(`  ${status} ${todo.content}`);
+          }
+        }
+      }
+      break;
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'planning',
+    subcommands: [
+      { name: 'create <goal>', description: 'Create a new plan' },
+      { name: 'todo add <title>', description: 'Add a todo item' },
+      { name: 'todo list', description: 'List todo items' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Planning Command');
+    await pretty.plain('Task planning and todo management\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(25)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/prompt-expand.ts

@@ -0,0 +1,77 @@
+/**
+ * Prompt Expand command - Expand prompts with more detail
+ */
+
+import { createPromptExpanderAgent } from '../../agent/prompt-expander';
+import { resolveConfig } from '../config/resolve';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface PromptExpandOptions {
+  model?: string;
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  strategy?: string;
+}
+
+export async function execute(args: string[], options: PromptExpandOptions): Promise<void> {
+  const prompt = args.join(' ');
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+  const config = resolveConfig(options);
+
+  if (!prompt) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a prompt to expand'));
+    } else {
+      await pretty.error('Please provide a prompt to expand');
+      await pretty.dim('Usage: praisonai-ts prompt-expand "your prompt"');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const startTime = Date.now();
+
+  try {
+    if (outputFormat !== 'json') {
+      await pretty.info(`Expanding prompt: "${prompt}"`);
+    }
+
+    const agent = createPromptExpanderAgent({
+      llm: config.model,
+      verbose: options.verbose,
+      defaultStrategy: options.strategy as any
+    });
+
+    const result = await agent.expand(prompt);
+
+    const duration = Date.now() - startTime;
+
+    if (outputFormat === 'json') {
+      outputJson(formatSuccess({
+        originalPrompt: prompt,
+        expandedPrompt: result.expanded,
+        strategy: result.strategy,
+        additions: result.additions
+      }, {
+        duration_ms: duration,
+        model: config.model
+      }));
+    } else {
+      await pretty.heading('Expanded Prompt');
+      await pretty.plain(result.expanded);
+      await pretty.newline();
+      await pretty.dim(`Strategy: ${result.strategy}`);
+      await pretty.success(`Completed in ${duration}ms`);
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}

src/praisonai-ts/src/cli/commands/providers.ts

@@ -0,0 +1,84 @@
+/**
+ * Providers command - List available LLM providers
+ */
+
+import { getAvailableProviders } from '../../llm/providers';
+import { hasApiKey } from '../runtime/env';
+import { outputJson, formatSuccess } from '../output/json';
+import * as pretty from '../output/pretty';
+
+export interface ProvidersOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+interface ProviderInfo {
+  name: string;
+  available: boolean;
+  hasApiKey: boolean;
+  models?: string[];
+}
+
+const PROVIDER_MODELS: Record<string, string[]> = {
+  openai: ['gpt-4o', 'gpt-4o-mini', 'gpt-4-turbo', 'gpt-4', 'gpt-3.5-turbo'],
+  anthropic: ['claude-sonnet-4-20250514', 'claude-3-5-sonnet-20241022', 'claude-3-opus-20240229', 'claude-3-haiku-20240307'],
+  google: ['gemini-2.0-flash', 'gemini-1.5-pro', 'gemini-1.5-flash']
+};
+
+export async function execute(args: string[], options: ProvidersOptions): Promise<void> {
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+  
+  const availableProviders = getAvailableProviders();
+  
+  const providers: ProviderInfo[] = [
+    {
+      name: 'openai',
+      available: availableProviders.includes('openai'),
+      hasApiKey: hasApiKey('openai'),
+      models: PROVIDER_MODELS.openai
+    },
+    {
+      name: 'anthropic',
+      available: availableProviders.includes('anthropic'),
+      hasApiKey: hasApiKey('anthropic'),
+      models: PROVIDER_MODELS.anthropic
+    },
+    {
+      name: 'google',
+      available: availableProviders.includes('google'),
+      hasApiKey: hasApiKey('google'),
+      models: PROVIDER_MODELS.google
+    }
+  ];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      providers: providers.map(p => ({
+        name: p.name,
+        available: p.available,
+        has_api_key: p.hasApiKey,
+        models: options.verbose ? p.models : undefined
+      }))
+    }));
+  } else {
+    await pretty.heading('Available Providers');
+    
+    for (const provider of providers) {
+      const status = provider.available ? '✅' : '❌';
+      const keyStatus = provider.hasApiKey ? '🔑' : '⚠️ No API key';
+      
+      await pretty.plain(`  ${status} ${provider.name} ${keyStatus}`);
+      
+      if (options.verbose && provider.models) {
+        for (const model of provider.models) {
+          await pretty.dim(`      - ${model}`);
+        }
+      }
+    }
+    
+    await pretty.newline();
+    await pretty.info('Set API keys via environment variables:');
+    await pretty.dim('  OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY');
+  }
+}

src/praisonai-ts/src/cli/commands/query-rewrite.ts

@@ -0,0 +1,80 @@
+/**
+ * Query Rewrite command - Rewrite queries for better search results
+ */
+
+import { createQueryRewriterAgent } from '../../agent/query-rewriter';
+import { resolveConfig } from '../config/resolve';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface QueryRewriteOptions {
+  model?: string;
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  strategy?: string;
+  count?: number;
+}
+
+export async function execute(args: string[], options: QueryRewriteOptions): Promise<void> {
+  const query = args.join(' ');
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+  const config = resolveConfig(options);
+
+  if (!query) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a query to rewrite'));
+    } else {
+      await pretty.error('Please provide a query to rewrite');
+      await pretty.dim('Usage: praisonai-ts query-rewrite "your search query"');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const startTime = Date.now();
+
+  try {
+    if (outputFormat !== 'json') {
+      await pretty.info(`Rewriting query: "${query}"`);
+    }
+
+    const agent = createQueryRewriterAgent({
+      llm: config.model,
+      verbose: options.verbose,
+      defaultStrategy: options.strategy as any
+    });
+
+    const result = await agent.rewrite(query);
+
+    const duration = Date.now() - startTime;
+
+    if (outputFormat === 'json') {
+      outputJson(formatSuccess({
+        originalQuery: query,
+        rewrittenQueries: result.rewritten,
+        strategy: result.strategy,
+        confidence: result.confidence
+      }, {
+        duration_ms: duration,
+        model: config.model
+      }));
+    } else {
+      await pretty.heading('Rewritten Queries');
+      for (let i = 0; i < result.rewritten.length; i++) {
+        await pretty.plain(`  ${i + 1}. ${result.rewritten[i]}`);
+      }
+      await pretty.newline();
+      await pretty.dim(`Strategy: ${result.strategy}`);
+      await pretty.success(`Completed in ${duration}ms`);
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}

src/praisonai-ts/src/cli/commands/repo-map.ts

@@ -0,0 +1,154 @@
+/**
+ * CLI command: repo-map
+ * Repository structure visualization and symbol extraction
+ */
+
+import { RepoMap, createRepoMap, getRepoTree } from '../features/repo-map';
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'tree';
+  const isJson = Boolean(options.output === 'json' || options.json);
+
+  switch (subcommand) {
+    case 'tree':
+      await handleTree(args.slice(1), options, isJson);
+      break;
+    case 'symbols':
+      await handleSymbols(args.slice(1), options, isJson);
+      break;
+    case 'help':
+    default:
+      if (subcommand !== 'help' && !subcommand.startsWith('-')) {
+        // Treat as path for tree command
+        await handleTree([subcommand, ...args.slice(1)], options, isJson);
+      } else {
+        showHelp(isJson);
+      }
+  }
+}
+
+async function handleTree(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const rootPath = args[0] || process.cwd();
+  const maxDepth = (options.depth as number) || 5;
+  const includeSymbols = Boolean(options.symbols);
+
+  const map = createRepoMap({
+    rootPath,
+    maxDepth,
+    includeSymbols
+  });
+
+  try {
+    const result = await map.generate();
+
+    if (isJson) {
+      console.log(JSON.stringify({
+        success: true,
+        root: result.root,
+        totalFiles: result.totalFiles,
+        totalDirectories: result.totalDirectories,
+        symbolCount: result.symbols.length
+      }, null, 2));
+    } else {
+      console.log(result.summary);
+    }
+  } catch (error: any) {
+    if (isJson) {
+      console.log(JSON.stringify({ success: false, error: error.message }));
+    } else {
+      console.error(`Error: ${error.message}`);
+    }
+    process.exit(1);
+  }
+}
+
+async function handleSymbols(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const rootPath = args[0] || process.cwd();
+  const maxDepth = (options.depth as number) || 5;
+
+  const map = createRepoMap({
+    rootPath,
+    maxDepth,
+    includeSymbols: true
+  });
+
+  try {
+    const result = await map.generate();
+
+    if (isJson) {
+      console.log(JSON.stringify({
+        success: true,
+        symbols: result.symbols,
+        count: result.symbols.length
+      }, null, 2));
+    } else {
+      console.log(`Symbols in ${rootPath}:\n`);
+      
+      const byType: Record<string, typeof result.symbols> = {};
+      for (const sym of result.symbols) {
+        if (!byType[sym.type]) byType[sym.type] = [];
+        byType[sym.type].push(sym);
+      }
+
+      for (const [type, symbols] of Object.entries(byType)) {
+        console.log(`${type}s (${symbols.length}):`);
+        for (const sym of symbols.slice(0, 20)) {
+          const exported = sym.exported ? ' [exported]' : '';
+          console.log(`  ${sym.name}${exported} (line ${sym.line})`);
+        }
+        if (symbols.length > 20) {
+          console.log(`  ... and ${symbols.length - 20} more`);
+        }
+        console.log();
+      }
+    }
+  } catch (error: any) {
+    if (isJson) {
+      console.log(JSON.stringify({ success: false, error: error.message }));
+    } else {
+      console.error(`Error: ${error.message}`);
+    }
+    process.exit(1);
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'repo-map',
+    description: 'Repository structure visualization and symbol extraction',
+    subcommands: {
+      tree: 'Show repository tree structure',
+      symbols: 'Extract and list code symbols'
+    },
+    flags: {
+      '--depth': 'Maximum directory depth (default: 5)',
+      '--symbols': 'Include symbols in tree output',
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts repo-map',
+      'praisonai-ts repo-map tree ./src',
+      'praisonai-ts repo-map tree --depth 3',
+      'praisonai-ts repo-map symbols ./src',
+      'praisonai-ts repo-map tree --symbols'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('Repo Map - Repository visualization\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nFlags:');
+    for (const [flag, desc] of Object.entries(help.flags)) {
+      console.log(`  ${flag.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/reranker.ts

