Release v3.12.2

- Create docker/bots/ with own Dockerfile, docker-compose.yml, README
- Remove bot services from main docker-compose.yml
- Add .env.template with bot tokens
- Add README with setup instructions for Slack/Discord/Telegram

.github/workflows/update-parity-tracker.yml

@@ -1,58 +0,0 @@
-name: Update Feature Parity Tracker
-
-on:
-  push:
-    branches: [ "main" ]
-    paths:
-      - 'src/praisonai-agents/praisonaiagents/**/*.py'
-      - 'src/praisonai-ts/src/**/*.ts'
-      - 'src/praisonai-rust/src/**/*.rs'
-      - '.github/workflows/update-parity-tracker.yml'
-
-permissions:
-  contents: write
-
-jobs:
-  update-parity-tracker:
-    runs-on: ubuntu-latest
-    
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v4
-      with:
-        ref: main
-        persist-credentials: true
-        fetch-depth: 0
-
-    - name: Set up Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: '3.11'
-
-    - name: Generate parity trackers
-      run: |
-        cd $GITHUB_WORKSPACE
-        python3 src/praisonai/scripts/generate_parity_tracker.py
-        
-    - name: Check for changes
-      id: check_changes
-      run: |
-        if git diff --quiet src/praisonai-ts/FEATURE_PARITY_TRACKER.json src/praisonai-ts/PARITY.md src/praisonai-rust/FEATURE_PARITY_TRACKER.json src/praisonai-rust/PARITY.md 2>/dev/null; then
-          echo "changes=false" >> $GITHUB_OUTPUT
-          echo "No changes to parity trackers"
-        else
-          echo "changes=true" >> $GITHUB_OUTPUT
-          echo "Parity trackers have been updated"
-          git diff src/praisonai-ts/FEATURE_PARITY_TRACKER.json | head -50
-        fi
-
-    - name: Commit and push changes
-      if: steps.check_changes.outputs.changes == 'true'
-      uses: stefanzweifel/git-auto-commit-action@v5
-      with:
-        commit_message: "docs: auto-update feature parity trackers [skip ci]"
-        file_pattern: 'src/praisonai-ts/FEATURE_PARITY_TRACKER.json src/praisonai-ts/PARITY.md src/praisonai-rust/FEATURE_PARITY_TRACKER.json src/praisonai-rust/PARITY.md'
-        commit_user_name: "github-actions[bot]"
-        commit_user_email: "41898282+github-actions[bot]@users.noreply.github.com"
-        commit_author: "github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>"
-

.gitignore

@@ -84,11 +84,4 @@ issue_details.json
 .mcpregistry_*
 
 *.log
-.internal
-.praisonai
-
-# Rust / Cargo
-target/
-Cargo.lock
-**/*.rs.bk
-*.pdb
+.internal

api.md

@@ -58,7 +58,6 @@ Methods:
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">generate_task</a>() -> 'Task'</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">get_available_tools</a>() -> List[Any]</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">get_history_size</a>() -> int</code>
-* <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">get_learn_context</a>() -> str</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">get_memory_context</a>(query: Optional[str] = None) -> str</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">get_recommended_stage</a>(prompt: str) -> str</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">get_rules_context</a>(file_path: Optional[str] = None, include_manual: Optional[List[str]] = None) -> str</code>
@@ -82,8 +81,6 @@ Methods:
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">run</a>(prompt: str, **kwargs)</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">run_autonomous</a>(prompt: str, max_iterations: Optional[int] = None, timeout_seconds: Optional[float] = None, completion_promise: Optional[str] = None, clear_context: bool = False)</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">run_autonomous_async</a>(prompt: str, max_iterations: Optional[int] = None, timeout_seconds: Optional[float] = None, completion_promise: Optional[str] = None, clear_context: bool = False)</code>
-* <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">run_until</a>(prompt: str, criteria: str, threshold: float = 8.0, max_iterations: int = 5, mode: str = 'optimize', on_iteration: Optional[Callable[[Any], None]] = None, verbose: bool = False) -> 'EvaluationLoopResult'</code>
-* <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">run_until_async</a>(prompt: str, criteria: str, threshold: float = 8.0, max_iterations: int = 5, mode: str = 'optimize', on_iteration: Optional[Callable[[Any], None]] = None, verbose: bool = False) -> 'EvaluationLoopResult'</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">session_id</a>() -> Optional[str]</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">skill_manager</a>()</code>
 * <code title="class Agent">Agent.<a href="./src/praisonai-agents/praisonaiagents/agent/agent.py">start</a>(prompt: str = None, **kwargs)</code>
@@ -188,7 +185,6 @@ Methods:
 * <code title="class FunctionTool">FunctionTool.<a href="./src/praisonai-agents/praisonaiagents/tools/decorator.py">run</a>(**kwargs) -> Any</code>
 * <code title="class ToolRegistry">ToolRegistry.<a href="./src/praisonai-agents/praisonaiagents/tools/registry.py">clear</a>() -> None</code>
 * <code title="class ToolRegistry">ToolRegistry.<a href="./src/praisonai-agents/praisonaiagents/tools/registry.py">discover_plugins</a>() -> int</code>
-* <code title="class ToolRegistry">ToolRegistry.<a href="./src/praisonai-agents/praisonaiagents/tools/registry.py">discover_single_file_plugins</a>() -> int</code>
 * <code title="class ToolRegistry">ToolRegistry.<a href="./src/praisonai-agents/praisonaiagents/tools/registry.py">get</a>(name: str) -> Optional[Union[BaseTool, Callable]]</code>
 * <code title="class ToolRegistry">ToolRegistry.<a href="./src/praisonai-agents/praisonaiagents/tools/registry.py">get_all</a>() -> Dict[str, Union[BaseTool, Callable]]</code>
 * <code title="class ToolRegistry">ToolRegistry.<a href="./src/praisonai-agents/praisonaiagents/tools/registry.py">list_base_tools</a>() -> List[BaseTool]</code>
@@ -206,20 +202,28 @@ Methods:
 
 Types:
 ```python
-from praisonaiagents import Loop, Parallel, Pipeline, Repeat, Route, Task, Workflow, loop, parallel, repeat, route
+from praisonaiagents import Loop, Parallel, Pipeline, Repeat, Route, Workflow, loop, parallel, repeat, route
 ```
 
 Methods:
 
-* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">depends_on</a>()</code>
-* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">depends_on</a>(value)</code>
-* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">evaluate_when</a>(context: Dict[str, Any]) -> bool</code>
-* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">execute_callback</a>(task_output: TaskOutput) -> None</code>
-* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">execute_callback_sync</a>(task_output: TaskOutput) -> None</code>
-* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">get_next_task</a>(context: Dict[str, Any]) -> Optional[str]</code>
-* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">initialize_memory</a>()</code>
-* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">store_in_memory</a>(content: str, agent_name: str = None, task_id: str = None)</code>
-* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">to_dict</a>() -> Dict[str, Any]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">arun</a>(input: str = '', llm: Optional[str] = None, verbose: bool = False) -> Dict[str, Any]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">astart</a>(input: str = '', llm: Optional[str] = None, verbose: bool = False) -> Dict[str, Any]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">from_template</a>(uri: str, config: Optional[Dict[str, Any]] = None, offline: bool = False, **kwargs) -> 'Workflow'</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">memory_config</a>() -> Optional[Dict[str, Any]]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">on_step_complete</a>() -> Optional[Callable]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">on_step_error</a>() -> Optional[Callable]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">on_step_start</a>() -> Optional[Callable]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">on_workflow_complete</a>() -> Optional[Callable]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">on_workflow_start</a>() -> Optional[Callable]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">planning_llm</a>() -> Optional[str]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">reasoning</a>() -> bool</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">run</a>(input: str = '', llm: Optional[str] = None, verbose: bool = False, stream: bool = None) -> Dict[str, Any]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">start</a>(input: str = '', **kwargs) -> Dict[str, Any]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">stream</a>() -> bool</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">to_dict</a>() -> Dict[str, Any]</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">verbose</a>() -> bool</code>
+* <code title="class Workflow">Workflow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">verbose</a>(value: bool)</code>
 * <code title="function">praisonaiagents.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">loop</a>(step: Any = None, steps: Optional[List[Any]] = None, over: Optional[str] = None, from_csv: Optional[str] = None, from_file: Optional[str] = None, var_name: str = 'item', parallel: bool = False, max_workers: Optional[int] = None, output_variable: Optional[str] = None) -> Loop</code>
 * <code title="function">praisonaiagents.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">parallel</a>(steps: List) -> Parallel</code>
 * <code title="function">praisonaiagents.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">repeat</a>(step: Any, until: Optional[Callable[[WorkflowContext], bool]] = None, max_iterations: int = 10) -> Repeat</code>
@@ -576,7 +580,7 @@ Methods:
 