@@ -0,0 +1,119 @@
+/**
+ * Reranker command - Document reranking
+ */
+
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface RerankerOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  provider?: string;
+}
+
+export async function execute(args: string[], options: RerankerOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'providers':
+        await listProviders(outputFormat);
+        break;
+      case 'info':
+        await showInfo(outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function showInfo(outputFormat: string): Promise<void> {
+  const info = {
+    feature: 'Reranker',
+    description: 'Rerank search results for improved relevance',
+    providers: [
+      { name: 'CohereReranker', description: 'Cohere reranking API' },
+      { name: 'CrossEncoderReranker', description: 'Cross-encoder model reranking' },
+      { name: 'LLMReranker', description: 'LLM-based reranking' }
+    ],
+    capabilities: [
+      'Rerank search results by relevance',
+      'Improve RAG retrieval quality',
+      'Multiple reranking strategies',
+      'Configurable top-k selection'
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(info));
+  } else {
+    await pretty.heading('Reranker');
+    await pretty.plain(info.description);
+    await pretty.newline();
+    await pretty.plain('Providers:');
+    for (const p of info.providers) {
+      await pretty.plain(`  • ${p.name}: ${p.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Capabilities:');
+    for (const cap of info.capabilities) {
+      await pretty.plain(`  • ${cap}`);
+    }
+  }
+}
+
+async function listProviders(outputFormat: string): Promise<void> {
+  const providers = [
+    { name: 'cohere', description: 'Cohere reranking API', available: true },
+    { name: 'cross-encoder', description: 'Cross-encoder model', available: true },
+    { name: 'llm', description: 'LLM-based reranking', available: true }
+  ];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ providers }));
+  } else {
+    await pretty.heading('Reranker Providers');
+    for (const p of providers) {
+      const status = p.available ? '✓' : '✗';
+      await pretty.plain(`  ${status} ${p.name.padEnd(15)} ${p.description}`);
+    }
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'reranker',
+    description: 'Document reranking for improved search relevance',
+    subcommands: [
+      { name: 'info', description: 'Show reranker feature information' },
+      { name: 'providers', description: 'List available reranker providers' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Reranker Command');
+    await pretty.plain(help.description);
+    await pretty.newline();
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(20)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/research.ts

@@ -0,0 +1,88 @@
+/**
+ * Research command - Deep research agent
+ */
+
+import { createDeepResearchAgent } from '../../agent/research';
+import { resolveConfig } from '../config/resolve';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface ResearchOptions {
+  model?: string;
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  depth?: number;
+  maxSources?: number;
+}
+
+export async function execute(args: string[], options: ResearchOptions): Promise<void> {
+  const query = args.join(' ');
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+  const config = resolveConfig(options);
+
+  if (!query) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a research query'));
+    } else {
+      await pretty.error('Please provide a research query');
+      await pretty.dim('Usage: praisonai-ts research "What are the latest AI trends?"');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const startTime = Date.now();
+
+  try {
+    if (outputFormat !== 'json') {
+      await pretty.info(`Researching: "${query}"`);
+    }
+
+    const agent = createDeepResearchAgent({
+      llm: config.model,
+      verbose: options.verbose,
+      maxIterations: options.depth
+    });
+
+    const result = await agent.research(query);
+
+    const duration = Date.now() - startTime;
+
+    if (outputFormat === 'json') {
+      outputJson(formatSuccess({
+        query,
+        answer: result.answer,
+        citations: result.citations,
+        reasoning: result.reasoning,
+        confidence: result.confidence
+      }, {
+        duration_ms: duration,
+        model: config.model
+      }));
+    } else {
+      await pretty.heading('Research Results');
+      await pretty.newline();
+      await pretty.plain(result.answer);
+      
+      if (result.citations && result.citations.length > 0) {
+        await pretty.newline();
+        await pretty.plain('Citations:');
+        for (const citation of result.citations) {
+          await pretty.dim(`  • ${citation.title || citation.url}`);
+        }
+      }
+      
+      await pretty.newline();
+      await pretty.success(`Completed in ${duration}ms`);
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}

src/praisonai-ts/src/cli/commands/router.ts

@@ -0,0 +1,122 @@
+/**
+ * Router command - Route requests to appropriate agents
+ */
+
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface RouterOptions {
+  model?: string;
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  routes?: string;
+}
+
+export async function execute(args: string[], options: RouterOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const actionArgs = args.slice(1);
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'analyze':
+        await analyzeInput(actionArgs, outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function analyzeInput(args: string[], outputFormat: string): Promise<void> {
+  const input = args.join(' ');
+  if (!input) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide input to analyze'));
+    } else {
+      await pretty.error('Please provide input to analyze');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const startTime = Date.now();
+
+  if (outputFormat !== 'json') {
+    await pretty.info(`Analyzing routing for: "${input}"`);
+  }
+
+  // Simple rule-based routing analysis
+  const routes = [
+    { name: 'greeting', pattern: /\b(hello|hi|hey|greetings)\b/i, priority: 1 },
+    { name: 'question', pattern: /\?$/, priority: 2 },
+    { name: 'code', pattern: /\b(code|function|class|implement|debug)\b/i, priority: 3 },
+    { name: 'research', pattern: /\b(research|analyze|investigate|study)\b/i, priority: 3 },
+    { name: 'creative', pattern: /\b(write|create|generate|compose)\b/i, priority: 2 },
+    { name: 'general', pattern: /.*/, priority: 0 }
+  ];
+
+  const matches = routes
+    .filter(r => r.pattern.test(input))
+    .sort((a, b) => b.priority - a.priority);
+
+  const selectedRoute = matches[0]?.name || 'general';
+  const confidence = matches[0]?.priority ? Math.min(0.5 + matches[0].priority * 0.15, 0.95) : 0.5;
+
+  const duration = Date.now() - startTime;
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      input,
+      selectedRoute,
+      confidence,
+      matchedRoutes: matches.map(m => m.name)
+    }, {
+      duration_ms: duration
+    }));
+  } else {
+    await pretty.heading('Routing Analysis');
+    await pretty.plain(`Input: "${input}"`);
+    await pretty.plain(`Selected Route: ${selectedRoute}`);
+    await pretty.plain(`Confidence: ${(confidence * 100).toFixed(1)}%`);
+    await pretty.plain(`Matched Routes: ${matches.map(m => m.name).join(', ')}`);
+    await pretty.newline();
+    await pretty.success(`Analyzed in ${duration}ms`);
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'router',
+    description: 'Route requests to appropriate agents based on content analysis',
+    subcommands: [
+      { name: 'analyze <input>', description: 'Analyze input and suggest routing' },
+      { name: 'help', description: 'Show this help' }
+    ],
+    usage: 'For programmatic routing with actual agents, use the RouterAgent SDK class'
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Router Command');
+    await pretty.plain('Route requests to appropriate agents\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(25)} ${cmd.description}`);
+    }
+    await pretty.newline();
+    await pretty.dim('Note: For full routing with agents, use the RouterAgent SDK class');
+  }
+}

src/praisonai-ts/src/cli/commands/run.ts

@@ -0,0 +1,97 @@
+/**
+ * Run command - Run an agent with a task
+ */
+
+import { Agent } from '../../agent';
+import { resolveConfig } from '../config/resolve';
+import { printSuccess, printError, outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES, normalizeError } from '../output/errors';
+
+export interface RunOptions {
+  agent?: string;
+  tools?: string;
+  model?: string;
+  verbose?: boolean;
+  profile?: string;
+  config?: string;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: RunOptions): Promise<void> {
+  const task = args[0];
+  
+  if (!task) {
+    if (options.json || options.output === 'json') {
+      printError(ERROR_CODES.MISSING_ARG, 'Please provide a task');
+    } else {
+      await pretty.error('Please provide a task');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  // Resolve config with precedence
+  const config = resolveConfig({
+    configPath: options.config,
+    profile: options.profile,
+    model: options.model,
+    verbose: options.verbose
+  });
+
+  const startTime = Date.now();
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    // Parse tools if provided
+    const tools: string[] = options.tools ? options.tools.split(',').map(t => t.trim()) : [];
+
+    // Create agent
+    const agent = new Agent({
+      name: 'CLI Agent',
+      instructions: 'You are a helpful AI assistant.',
+      llm: config.model,
+      verbose: config.verbose
+    });
+
+    // Execute task
+    const result = await agent.start(task);
+
+    const duration = Date.now() - startTime;
+
+    if (outputFormat === 'json') {
+      outputJson(formatSuccess(
+        { 
+          result: result,
+          agent: 'CLI Agent',
+          task: task
+        },
+        {
+          duration_ms: duration,
+          model: config.model
+        }
+      ));
+    } else {
+      if (typeof result === 'string') {
+        console.log(result);
+      } else {
+        console.log(JSON.stringify(result, null, 2));
+      }
+    }
+
+  } catch (error) {
+    const cliError = normalizeError(error);
+    
+    if (outputFormat === 'json') {
+      outputJson(formatError(cliError.code, cliError.message, cliError.details));
+    } else {
+      await pretty.error(cliError.message);
+      if (config.verbose && error instanceof Error && error.stack) {
+        await pretty.dim(error.stack);
+      }
+    }
+    
+    process.exit(cliError.exitCode);
+  }
+}

src/praisonai-ts/src/cli/commands/sandbox.ts

@@ -0,0 +1,139 @@
+/**
+ * CLI command: sandbox
+ * Safe command execution with restrictions
+ */
+
+import { SandboxExecutor, createSandboxExecutor, CommandValidator, type SandboxMode } from '../features/sandbox-executor';
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+
+  switch (subcommand) {
+    case 'exec':
+      await handleExec(args.slice(1), options, isJson);
+      break;
+    case 'check':
+      await handleCheck(args.slice(1), isJson);
+      break;
+    case 'mode':
+      await handleMode(args.slice(1), isJson);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+async function handleExec(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const command = args.join(' ');
+  if (!command) {
+    console.error('Error: Command is required');
+    process.exit(1);
+  }
+
+  const mode = (options.mode as SandboxMode) || 'basic';
+  const timeout = (options.timeout as number) || 30000;
+  
+  const executor = createSandboxExecutor({ mode, timeout });
+  const result = await executor.execute(command);
+
+  if (isJson) {
+    console.log(JSON.stringify(result, null, 2));
+  } else {
+    if (result.success) {
+      console.log('✓ Command executed successfully');
+      console.log(`Duration: ${result.duration}ms`);
+      if (result.stdout) {
+        console.log('\nOutput:');
+        console.log(result.stdout);
+      }
+    } else {
+      console.error('✗ Command failed');
+      if (result.stderr) console.error(result.stderr);
+    }
+  }
+
+  if (!result.success) process.exit(result.exitCode || 1);
+}
+
+async function handleCheck(args: string[], isJson: boolean): Promise<void> {
+  const command = args.join(' ');
+  if (!command) {
+    console.error('Error: Command is required');
+    process.exit(1);
+  }
+
+  const validator = new CommandValidator();
+  const result = validator.validate(command);
+
+  if (isJson) {
+    console.log(JSON.stringify({ command, ...result }, null, 2));
+  } else {
+    if (result.valid) {
+      console.log(`✓ Command is allowed: ${command}`);
+    } else {
+      console.log(`✗ Command blocked: ${command}`);
+      console.log(`  Reason: ${result.reason}`);
+    }
+  }
+}
+
+async function handleMode(args: string[], isJson: boolean): Promise<void> {
+  const modes: Record<SandboxMode, string> = {
+    disabled: 'No execution allowed',
+    basic: 'Basic validation, blocks dangerous patterns',
+    strict: 'Minimal environment, restricted PATH',
+    'network-isolated': 'No network access (proxy blocked)'
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, modes }, null, 2));
+  } else {
+    console.log('Sandbox Modes:\n');
+    for (const [mode, desc] of Object.entries(modes)) {
+      console.log(`  ${mode.padEnd(18)} ${desc}`);
+    }
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'sandbox',
+    description: 'Safe command execution with restrictions',
+    subcommands: {
+      exec: 'Execute a command in sandbox',
+      check: 'Check if a command would be allowed',
+      mode: 'List available sandbox modes'
+    },
+    flags: {
+      '--mode': 'Sandbox mode (disabled, basic, strict, network-isolated)',
+      '--timeout': 'Execution timeout in ms (default: 30000)',
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts sandbox exec "ls -la"',
+      'praisonai-ts sandbox exec "npm install" --mode strict',
+      'praisonai-ts sandbox check "rm -rf /"',
+      'praisonai-ts sandbox mode'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('Sandbox - Safe command execution\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nFlags:');
+    for (const [flag, desc] of Object.entries(help.flags)) {
+      console.log(`  ${flag.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/scheduler.ts

@@ -0,0 +1,266 @@
+/**
+ * CLI command: scheduler
+ * Agent task scheduling with cron-like patterns
+ */
+
+import { Scheduler, createScheduler, cronExpressions } from '../features/scheduler';
+
+export async function execute(args: string[], options: Record<string, unknown>): Promise<void> {
+  const subcommand = args[0] || 'help';
+  const isJson = Boolean(options.output === 'json' || options.json);
+
+  switch (subcommand) {
+    case 'create':
+      await handleCreate(args.slice(1), options, isJson);
+      break;
+    case 'list':
+      await handleList(options, isJson);
+      break;
+    case 'run':
+      await handleRun(args.slice(1), options, isJson);
+      break;
+    case 'remove':
+      await handleRemove(args.slice(1), options, isJson);
+      break;
+    case 'enable':
+      await handleEnable(args.slice(1), options, isJson);
+      break;
+    case 'disable':
+      await handleDisable(args.slice(1), options, isJson);
+      break;
+    case 'patterns':
+      await handlePatterns(isJson);
+      break;
+    case 'help':
+    default:
+      showHelp(isJson);
+  }
+}
+
+async function handleCreate(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const name = args[0];
+  const cron = options.cron as string | undefined;
+  const interval = options.interval as number | undefined;
+
+  if (!name) {
+    const error = { error: 'Task name is required' };
+    if (isJson) {
+      console.log(JSON.stringify(error));
+    } else {
+      console.error('Error: Task name is required');
+      console.log('Usage: praisonai-ts scheduler create <name> --cron "* * * * *"');
+    }
+    process.exit(1);
+  }
+
+  if (!cron && !interval) {
+    const error = { error: 'Either --cron or --interval is required' };
+    if (isJson) {
+      console.log(JSON.stringify(error));
+    } else {
+      console.error('Error: Either --cron or --interval is required');
+    }
+    process.exit(1);
+  }
+
+  const scheduler = createScheduler();
+  const id = scheduler.add({
+    name,
+    cron,
+    interval: interval ? interval * 1000 : undefined,
+    task: async () => {
+      console.log(`Task ${name} executed at ${new Date().toISOString()}`);
+      return { executed: true };
+    }
+  });
+
+  const result = {
+    success: true,
+    id,
+    name,
+    cron,
+    interval,
+    message: `Task '${name}' created with ID: ${id}`
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(result, null, 2));
+  } else {
+    console.log(`✓ Task '${name}' created`);
+    console.log(`  ID: ${id}`);
+    if (cron) console.log(`  Cron: ${cron}`);
+    if (interval) console.log(`  Interval: ${interval}s`);
+  }
+}
+
+async function handleList(options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const scheduler = createScheduler();
+  const tasks = scheduler.getAllTasks();
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, tasks }, null, 2));
+  } else {
+    if (tasks.length === 0) {
+      console.log('No scheduled tasks');
+    } else {
+      console.log('Scheduled Tasks:');
+      for (const task of tasks) {
+        console.log(`  ${task.name} (${task.id})`);
+        console.log(`    Status: ${task.status}`);
+        console.log(`    Enabled: ${task.enabled}`);
+        console.log(`    Run count: ${task.runCount}`);
+        if (task.nextRun) console.log(`    Next run: ${task.nextRun.toISOString()}`);
+      }
+    }
+  }
+}
+
+async function handleRun(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Task ID is required');
+    process.exit(1);
+  }
+
+  const scheduler = createScheduler();
+  try {
+    const result = await scheduler.runNow(id);
+    if (isJson) {
+      console.log(JSON.stringify({ success: true, result }, null, 2));
+    } else {
+      console.log(`✓ Task ${id} executed successfully`);
+    }
+  } catch (error: any) {
+    if (isJson) {
+      console.log(JSON.stringify({ success: false, error: error.message }));
+    } else {
+      console.error(`Error: ${error.message}`);
+    }
+    process.exit(1);
+  }
+}
+
+async function handleRemove(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Task ID is required');
+    process.exit(1);
+  }
+
+  const scheduler = createScheduler();
+  const removed = scheduler.remove(id);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: removed, id }));
+  } else {
+    if (removed) {
+      console.log(`✓ Task ${id} removed`);
+    } else {
+      console.error(`Task ${id} not found`);
+      process.exit(1);
+    }
+  }
+}
+
+async function handleEnable(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Task ID is required');
+    process.exit(1);
+  }
+
+  const scheduler = createScheduler();
+  const enabled = scheduler.enable(id);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: enabled, id }));
+  } else {
+    console.log(enabled ? `✓ Task ${id} enabled` : `Task ${id} not found`);
+  }
+}
+
+async function handleDisable(args: string[], options: Record<string, unknown>, isJson: boolean): Promise<void> {
+  const id = args[0];
+  if (!id) {
+    console.error('Error: Task ID is required');
+    process.exit(1);
+  }
+
+  const scheduler = createScheduler();
+  const disabled = scheduler.disable(id);
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: disabled, id }));
+  } else {
+    console.log(disabled ? `✓ Task ${id} disabled` : `Task ${id} not found`);
+  }
+}
+
+async function handlePatterns(isJson: boolean): Promise<void> {
+  const patterns = {
+    everyMinute: cronExpressions.everyMinute,
+    every5Minutes: cronExpressions.every5Minutes,
+    every15Minutes: cronExpressions.every15Minutes,
+    everyHour: cronExpressions.everyHour,
+    everyDay: cronExpressions.everyDay,
+    everyWeek: cronExpressions.everyWeek,
+    everyMonth: cronExpressions.everyMonth,
+    weekdays: cronExpressions.weekdays,
+    weekends: cronExpressions.weekends
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify({ success: true, patterns }, null, 2));
+  } else {
+    console.log('Common Cron Patterns:');
+    for (const [name, pattern] of Object.entries(patterns)) {
+      console.log(`  ${name}: ${pattern}`);
+    }
+  }
+}
+
+function showHelp(isJson: boolean): void {
+  const help = {
+    command: 'scheduler',
+    description: 'Agent task scheduling with cron-like patterns',
+    subcommands: {
+      create: 'Create a scheduled task',
+      list: 'List all scheduled tasks',
+      run: 'Run a task immediately',
+      remove: 'Remove a scheduled task',
+      enable: 'Enable a task',
+      disable: 'Disable a task',
+      patterns: 'Show common cron patterns'
+    },
+    flags: {
+      '--cron': 'Cron expression (e.g., "*/5 * * * *")',
+      '--interval': 'Interval in seconds',
+      '--json': 'Output in JSON format'
+    },
+    examples: [
+      'praisonai-ts scheduler create my-task --cron "*/5 * * * *"',
+      'praisonai-ts scheduler create backup --interval 3600',
+      'praisonai-ts scheduler list',
+      'praisonai-ts scheduler run <task-id>',
+      'praisonai-ts scheduler patterns'
+    ]
+  };
+
+  if (isJson) {
+    console.log(JSON.stringify(help, null, 2));
+  } else {
+    console.log('Scheduler - Agent task scheduling\n');
+    console.log('Subcommands:');
+    for (const [cmd, desc] of Object.entries(help.subcommands)) {
+      console.log(`  ${cmd.padEnd(12)} ${desc}`);
+    }
+    console.log('\nFlags:');
+    for (const [flag, desc] of Object.entries(help.flags)) {
+      console.log(`  ${flag.padEnd(12)} ${desc}`);
+    }
+    console.log('\nExamples:');
+    for (const ex of help.examples) {
+      console.log(`  ${ex}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/session.ts