 Types:
 ```python
-from praisonaiagents import ContextManager
+from praisonaiagents import ContextManager, ManagerConfig
 ```
 
 Methods:
@@ -594,16 +598,20 @@ Methods:
 * <code title="class ContextManager">ContextManager.<a href="./src/praisonai-agents/praisonaiagents/context/manager.py">reset</a>() -> None</code>
 * <code title="class ContextManager">ContextManager.<a href="./src/praisonai-agents/praisonaiagents/context/manager.py">set_tool_budget</a>(tool_name: str, max_tokens: int, protected: bool = False) -> None</code>
 * <code title="class ContextManager">ContextManager.<a href="./src/praisonai-agents/praisonaiagents/context/manager.py">truncate_tool_output</a>(tool_name: str, output: str) -> str</code>
+* <code title="class ManagerConfig">ManagerConfig.<a href="./src/praisonai-agents/praisonaiagents/context/manager.py">from_env</a>() -> 'ManagerConfig'</code>
+* <code title="class ManagerConfig">ManagerConfig.<a href="./src/praisonai-agents/praisonaiagents/context/manager.py">merge</a>(**overrides) -> 'ManagerConfig'</code>
+* <code title="class ManagerConfig">ManagerConfig.<a href="./src/praisonai-agents/praisonaiagents/context/manager.py">to_dict</a>() -> Dict[str, Any]</code>
 
 # Config
 
 Types:
 ```python
-from praisonaiagents import AutonomyLevel, CachingConfig, ExecutionConfig, ExecutionPreset, GuardrailConfig, HooksConfig, KnowledgeConfig, MemoryConfig, MultiAgentExecutionConfig, MultiAgentHooksConfig, MultiAgentMemoryConfig, MultiAgentOutputConfig, MultiAgentPlanningConfig, OutputConfig, OutputPreset, PlanningConfig, ReflectionConfig, SkillsConfig, TemplateConfig, WebConfig, WebSearchProvider
+from praisonaiagents import AutonomyConfig, AutonomyLevel, CachingConfig, ExecutionConfig, ExecutionPreset, GuardrailConfig, HooksConfig, KnowledgeConfig, MemoryConfig, MultiAgentExecutionConfig, MultiAgentHooksConfig, MultiAgentMemoryConfig, MultiAgentOutputConfig, MultiAgentPlanningConfig, OutputConfig, OutputPreset, PlanningConfig, ReflectionConfig, SkillsConfig, TemplateConfig, WebConfig, WebSearchProvider
 ```
 
 Methods:
 
+* <code title="class AutonomyConfig">AutonomyConfig.<a href="./src/praisonai-agents/praisonaiagents/config/feature_configs.py">to_dict</a>() -> Dict[str, Any]</code>
 * <code title="class CachingConfig">CachingConfig.<a href="./src/praisonai-agents/praisonaiagents/config/feature_configs.py">to_dict</a>() -> Dict[str, Any]</code>
 * <code title="class ExecutionConfig">ExecutionConfig.<a href="./src/praisonai-agents/praisonaiagents/config/feature_configs.py">to_dict</a>() -> Dict[str, Any]</code>
 * <code title="class GuardrailConfig">GuardrailConfig.<a href="./src/praisonai-agents/praisonaiagents/config/feature_configs.py">to_dict</a>() -> Dict[str, Any]</code>
@@ -672,70 +680,54 @@ Methods:
 
 Types:
 ```python
-from praisonaiagents import AgentAppConfig, AgentAppProtocol, AgentFlow, AgentManager, AgentOSConfig, AgentOSProtocol, AgentTeam, EmbeddingResult, aembedding, aembeddings, embedding, embeddings, get_dimensions
+from praisonaiagents import AgentManager, EmbeddingResult, Task, aembedding, aembeddings, embedding, embeddings, get_dimensions
 ```
 
 Methods:
 
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">arun</a>(input: str = '', llm: Optional[str] = None, verbose: bool = False) -> Dict[str, Any]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">astart</a>(input: str = '', llm: Optional[str] = None, verbose: bool = False) -> Dict[str, Any]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">from_template</a>(uri: str, config: Optional[Dict[str, Any]] = None, offline: bool = False, **kwargs) -> 'Workflow'</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">get_history</a>() -> List[Dict[str, Any]]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">memory_config</a>() -> Optional[Dict[str, Any]]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">on_step_complete</a>() -> Optional[Callable]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">on_step_error</a>() -> Optional[Callable]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">on_step_start</a>() -> Optional[Callable]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">on_workflow_complete</a>() -> Optional[Callable]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">on_workflow_start</a>() -> Optional[Callable]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">planning_llm</a>() -> Optional[str]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">reasoning</a>() -> bool</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">run</a>(input: str = '', llm: Optional[str] = None, verbose: bool = False, stream: bool = None) -> Dict[str, Any]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">start</a>(input: str = '', **kwargs) -> Dict[str, Any]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">stream</a>() -> bool</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">to_dict</a>() -> Dict[str, Any]</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">verbose</a>() -> bool</code>
-* <code title="class AgentFlow">AgentFlow.<a href="./src/praisonai-agents/praisonaiagents/workflows/workflows.py">verbose</a>(value: bool)</code>
-* <code title="class AgentOSProtocol">AgentOSProtocol.<a href="./src/praisonai-agents/praisonaiagents/app/protocols.py">get_app</a>() -> Any</code>
-* <code title="class AgentOSProtocol">AgentOSProtocol.<a href="./src/praisonai-agents/praisonaiagents/app/protocols.py">serve</a>(host: Optional[str] = None, port: Optional[int] = None, reload: bool = False, **kwargs: Any) -> None</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">add_task</a>(task)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">aexecute_task</a>(task_id)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">append_to_state</a>(key: str, value: Any, max_length: Optional[int] = None) -> List[Any]</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">arun_all_tasks</a>()</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">arun_task</a>(task_id)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">astart</a>(content = None, return_dict = False, **kwargs)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">clean_json_output</a>(output: str) -> str</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">clear_state</a>() -> None</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">context_manager</a>()</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">current_plan</a>()</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">default_completion_checker</a>(task, agent_output)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">delete_state</a>(key: str) -> bool</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">display_token_usage</a>()</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">execute_task</a>(task_id)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_agent_details</a>(agent_name)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_all_state</a>() -> Dict[str, Any]</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_all_tasks_status</a>()</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_detailed_token_report</a>() -> Dict[str, Any]</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_plan_markdown</a>() -> str</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_state</a>(key: str, default: Any = None) -> Any</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_task_details</a>(task_id)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_task_result</a>(task_id)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_task_status</a>(task_id)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_todo_markdown</a>() -> str</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_token_usage_summary</a>() -> Dict[str, Any]</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">has_state</a>(key: str) -> bool</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">increment_state</a>(key: str, amount: float = 1, default: float = 0) -> float</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">launch</a>(path: str = '/agents', port: int = 8000, host: str = '0.0.0.0', debug: bool = False, protocol: str = 'http')</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">restore_session_state</a>(session_id: str) -> bool</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">run</a>(content = None, return_dict = False, **kwargs)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">run_all_tasks</a>()</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">run_task</a>(task_id)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">save_output_to_file</a>(task, task_output)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">save_session_state</a>(session_id: str, include_memory: bool = True) -> None</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">set_state</a>(key: str, value: Any) -> None</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">start</a>(content = None, return_dict = False, output = None, **kwargs)</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">todo_list</a>()</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">update_plan_step_status</a>(step_id: str, status: str) -> bool</code>