@@ -0,0 +1,214 @@
+/**
+ * Session command - Manage agent sessions
+ */
+
+import { Session, SessionManager, getSessionManager } from '../../session';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface SessionOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: SessionOptions): Promise<void> {
+  const action = args[0] || 'list';
+  const actionArgs = args.slice(1);
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    const manager = getSessionManager();
+
+    switch (action) {
+      case 'list':
+        await listSessions(manager, outputFormat);
+        break;
+      case 'create':
+        await createSession(manager, actionArgs, outputFormat);
+        break;
+      case 'get':
+        await getSession(manager, actionArgs, outputFormat);
+        break;
+      case 'delete':
+        await deleteSession(manager, actionArgs, outputFormat);
+        break;
+      case 'export':
+        await exportSession(manager, actionArgs, outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function listSessions(manager: SessionManager, outputFormat: string): Promise<void> {
+  const sessions = manager.list();
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      sessions: sessions.map((s: Session) => ({
+        id: s.id,
+        messageCount: s.messages.length,
+        createdAt: s.createdAt
+      })),
+      count: sessions.length
+    }));
+  } else {
+    await pretty.heading('Sessions');
+    if (sessions.length === 0) {
+      await pretty.info('No sessions found');
+    } else {
+      for (const session of sessions) {
+        await pretty.plain(`  • ${session.id}`);
+        await pretty.dim(`    Messages: ${session.messages.length}`);
+      }
+    }
+    await pretty.newline();
+    await pretty.info(`Total: ${sessions.length} sessions`);
+  }
+}
+
+async function createSession(manager: SessionManager, args: string[], outputFormat: string): Promise<void> {
+  const sessionId = args[0];
+  const session = manager.create({ id: sessionId });
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      created: true,
+      sessionId: session.id
+    }));
+  } else {
+    await pretty.success(`Session created: ${session.id}`);
+  }
+}
+
+async function getSession(manager: SessionManager, args: string[], outputFormat: string): Promise<void> {
+  const sessionId = args[0];
+  if (!sessionId) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a session ID'));
+    } else {
+      await pretty.error('Please provide a session ID');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const session = manager.get(sessionId);
+  if (!session) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, `Session not found: ${sessionId}`));
+    } else {
+      await pretty.error(`Session not found: ${sessionId}`);
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+
+  const messages = session.messages;
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      id: session.id,
+      messages,
+      messageCount: messages.length
+    }));
+  } else {
+    await pretty.heading(`Session: ${session.id}`);
+    await pretty.plain(`Messages: ${messages.length}`);
+    await pretty.newline();
+    for (const msg of messages.slice(-10)) {
+      const content = msg.content || '';
+      await pretty.plain(`  [${msg.role}] ${content.substring(0, 80)}${content.length > 80 ? '...' : ''}`);
+    }
+  }
+}
+
+async function deleteSession(manager: SessionManager, args: string[], outputFormat: string): Promise<void> {
+  const sessionId = args[0];
+  if (!sessionId) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a session ID'));
+    } else {
+      await pretty.error('Please provide a session ID');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const deleted = manager.delete(sessionId);
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ deleted, sessionId }));
+  } else {
+    if (deleted) {
+      await pretty.success(`Session deleted: ${sessionId}`);
+    } else {
+      await pretty.warn(`Session not found: ${sessionId}`);
+    }
+  }
+}
+
+async function exportSession(manager: SessionManager, args: string[], outputFormat: string): Promise<void> {
+  const sessionId = args[0];
+  if (!sessionId) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a session ID'));
+    } else {
+      await pretty.error('Please provide a session ID');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const session = manager.get(sessionId);
+  if (!session) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, `Session not found: ${sessionId}`));
+    } else {
+      await pretty.error(`Session not found: ${sessionId}`);
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+
+  const exported = session.toJSON();
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(exported));
+  } else {
+    console.log(JSON.stringify(exported, null, 2));
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'session',
+    subcommands: [
+      { name: 'list', description: 'List all sessions' },
+      { name: 'create [id]', description: 'Create a new session' },
+      { name: 'get <id>', description: 'Get session details' },
+      { name: 'delete <id>', description: 'Delete a session' },
+      { name: 'export <id>', description: 'Export session data' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Session Command');
+    await pretty.plain('Manage agent sessions\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(20)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/skills.ts