-* <code title="class AgentTeam">AgentTeam.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">update_state</a>(updates: Dict) -> None</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">add_task</a>(task)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">aexecute_task</a>(task_id)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">append_to_state</a>(key: str, value: Any, max_length: Optional[int] = None) -> List[Any]</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">arun_all_tasks</a>()</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">arun_task</a>(task_id)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">astart</a>(content = None, return_dict = False, **kwargs)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">clean_json_output</a>(output: str) -> str</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">clear_state</a>() -> None</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">context_manager</a>()</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">current_plan</a>()</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">default_completion_checker</a>(task, agent_output)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">delete_state</a>(key: str) -> bool</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">display_token_usage</a>()</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">execute_task</a>(task_id)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_agent_details</a>(agent_name)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_all_state</a>() -> Dict[str, Any]</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_all_tasks_status</a>()</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_detailed_token_report</a>() -> Dict[str, Any]</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_plan_markdown</a>() -> str</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_state</a>(key: str, default: Any = None) -> Any</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_task_details</a>(task_id)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_task_result</a>(task_id)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_task_status</a>(task_id)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_todo_markdown</a>() -> str</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">get_token_usage_summary</a>() -> Dict[str, Any]</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">has_state</a>(key: str) -> bool</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">increment_state</a>(key: str, amount: float = 1, default: float = 0) -> float</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">launch</a>(path: str = '/agents', port: int = 8000, host: str = '0.0.0.0', debug: bool = False, protocol: str = 'http')</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">restore_session_state</a>(session_id: str) -> bool</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">run</a>(content = None, return_dict = False, **kwargs)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">run_all_tasks</a>()</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">run_task</a>(task_id)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">save_output_to_file</a>(task, task_output)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">save_session_state</a>(session_id: str, include_memory: bool = True) -> None</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">set_state</a>(key: str, value: Any) -> None</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">start</a>(content = None, return_dict = False, output = None, **kwargs)</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">todo_list</a>()</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">update_plan_step_status</a>(step_id: str, status: str) -> bool</code>
+* <code title="class AgentManager">AgentManager.<a href="./src/praisonai-agents/praisonaiagents/agents/agents.py">update_state</a>(updates: Dict) -> None</code>
+* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">execute_callback</a>(task_output: TaskOutput) -> None</code>
+* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">execute_callback_sync</a>(task_output: TaskOutput) -> None</code>
+* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">initialize_memory</a>()</code>
+* <code title="class Task">Task.<a href="./src/praisonai-agents/praisonaiagents/task/task.py">store_in_memory</a>(content: str, agent_name: str = None, task_id: str = None)</code>
 * <code title="function">praisonaiagents.<a href="./src/praisonai-agents/praisonaiagents/embedding/embed.py">aembedding</a>(input: Union[str, List[str]], model: str = 'text-embedding-3-small', dimensions: Optional[int] = None, encoding_format: str = 'float', timeout: float = 600.0, api_key: Optional[str] = None, api_base: Optional[str] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs) -> EmbeddingResult</code>
 * <code title="function">praisonaiagents.<a href="./src/praisonai-agents/praisonaiagents/embedding/embed.py">aembeddings</a>(input: Union[str, List[str]], model: str = 'text-embedding-3-small', dimensions: Optional[int] = None, encoding_format: str = 'float', timeout: float = 600.0, api_key: Optional[str] = None, api_base: Optional[str] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs) -> EmbeddingResult</code>
 * <code title="function">praisonaiagents.<a href="./src/praisonai-agents/praisonaiagents/embedding/embed.py">embedding</a>(input: Union[str, List[str]], model: str = 'text-embedding-3-small', dimensions: Optional[int] = None, encoding_format: str = 'float', timeout: float = 600.0, api_key: Optional[str] = None, api_base: Optional[str] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs) -> EmbeddingResult</code>
@@ -746,7 +738,7 @@ Methods:
 