@@ -0,0 +1,228 @@
+/**
+ * Skills command - Manage agent skills
+ */
+
+import { SkillManager, createSkillManager, Skill } from '../../skills';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface SkillsOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: SkillsOptions): Promise<void> {
+  const action = args[0] || 'list';
+  const actionArgs = args.slice(1);
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    const searchPath = actionArgs[0] || '.';
+    const manager = createSkillManager({ paths: [searchPath] });
+
+    switch (action) {
+      case 'list':
+        await listSkills(manager, outputFormat);
+        break;
+      case 'discover':
+        await discoverSkills(manager, actionArgs, outputFormat);
+        break;
+      case 'validate':
+        await validateSkill(manager, actionArgs, outputFormat);
+        break;
+      case 'info':
+        await skillInfo(manager, actionArgs, outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function listSkills(manager: SkillManager, outputFormat: string): Promise<void> {
+  const skills = manager.list();
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      skills: skills.map((s: Skill) => ({
+        name: s.metadata.name,
+        description: s.metadata.description,
+        path: s.path
+      })),
+      count: skills.length
+    }));
+  } else {
+    await pretty.heading('Available Skills');
+    if (skills.length === 0) {
+      await pretty.info('No skills loaded');
+      await pretty.dim('Run "praisonai-ts skills discover <path>" to discover skills');
+    } else {
+      for (const skill of skills) {
+        await pretty.plain(`  • ${skill.metadata.name}`);
+        if (skill.metadata.description) {
+          await pretty.dim(`    ${skill.metadata.description}`);
+        }
+      }
+    }
+    await pretty.newline();
+    await pretty.info(`Total: ${skills.length} skills`);
+  }
+}
+
+async function discoverSkills(manager: SkillManager, args: string[], outputFormat: string): Promise<void> {
+  const searchPath = args[0] || '.';
+  
+  const discovered = await manager.discover();
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      discovered: discovered.map((s: Skill) => ({
+        name: s.metadata.name,
+        description: s.metadata.description,
+        path: s.path
+      })),
+      count: discovered.length,
+      searchPath
+    }));
+  } else {
+    await pretty.heading(`Discovered Skills in: ${searchPath}`);
+    if (discovered.length === 0) {
+      await pretty.info('No skills found');
+    } else {
+      for (const skill of discovered) {
+        await pretty.plain(`  • ${skill.metadata.name}`);
+        if (skill.metadata.description) {
+          await pretty.dim(`    ${skill.metadata.description}`);
+        }
+        if (skill.path) {
+          await pretty.dim(`    Path: ${skill.path}`);
+        }
+      }
+    }
+    await pretty.newline();
+    await pretty.info(`Found: ${discovered.length} skills`);
+  }
+}
+
+async function validateSkill(manager: SkillManager, args: string[], outputFormat: string): Promise<void> {
+  const skillPath = args[0];
+  if (!skillPath) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a skill path'));
+    } else {
+      await pretty.error('Please provide a skill path');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  try {
+    // Load the skill first, then validate
+    const skill = await manager.loadSkill(skillPath);
+    const result = manager.validate(skill);
+    
+    if (outputFormat === 'json') {
+      outputJson(formatSuccess({
+        valid: result.valid,
+        path: skillPath,
+        errors: result.errors || []
+      }));
+    } else {
+      if (result.valid) {
+        await pretty.success(`Skill is valid: ${skillPath}`);
+      } else {
+        await pretty.error(`Skill validation failed: ${skillPath}`);
+        if (result.errors) {
+          for (const err of result.errors) {
+            await pretty.plain(`  ❌ ${err}`);
+          }
+        }
+      }
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(`Validation error: ${error instanceof Error ? error.message : String(error)}`);
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function skillInfo(manager: SkillManager, args: string[], outputFormat: string): Promise<void> {
+  const skillName = args[0];
+  if (!skillName) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a skill name'));
+    } else {
+      await pretty.error('Please provide a skill name');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  const skill = manager.get(skillName);
+  if (!skill) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, `Skill not found: ${skillName}`));
+    } else {
+      await pretty.error(`Skill not found: ${skillName}`);
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      name: skill.metadata.name,
+      description: skill.metadata.description,
+      path: skill.path,
+      metadata: skill.metadata
+    }));
+  } else {
+    await pretty.heading(`Skill: ${skill.metadata.name}`);
+    await pretty.keyValue({
+      'Name': skill.metadata.name,
+      'Description': skill.metadata.description || 'No description',
+      'Path': skill.path || 'N/A'
+    });
+    if (skill.metadata.metadata && Object.keys(skill.metadata.metadata).length > 0) {
+      await pretty.newline();
+      await pretty.plain('Metadata:');
+      await pretty.plain(JSON.stringify(skill.metadata.metadata, null, 2));
+    }
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'skills',
+    subcommands: [
+      { name: 'list', description: 'List loaded skills' },
+      { name: 'discover <path>', description: 'Discover skills in directory' },
+      { name: 'validate <path>', description: 'Validate a skill' },
+      { name: 'info <name>', description: 'Show skill information' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Skills Command');
+    await pretty.plain('Manage agent skills\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(20)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/telemetry.ts

@@ -0,0 +1,117 @@
+/**
+ * Telemetry command - Usage monitoring and analytics
+ */
+
+import { getTelemetry, enableTelemetry, disableTelemetry, cleanupTelemetry } from '../../telemetry';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface TelemetryOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: TelemetryOptions): Promise<void> {
+  const action = args[0] || 'status';
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'enable':
+        enableTelemetry();
+        if (outputFormat === 'json') {
+          outputJson(formatSuccess({ enabled: true }));
+        } else {
+          await pretty.success('Telemetry enabled');
+        }
+        break;
+      case 'disable':
+        disableTelemetry();
+        if (outputFormat === 'json') {
+          outputJson(formatSuccess({ enabled: false }));
+        } else {
+          await pretty.success('Telemetry disabled');
+        }
+        break;
+      case 'status':
+        await showStatus(outputFormat);
+        break;
+      case 'clear':
+        cleanupTelemetry();
+        if (outputFormat === 'json') {
+          outputJson(formatSuccess({ cleared: true }));
+        } else {
+          await pretty.success('Telemetry data cleared');
+        }
+        break;
+      case 'export':
+        await exportTelemetry(outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function showStatus(outputFormat: string): Promise<void> {
+  const telemetry = getTelemetry();
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      enabled: telemetry.isEnabled()
+    }));
+  } else {
+    await pretty.heading('Telemetry Status');
+    await pretty.plain(`Enabled: ${telemetry.isEnabled() ? 'Yes' : 'No'}`);
+  }
+}
+
+async function exportTelemetry(outputFormat: string): Promise<void> {
+  const telemetry = getTelemetry();
+  
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      enabled: telemetry.isEnabled(),
+      exportedAt: new Date().toISOString()
+    }));
+  } else {
+    await pretty.plain(`Telemetry enabled: ${telemetry.isEnabled()}`);
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'telemetry',
+    subcommands: [
+      { name: 'status', description: 'Show telemetry status' },
+      { name: 'enable', description: 'Enable telemetry collection' },
+      { name: 'disable', description: 'Disable telemetry collection' },
+      { name: 'clear', description: 'Clear collected telemetry data' },
+      { name: 'export', description: 'Export telemetry data' },
+      { name: 'help', description: 'Show this help' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Telemetry Command');
+    await pretty.plain('Usage monitoring and analytics\n');
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(15)} ${cmd.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/tools.ts

@@ -0,0 +1,160 @@
+/**
+ * Tools command - List or manage tools
+ */
+
+import { getRegistry, FunctionTool } from '../../tools/decorator';
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface ToolsOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+interface ToolInfo {
+  name: string;
+  description?: string;
+  parameters?: unknown;
+}
+
+// Built-in tools that are always available
+const BUILTIN_TOOLS: ToolInfo[] = [
+  { name: 'arxiv_search', description: 'Search arXiv for academic papers' },
+  { name: 'web_search', description: 'Search the web for information' },
+  { name: 'calculator', description: 'Perform mathematical calculations' },
+  { name: 'code_executor', description: 'Execute code snippets' },
+  { name: 'file_reader', description: 'Read file contents' },
+  { name: 'file_writer', description: 'Write content to files' }
+];
+
+export async function execute(args: string[], options: ToolsOptions): Promise<void> {
+  const subcommand = args[0] || 'list';
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  switch (subcommand) {
+    case 'list':
+      await listTools(options, outputFormat);
+      break;
+    case 'info':
+      await toolInfo(args.slice(1), options, outputFormat);
+      break;
+    default:
+      if (outputFormat === 'json') {
+        outputJson(formatError(ERROR_CODES.INVALID_ARGS, `Unknown subcommand: ${subcommand}`));
+      } else {
+        await pretty.error(`Unknown subcommand: ${subcommand}`);
+      }
+      process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+}
+
+async function listTools(options: ToolsOptions, outputFormat: string): Promise<void> {
+  // Get registered tools from registry
+  const registry = getRegistry();
+  const registeredTools = registry.list();
+  
+  // Combine built-in and registered tools
+  const allTools: ToolInfo[] = [
+    ...BUILTIN_TOOLS,
+    ...registeredTools.map((t: FunctionTool) => ({
+      name: t.name,
+      description: t.description,
+      parameters: t.parameters
+    }))
+  ];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      tools: allTools.map(t => ({
+        name: t.name,
+        description: t.description,
+        parameters: options.verbose ? t.parameters : undefined
+      })),
+      count: allTools.length
+    }));
+  } else {
+    await pretty.heading('Available Tools');
+    
+    await pretty.plain('Built-in Tools:');
+    for (const tool of BUILTIN_TOOLS) {
+      await pretty.plain(`  • ${tool.name}`);
+      if (tool.description) {
+        await pretty.dim(`    ${tool.description}`);
+      }
+    }
+    
+    if (registeredTools.length > 0) {
+      await pretty.newline();
+      await pretty.plain('Registered Tools:');
+      for (const tool of registeredTools) {
+        await pretty.plain(`  • ${tool.name}`);
+        if (tool.description) {
+          await pretty.dim(`    ${tool.description}`);
+        }
+      }
+    }
+    
+    await pretty.newline();
+    await pretty.info(`Total: ${allTools.length} tools`);
+  }
+}
+
+async function toolInfo(args: string[], options: ToolsOptions, outputFormat: string): Promise<void> {
+  const toolName = args[0];
+  
+  if (!toolName) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.MISSING_ARG, 'Please provide a tool name'));
+    } else {
+      await pretty.error('Please provide a tool name');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  // Look for tool in built-in and registered tools
+  const builtinTool = BUILTIN_TOOLS.find(t => t.name === toolName);
+  const registry = getRegistry();
+  const registeredTool = registry.get(toolName);
+  
+  const tool = builtinTool || (registeredTool ? {
+    name: registeredTool.name,
+    description: registeredTool.description,
+    parameters: registeredTool.parameters
+  } : null);
+
+  if (!tool) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.TOOL_NOT_FOUND, `Tool not found: ${toolName}`));
+    } else {
+      await pretty.error(`Tool not found: ${toolName}`);
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({
+      tool: {
+        name: tool.name,
+        description: tool.description,
+        parameters: tool.parameters,
+        type: builtinTool ? 'builtin' : 'registered'
+      }
+    }));
+  } else {
+    await pretty.heading(`Tool: ${tool.name}`);
+    await pretty.keyValue({
+      'Name': tool.name,
+      'Type': builtinTool ? 'Built-in' : 'Registered',
+      'Description': tool.description || 'No description'
+    });
+    
+    if (tool.parameters && options.verbose) {
+      await pretty.newline();
+      await pretty.plain('Parameters:');
+      await pretty.plain(JSON.stringify(tool.parameters, null, 2));
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/vector.ts

@@ -0,0 +1,146 @@
+/**
+ * Vector command - Vector store management
+ */
+
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface VectorOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  store?: string;
+}
+
+export async function execute(args: string[], options: VectorOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'providers':
+        await listProviders(outputFormat);
+        break;
+      case 'info':
+        await showInfo(outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function showInfo(outputFormat: string): Promise<void> {
+  const info = {
+    feature: 'Vector Stores',
+    description: 'Vector database integrations for embeddings and similarity search',
+    providers: [
+      { name: 'MemoryVectorStore', description: 'In-memory vector store for development' },
+      { name: 'PineconeVectorStore', description: 'Pinecone cloud vector database' },
+      { name: 'WeaviateVectorStore', description: 'Weaviate vector search engine' },
+      { name: 'QdrantVectorStore', description: 'Qdrant vector database' },
+      { name: 'ChromaVectorStore', description: 'ChromaDB embedding database' }
+    ],
+    sdkUsage: `
+import { createMemoryVectorStore, createPineconeStore } from 'praisonai';
+
+// Create a memory vector store
+const store = createMemoryVectorStore('my-store');
+
+// Create index
+await store.createIndex({ indexName: 'docs', dimension: 1536 });
+
+// Upsert vectors
+await store.upsert({
+  indexName: 'docs',
+  vectors: [{ id: '1', vector: [...], metadata: { text: 'Hello' } }]
+});
+
+// Query
+const results = await store.query({
+  indexName: 'docs',
+  vector: [...],
+  topK: 5
+});
+`
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(info));
+  } else {
+    await pretty.heading('Vector Stores');
+    await pretty.plain(info.description);
+    await pretty.newline();
+    await pretty.plain('Available Providers:');
+    for (const p of info.providers) {
+      await pretty.plain(`  • ${p.name}: ${p.description}`);
+    }
+    await pretty.newline();
+    await pretty.dim('Use the SDK for full vector store functionality');
+  }
+}
+
+async function listProviders(outputFormat: string): Promise<void> {
+  const providers = [
+    { name: 'memory', description: 'In-memory vector store (default)', available: true },
+    { name: 'pinecone', description: 'Pinecone vector database', available: true },
+    { name: 'weaviate', description: 'Weaviate vector database', available: true },
+    { name: 'qdrant', description: 'Qdrant vector database', available: true },
+    { name: 'chroma', description: 'ChromaDB vector database', available: true }
+  ];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ providers }));
+  } else {
+    await pretty.heading('Vector Store Providers');
+    for (const p of providers) {
+      const status = p.available ? '✓' : '✗';
+      await pretty.plain(`  ${status} ${p.name.padEnd(15)} ${p.description}`);
+    }
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'vector',
+    description: 'Vector store management for embeddings and similarity search',
+    subcommands: [
+      { name: 'add <content>', description: 'Add document to vector store' },
+      { name: 'search <query>', description: 'Search vector store' },
+      { name: 'stats', description: 'Show vector store statistics' },
+      { name: 'providers', description: 'List available vector store providers' },
+      { name: 'help', description: 'Show this help' }
+    ],
+    flags: [
+      { name: '--store', description: 'Vector store provider (memory, pinecone, etc.)' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Vector Command');
+    await pretty.plain(help.description);
+    await pretty.newline();
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(25)} ${cmd.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Flags:');
+    for (const flag of help.flags) {
+      await pretty.plain(`  ${flag.name.padEnd(20)} ${flag.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/version.ts

@@ -0,0 +1,40 @@
+/**
+ * Version command - Show CLI version
+ */
+
+import { CLI_SPEC_VERSION } from '../spec/cli-spec';
+import { outputJson, formatSuccess } from '../output/json';
+import * as pretty from '../output/pretty';
+
+export interface VersionOptions {
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+export async function execute(args: string[], options: VersionOptions): Promise<void> {
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+  
+  // Load package.json for version
+  let packageVersion = '0.0.0';
+  try {
+    const pkg = require('../../../package.json');
+    packageVersion = pkg.version;
+  } catch {
+    // Fallback if package.json not found
+  }
+
+  const versionInfo = {
+    version: packageVersion,
+    cli_spec: CLI_SPEC_VERSION,
+    runtime: 'node',
+    node_version: process.version
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(versionInfo));
+  } else {
+    await pretty.plain(`praisonai-ts v${packageVersion}`);
+    await pretty.dim(`CLI Spec: v${CLI_SPEC_VERSION}`);
+    await pretty.dim(`Node: ${process.version}`);
+  }
+}

src/praisonai-ts/src/cli/commands/voice.ts

@@ -0,0 +1,137 @@
+/**
+ * Voice command - Text-to-speech and speech-to-text
+ */
+
+import { outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES } from '../output/errors';
+
+export interface VoiceOptions {
+  verbose?: boolean;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+  provider?: string;
+}
+
+export async function execute(args: string[], options: VoiceOptions): Promise<void> {
+  const action = args[0] || 'help';
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    switch (action) {
+      case 'providers':
+        await listProviders(outputFormat);
+        break;
+      case 'info':
+        await showInfo(outputFormat);
+        break;
+      case 'help':
+      default:
+        await showHelp(outputFormat);
+        break;
+    }
+  } catch (error) {
+    if (outputFormat === 'json') {
+      outputJson(formatError(ERROR_CODES.UNKNOWN, error instanceof Error ? error.message : String(error)));
+    } else {
+      await pretty.error(error instanceof Error ? error.message : String(error));
+    }
+    process.exit(EXIT_CODES.RUNTIME_ERROR);
+  }
+}
+
+async function showInfo(outputFormat: string): Promise<void> {
+  const info = {
+    feature: 'Voice',
+    description: 'Text-to-speech and speech-to-text capabilities',
+    providers: [
+      { name: 'OpenAIVoiceProvider', description: 'OpenAI TTS and Whisper' },
+      { name: 'ElevenLabsVoiceProvider', description: 'ElevenLabs voice synthesis' }
+    ],
+    capabilities: [
+      'Text-to-speech conversion',
+      'Speech-to-text transcription',
+      'Multiple voice options',
+      'Streaming audio support'
+    ],
+    sdkUsage: `
+import { createOpenAIVoice, createElevenLabsVoice } from 'praisonai';
+
+// Create OpenAI voice provider
+const voice = createOpenAIVoice({ apiKey: process.env.OPENAI_API_KEY });
+
+// Text to speech
+const audio = await voice.speak({ text: 'Hello world', voice: 'alloy' });
+
+// Speech to text
+const text = await voice.listen({ audio: audioBuffer });
+`
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(info));
+  } else {
+    await pretty.heading('Voice');
+    await pretty.plain(info.description);
+    await pretty.newline();
+    await pretty.plain('Providers:');
+    for (const p of info.providers) {
+      await pretty.plain(`  • ${p.name}: ${p.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Capabilities:');
+    for (const cap of info.capabilities) {
+      await pretty.plain(`  • ${cap}`);
+    }
+  }
+}
+
+async function listProviders(outputFormat: string): Promise<void> {
+  const providers = [
+    { name: 'openai', description: 'OpenAI TTS and Whisper', available: true },
+    { name: 'elevenlabs', description: 'ElevenLabs voice synthesis', available: true }
+  ];
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess({ providers }));
+  } else {
+    await pretty.heading('Voice Providers');
+    for (const p of providers) {
+      const status = p.available ? '✓' : '✗';
+      await pretty.plain(`  ${status} ${p.name.padEnd(15)} ${p.description}`);
+    }
+  }
+}
+
+async function showHelp(outputFormat: string): Promise<void> {
+  const help = {
+    command: 'voice',
+    description: 'Text-to-speech and speech-to-text capabilities',
+    subcommands: [
+      { name: 'info', description: 'Show voice feature information' },
+      { name: 'providers', description: 'List available voice providers' },
+      { name: 'help', description: 'Show this help' }
+    ],
+    flags: [
+      { name: '--provider', description: 'Voice provider (openai, elevenlabs)' }
+    ]
+  };
+
+  if (outputFormat === 'json') {
+    outputJson(formatSuccess(help));
+  } else {
+    await pretty.heading('Voice Command');
+    await pretty.plain(help.description);
+    await pretty.newline();
+    await pretty.plain('Subcommands:');
+    for (const cmd of help.subcommands) {
+      await pretty.plain(`  ${cmd.name.padEnd(20)} ${cmd.description}`);
+    }
+    await pretty.newline();
+    await pretty.plain('Flags:');
+    for (const flag of help.flags) {
+      await pretty.plain(`  ${flag.name.padEnd(20)} ${flag.description}`);
+    }
+  }
+}