 Types:
 ```python
-from praisonai import AgentApp, AgentOS, CloudProvider, Deploy, DeployConfig, DeployType, PraisonAI, __version__
+from praisonai import AgentApp, CloudProvider, Deploy, DeployConfig, DeployType, PraisonAI, __version__
 ```
 
 # CLI
@@ -888,16 +880,12 @@ Methods:
 * <code title="cli">praisonai package install <a href="./src/praisonai/praisonai/cli/commands/package.py">--help</a></code>
 * <code title="cli">praisonai package list <a href="./src/praisonai/praisonai/cli/commands/package.py">--help</a></code>
 * <code title="cli">praisonai package uninstall <a href="./src/praisonai/praisonai/cli/commands/package.py">--help</a></code>
-* <code title="cli">praisonai plugins create <a href="./src/praisonai/praisonai/cli/commands/plugins.py">--help</a></code>
 * <code title="cli">praisonai plugins disable <a href="./src/praisonai/praisonai/cli/commands/plugins.py">--help</a></code>
-* <code title="cli">praisonai plugins discover <a href="./src/praisonai/praisonai/cli/commands/plugins.py">--help</a></code>
 * <code title="cli">praisonai plugins doctor <a href="./src/praisonai/praisonai/cli/commands/plugins.py">--help</a></code>
 * <code title="cli">praisonai plugins enable <a href="./src/praisonai/praisonai/cli/commands/plugins.py">--help</a></code>
 * <code title="cli">praisonai plugins info <a href="./src/praisonai/praisonai/cli/commands/plugins.py">--help</a></code>
-* <code title="cli">praisonai plugins install <a href="./src/praisonai/praisonai/cli/commands/plugins.py">--help</a></code>
 * <code title="cli">praisonai plugins list <a href="./src/praisonai/praisonai/cli/commands/plugins.py">--help</a></code>
 * <code title="cli">praisonai plugins plugins-callback <a href="./src/praisonai/praisonai/cli/commands/plugins.py">--help</a></code>
-* <code title="cli">praisonai plugins remove <a href="./src/praisonai/praisonai/cli/commands/plugins.py">--help</a></code>
 * <code title="cli">praisonai profile imports <a href="./src/praisonai/praisonai/cli/commands/profile.py">--help</a></code>
 * <code title="cli">praisonai profile optimize <a href="./src/praisonai/praisonai/cli/commands/profile.py">--help</a></code>
 * <code title="cli">praisonai profile profile-callback <a href="./src/praisonai/praisonai/cli/commands/profile.py">--help</a></code>
@@ -1005,7 +993,6 @@ Methods:
 * <code title="cli">praisonai traces list <a href="./src/praisonai/praisonai/cli/commands/traces.py">--help</a></code>
 * <code title="cli">praisonai traces status <a href="./src/praisonai/praisonai/cli/commands/traces.py">--help</a></code>
 * <code title="cli">praisonai train agents <a href="./src/praisonai/praisonai/cli/commands/train.py">--help</a></code>
-* <code title="cli">praisonai train apply <a href="./src/praisonai/praisonai/cli/commands/train.py">--help</a></code>
 * <code title="cli">praisonai train list <a href="./src/praisonai/praisonai/cli/commands/train.py">--help</a></code>
 * <code title="cli">praisonai train llm <a href="./src/praisonai/praisonai/cli/commands/train.py">--help</a></code>
 * <code title="cli">praisonai train show <a href="./src/praisonai/praisonai/cli/commands/train.py">--help</a></code>
@@ -1026,8 +1013,8 @@ Methods:
 