src/praisonai-ts/src/cli/commands/workflow.ts

@@ -0,0 +1,188 @@
+/**
+ * Workflow command - Execute a multi-agent workflow
+ */
+
+import * as fs from 'fs';
+import * as path from 'path';
+import { resolveConfig } from '../config/resolve';
+import { printSuccess, printError, outputJson, formatSuccess, formatError } from '../output/json';
+import * as pretty from '../output/pretty';
+import { EXIT_CODES } from '../spec/cli-spec';
+import { ERROR_CODES, normalizeError } from '../output/errors';
+
+export interface WorkflowOptions {
+  parallel?: boolean;
+  model?: string;
+  verbose?: boolean;
+  profile?: string;
+  config?: string;
+  output?: 'json' | 'text' | 'pretty';
+  json?: boolean;
+}
+
+interface WorkflowStep {
+  name: string;
+  agent?: string;
+  task?: string;
+  depends_on?: string[];
+}
+
+interface WorkflowDefinition {
+  name?: string;
+  description?: string;
+  agents?: Record<string, any>;
+  steps?: WorkflowStep[];
+}
+
+/**
+ * Simple YAML parser for workflow files
+ */
+function parseWorkflowYaml(content: string): WorkflowDefinition {
+  const result: WorkflowDefinition = {};
+  const lines = content.split('\n');
+  let currentSection: string | null = null;
+  let currentItem: any = null;
+  let currentKey: string | null = null;
+  
+  for (const line of lines) {
+    if (!line.trim() || line.trim().startsWith('#')) continue;
+    
+    const indent = line.search(/\S/);
+    const trimmed = line.trim();
+    
+    // Top-level keys
+    if (indent === 0 && trimmed.includes(':')) {
+      const colonIdx = trimmed.indexOf(':');
+      const key = trimmed.slice(0, colonIdx).trim();
+      const value = trimmed.slice(colonIdx + 1).trim();
+      
+      if (value) {
+        (result as any)[key] = value;
+      } else {
+        currentSection = key;
+        if (key === 'agents') result.agents = {};
+        if (key === 'steps') result.steps = [];
+      }
+    } else if (indent > 0 && currentSection) {
+      // Handle list items (steps)
+      if (trimmed.startsWith('- ')) {
+        if (currentSection === 'steps') {
+          currentItem = {};
+          result.steps!.push(currentItem);
+          
+          // Parse inline values after -
+          const afterDash = trimmed.slice(2).trim();
+          if (afterDash.includes(':')) {
+            const colonIdx = afterDash.indexOf(':');
+            const key = afterDash.slice(0, colonIdx).trim();
+            const value = afterDash.slice(colonIdx + 1).trim();
+            currentItem[key] = value;
+          }
+        }
+      } else if (trimmed.includes(':') && currentItem) {
+        const colonIdx = trimmed.indexOf(':');
+        const key = trimmed.slice(0, colonIdx).trim();
+        const value = trimmed.slice(colonIdx + 1).trim();
+        currentItem[key] = value || [];
+      }
+    }
+  }
+  
+  return result;
+}
+
+export async function execute(args: string[], options: WorkflowOptions): Promise<void> {
+  const workflowFile = args[0];
+  
+  if (!workflowFile) {
+    if (options.json || options.output === 'json') {
+      printError(ERROR_CODES.MISSING_ARG, 'Please provide a workflow file path');
+    } else {
+      await pretty.error('Please provide a workflow file path');
+    }
+    process.exit(EXIT_CODES.INVALID_ARGUMENTS);
+  }
+
+  // Resolve config
+  const config = resolveConfig({
+    configPath: options.config,
+    profile: options.profile,
+    model: options.model,
+    verbose: options.verbose
+  });
+
+  const startTime = Date.now();
+  const outputFormat = options.json ? 'json' : (options.output || 'pretty');
+
+  try {
+    // Read and parse workflow file
+    const filePath = path.resolve(workflowFile);
+    if (!fs.existsSync(filePath)) {
+      throw new Error(`Workflow file not found: ${filePath}`);
+    }
+
+    const content = fs.readFileSync(filePath, 'utf-8');
+    const workflow = parseWorkflowYaml(content);
+
+    if (outputFormat !== 'json') {
+      await pretty.heading(`Executing workflow: ${workflow.name || 'Unnamed'}`);
+      if (workflow.description) {
+        await pretty.info(workflow.description);
+      }
+    }
+
+    // Execute workflow steps
+    const results: Record<string, any> = {};
+    const steps = workflow.steps || [];
+
+    for (const step of steps) {
+      if (outputFormat !== 'json') {
+        await pretty.info(`Running step: ${step.name}`);
+      }
+
+      // For now, we'll simulate step execution
+      // In a full implementation, this would create agents and execute tasks
+      results[step.name] = {
+        status: 'completed',
+        output: `Step ${step.name} completed`
+      };
+    }
+
+    const duration = Date.now() - startTime;
+
+    if (outputFormat === 'json') {
+      outputJson(formatSuccess(
+        {
+          workflow: workflow.name || 'Unnamed',
+          steps: steps.length,
+          results
+        },
+        {
+          duration_ms: duration,
+          model: config.model
+        }
+      ));
+    } else {
+      await pretty.success(`Workflow completed in ${duration}ms`);
+      await pretty.newline();
+      await pretty.keyValue({
+        'Steps executed': steps.length,
+        'Duration': `${duration}ms`
+      });
+    }
+
+  } catch (error) {
+    const cliError = normalizeError(error);
+    
+    if (outputFormat === 'json') {
+      outputJson(formatError(cliError.code, cliError.message, cliError.details));
+    } else {
+      await pretty.error(cliError.message);
+      if (config.verbose && error instanceof Error && error.stack) {
+        await pretty.dim(error.stack);
+      }
+    }
+    
+    process.exit(cliError.exitCode);
+  }
+}

src/praisonai-ts/src/cli/config/index.ts

@@ -0,0 +1,7 @@
+/**
+ * Config utilities index
+ */
+
+export * from './schema';
+export * from './load';
+export * from './resolve';

src/praisonai-ts/src/cli/config/load.ts

@@ -0,0 +1,213 @@
+/**
+ * Config file loading
+ */
+
+import * as fs from 'fs';
+import * as path from 'path';
+import { CONFIG_FILES } from '../spec/cli-spec';
+import { FullConfig, validateConfig, DEFAULT_CONFIG } from './schema';
+
+export interface LoadConfigOptions {
+  configPath?: string;
+  cwd?: string;
+}
+
+/**
+ * Find config file in directory hierarchy
+ */
+function findConfigFile(startDir: string): string | null {
+  let currentDir = startDir;
+  
+  while (true) {
+    for (const filename of CONFIG_FILES) {
+      const filePath = path.join(currentDir, filename);
+      if (fs.existsSync(filePath)) {
+        return filePath;
+      }
+    }
+    
+    const parentDir = path.dirname(currentDir);
+    if (parentDir === currentDir) {
+      break; // Reached root
+    }
+    currentDir = parentDir;
+  }
+  
+  return null;
+}
+
+/**
+ * Find user config file
+ */
+function findUserConfigFile(): string | null {
+  const homeDir = process.env.HOME || process.env.USERPROFILE;
+  if (!homeDir) return null;
+  
+  for (const filename of CONFIG_FILES) {
+    const filePath = path.join(homeDir, filename);
+    if (fs.existsSync(filePath)) {
+      return filePath;
+    }
+  }
+  
+  return null;
+}
+
+/**
+ * Parse config file content
+ */
+function parseConfigFile(filePath: string): unknown {
+  const content = fs.readFileSync(filePath, 'utf-8');
+  const ext = path.extname(filePath).toLowerCase();
+  
+  if (ext === '.json') {
+    return JSON.parse(content);
+  }
+  
+  if (ext === '.yaml' || ext === '.yml') {
+    // Simple YAML parsing for basic config
+    // For complex YAML, we'd need a proper parser
+    return parseSimpleYaml(content);
+  }
+  
+  throw new Error(`Unsupported config file format: ${ext}`);
+}
+
+/**
+ * Simple YAML parser for basic key-value configs
+ * Handles: strings, booleans, numbers, simple objects
+ */
+function parseSimpleYaml(content: string): Record<string, unknown> {
+  const result: Record<string, unknown> = {};
+  const lines = content.split('\n');
+  let currentObject: Record<string, unknown> | null = null;
+  let currentKey: string | null = null;
+  let baseIndent = 0;
+  
+  for (const line of lines) {
+    // Skip empty lines and comments
+    if (!line.trim() || line.trim().startsWith('#')) {
+      continue;
+    }
+    
+    const indent = line.search(/\S/);
+    const trimmed = line.trim();
+    
+    // Check for key: value pattern
+    const colonIndex = trimmed.indexOf(':');
+    if (colonIndex === -1) continue;
+    
+    const key = trimmed.slice(0, colonIndex).trim();
+    const value = trimmed.slice(colonIndex + 1).trim();
+    
+    if (indent === 0) {
+      // Top-level key
+      if (value === '' || value === '{}') {
+        // Start of nested object
+        currentObject = {};
+        currentKey = key;
+        baseIndent = indent;
+        result[key] = currentObject;
+      } else {
+        result[key] = parseYamlValue(value);
+        currentObject = null;
+        currentKey = null;
+      }
+    } else if (currentObject !== null && indent > baseIndent) {
+      // Nested key
+      if (value === '' || value === '{}') {
+        // Nested object within nested object
+        const nestedObj: Record<string, unknown> = {};
+        currentObject[key] = nestedObj;
+        // For simplicity, we only support one level of nesting in profiles
+      } else {
+        currentObject[key] = parseYamlValue(value);
+      }
+    }
+  }
+  
+  return result;
+}
+
+function parseYamlValue(value: string): string | number | boolean {
+  // Remove quotes
+  if ((value.startsWith('"') && value.endsWith('"')) ||
+      (value.startsWith("'") && value.endsWith("'"))) {
+    return value.slice(1, -1);
+  }
+  
+  // Boolean
+  if (value === 'true') return true;
+  if (value === 'false') return false;
+  
+  // Number
+  const num = Number(value);
+  if (!isNaN(num) && value !== '') return num;
+  
+  return value;
+}
+
+/**
+ * Load config from file
+ */
+export function loadConfigFile(filePath: string): FullConfig {
+  try {
+    const parsed = parseConfigFile(filePath);
+    if (!validateConfig(parsed)) {
+      throw new Error('Invalid config format');
+    }
+    return parsed;
+  } catch (error) {
+    throw new Error(`Failed to load config from ${filePath}: ${error instanceof Error ? error.message : String(error)}`);
+  }
+}
+
+/**
+ * Load config with resolution order:
+ * 1. Explicit config path
+ * 2. Project config (current dir and parents)
+ * 3. User config (~/.praisonai.yaml)
+ * 4. Defaults
+ */
+export function loadConfig(options: LoadConfigOptions = {}): FullConfig {
+  const configs: Partial<FullConfig>[] = [DEFAULT_CONFIG];
+  
+  // User config
+  const userConfigPath = findUserConfigFile();
+  if (userConfigPath) {
+    try {
+      configs.push(loadConfigFile(userConfigPath));
+    } catch {
+      // Ignore user config errors
+    }
+  }
+  
+  // Project config
+  const cwd = options.cwd || process.cwd();
+  const projectConfigPath = findConfigFile(cwd);
+  if (projectConfigPath) {
+    try {
+      configs.push(loadConfigFile(projectConfigPath));
+    } catch {
+      // Ignore project config errors
+    }
+  }
+  
+  // Explicit config path
+  if (options.configPath) {
+    configs.push(loadConfigFile(options.configPath));
+  }
+  
+  // Merge all configs
+  const result: FullConfig = { ...DEFAULT_CONFIG };
+  for (const config of configs) {
+    if (config.model !== undefined) result.model = config.model;
+    if (config.verbose !== undefined) result.verbose = config.verbose;
+    if (config.stream !== undefined) result.stream = config.stream;
+    if (config.profiles !== undefined) {
+      result.profiles = { ...result.profiles, ...config.profiles };
+    }
+  }
+  
+  return result;
+}

src/praisonai-ts/src/cli/config/resolve.ts

@@ -0,0 +1,80 @@
+/**
+ * Config resolution with profiles and CLI overrides
+ */
+
+import { loadConfig } from './load';
+import { loadEnvConfig } from '../runtime/env';
+import { FullConfig, ProfileConfig, DEFAULT_CONFIG } from './schema';
+
+export interface ResolvedConfig {
+  model: string;
+  verbose: boolean;
+  stream: boolean;
+}
+
+export interface ResolveOptions {
+  configPath?: string;
+  profile?: string;
+  model?: string;
+  verbose?: boolean;
+  stream?: boolean;
+}
+
+/**
+ * Resolve final config with precedence:
+ * 1. CLI flags (highest)
+ * 2. Environment variables
+ * 3. Profile settings
+ * 4. Config file
+ * 5. Defaults (lowest)
+ */
+export function resolveConfig(options: ResolveOptions = {}): ResolvedConfig {
+  // Load base config from files
+  const fileConfig = loadConfig({ configPath: options.configPath });
+  
+  // Load env config
+  const envConfig = loadEnvConfig();
+  
+  // Get profile config if specified
+  let profileConfig: ProfileConfig = {};
+  const profileName = options.profile || envConfig.profile;
+  if (profileName && fileConfig.profiles?.[profileName]) {
+    profileConfig = fileConfig.profiles[profileName];
+  }
+  
+  // Resolve with precedence
+  const resolved: ResolvedConfig = {
+    model: DEFAULT_CONFIG.model!,
+    verbose: DEFAULT_CONFIG.verbose!,
+    stream: DEFAULT_CONFIG.stream!
+  };
+  
+  // Apply file config
+  if (fileConfig.model !== undefined) resolved.model = fileConfig.model;
+  if (fileConfig.verbose !== undefined) resolved.verbose = fileConfig.verbose;
+  if (fileConfig.stream !== undefined) resolved.stream = fileConfig.stream;
+  
+  // Apply profile config
+  if (profileConfig.model !== undefined) resolved.model = profileConfig.model;
+  if (profileConfig.verbose !== undefined) resolved.verbose = profileConfig.verbose;
+  if (profileConfig.stream !== undefined) resolved.stream = profileConfig.stream;
+  
+  // Apply env config
+  if (envConfig.model !== undefined) resolved.model = envConfig.model;
+  if (envConfig.verbose !== undefined) resolved.verbose = envConfig.verbose;
+  
+  // Apply CLI flags (highest precedence)
+  if (options.model !== undefined) resolved.model = options.model;
+  if (options.verbose !== undefined) resolved.verbose = options.verbose;
+  if (options.stream !== undefined) resolved.stream = options.stream;
+  
+  return resolved;
+}
+
+/**
+ * Get available profile names
+ */
+export function getAvailableProfiles(configPath?: string): string[] {
+  const config = loadConfig({ configPath });
+  return Object.keys(config.profiles || {});
+}

src/praisonai-ts/src/cli/config/schema.ts

@@ -0,0 +1,80 @@
+/**
+ * Config schema definitions
+ */
+
+import { ConfigSchema } from '../spec/cli-spec';
+
+export interface ProfileConfig {
+  model?: string;
+  verbose?: boolean;
+  stream?: boolean;
+}
+
+export interface FullConfig extends ConfigSchema {
+  profiles?: Record<string, ProfileConfig>;
+}
+
+export const DEFAULT_CONFIG: FullConfig = {
+  model: 'openai/gpt-4o-mini',
+  verbose: false,
+  stream: false,
+  profiles: {}
+};
+
+export function validateConfig(config: unknown): config is FullConfig {
+  if (typeof config !== 'object' || config === null) {
+    return false;
+  }
+
+  const c = config as Record<string, unknown>;
+
+  if (c.model !== undefined && typeof c.model !== 'string') {
+    return false;
+  }
+
+  if (c.verbose !== undefined && typeof c.verbose !== 'boolean') {
+    return false;
+  }
+
+  if (c.stream !== undefined && typeof c.stream !== 'boolean') {
+    return false;
+  }
+
+  if (c.profiles !== undefined) {
+    if (typeof c.profiles !== 'object' || c.profiles === null) {
+      return false;
+    }
+    for (const profile of Object.values(c.profiles as Record<string, unknown>)) {
+      if (typeof profile !== 'object' || profile === null) {
+        return false;
+      }
+      const p = profile as Record<string, unknown>;
+      if (p.model !== undefined && typeof p.model !== 'string') {
+        return false;
+      }
+      if (p.verbose !== undefined && typeof p.verbose !== 'boolean') {
+        return false;
+      }
+      if (p.stream !== undefined && typeof p.stream !== 'boolean') {
+        return false;
+      }
+    }
+  }
+
+  return true;
+}
+
+export function mergeConfigs(...configs: Partial<FullConfig>[]): FullConfig {
+  const result: FullConfig = { ...DEFAULT_CONFIG };
+
+  for (const config of configs) {
+    if (config.model !== undefined) result.model = config.model;
+    if (config.verbose !== undefined) result.verbose = config.verbose;
+    if (config.stream !== undefined) result.stream = config.stream;
+    if (config.profiles !== undefined) {
+      result.profiles = { ...result.profiles, ...config.profiles };
+    }
+  }
+
+  return result;
+}