 Types/Exports:
 ```ts
-export { Agent, AgentTeam, Agents, PraisonAIAgents, Router } from "./agent";
-export type { AgentTeamConfig, PraisonAIAgentsConfig, SimpleAgentConfig, SimpleRouteConfig, SimpleRouterConfig } from "./agent";
+export { Agent, Agents, PraisonAIAgents, Router } from "./agent";
+export type { PraisonAIAgentsConfig, SimpleAgentConfig, SimpleRouteConfig, SimpleRouterConfig } from "./agent";
 export { AudioAgent, createAudioAgent } from "./agent/audio";
 export type { AudioAgentConfig, AudioProvider, AudioSpeakOptions, AudioSpeakResult, AudioTranscribeOptions, AudioTranscribeResult } from "./agent/audio";
 export { ContextAgent, createContextAgent } from "./agent/context";
@@ -1052,7 +1039,7 @@ export { // Agent loop
   ApprovalManager, // Tools
   defineTool, // UI Message (AI SDK v6 parity)
   convertToModelMessages, AIAgentStep, AIEmbedManyResult, AIEmbedOptions, AIEmbedResult, AIFilePart, AIGenerateImageOptions, AIGenerateImageResult, AIGenerateObjectOptions, AIGenerateObjectResult, AIGenerateTextOptions, AIGenerateTextResult, AIImagePart, AIMiddleware, AIMiddlewareConfig, AIModelMessage, AISpan, AISpanKind, AISpanOptions, AISpanStatus, AIStreamObjectOptions, AIStreamObjectResult, AIStreamTextOptions, AIStreamTextResult, AITelemetryEvent, AITelemetrySettings, AITextPart, AIToolDefinition, AITracer, AgentLoop, DANGEROUS_PATTERNS, MCPClientType, MODEL_ALIASES, SPEECH_MODELS, TRANSCRIPTION_MODELS, ToolApprovalDeniedError, ToolApprovalTimeoutError, aiEmbed, aiEmbedMany, aiGenerateImage, aiGenerateObject, aiGenerateText, aiStreamObject, aiStreamText, applyMiddleware, autoEnableDevTools, base64ToUint8Array, clearAICache, clearEvents, closeAllMCPClients, closeMCPClient, convertToUIMessages, createAILoggingMiddleware, createAISpan, createApprovalResponse, createDangerousPatternChecker, createDevToolsMiddleware, createExpressHandler, createFastifyHandler, createFilePart, createHonoHandler, createMultimodalMessage, createNestHandler, createPagesHandler, createPdfPart, createSystemMessage, createTelemetryMiddleware, createTelemetrySettings, createTextMessage, createTextPart, createToolSet, disableAITelemetry, disableDevTools, enableAITelemetry, functionToTool, getAICacheStats, getApprovalManager, getDevToolsState, getDevToolsUrl, getEvents, getMCPClient, getModel, getTelemetrySettings, getToolsNeedingApproval, getTracer, hasModelAlias, hasPendingApprovals, initOpenTelemetry, isDangerous, isDataUrl, isDevToolsEnabled, isTelemetryEnabled, isUrl, listModelAliases, mcpToolsToAITools, parseModel, pipeUIMessageStreamToResponse, recordEvent, resolveModelAlias, safeValidateUIMessages, setApprovalManager, stopAfterSteps, stopWhen, stopWhenNoToolCalls, toMessageContent, toUIMessageStreamResponse, transcribe, uint8ArrayToBase64, validateUIMessages, withApproval, withSpan, wrapModel } from "./ai";
-export { AutoAgents, AutoTaskConfig, createAutoAgents } from "./auto";
+export { AutoAgents, createAutoAgents } from "./auto";
 export { BaseCache, FileCache, MemoryCache, createFileCache, createMemoryCache } from "./cache";
 export { CLI_SPEC_VERSION, executeCommand, parseArgs } from "./cli";
 export { // Autonomy Mode
@@ -1110,8 +1097,6 @@ export { // Adapters
   OBSERVABILITY_TOOLS, // Global adapter management
   setObservabilityAdapter, // Types
   type SpanKind, ConsoleObservabilityAdapter, MemoryObservabilityAdapter, clearAdapterCache, createConsoleAdapter, createMemoryAdapter, createObservabilityAdapter, getObservabilityAdapter, getObservabilityToolInfo, hasObservabilityToolEnvVar, listObservabilityTools, noopAdapter, resetObservabilityAdapter, trace } from "./observability";
-export { AgentApp, AgentAppConfig, AgentAppProtocol, AgentOS, AgentOSConfig, AgentOSProtocol, DEFAULT_AGENTOS_CONFIG, mergeConfig } from "./os";
-export type { AgentAppOptions, AgentOSOptions } from "./os";
 export { Plan, PlanStep, PlanStorage, PlanningAgent, TaskAgent, TodoItem, TodoList, createPlan, createPlanStorage, createPlanningAgent, createTaskAgent, createTodoList } from "./planning";
 export { SkillManager, createSkillManager, parseSkillFile } from "./skills";
 export { AgentTelemetry, PerformanceMonitor, TelemetryCollector, TelemetryIntegration, cleanupTelemetry, createAgentTelemetry, createConsoleSink, createHTTPSink, createPerformanceMonitor, createTelemetryIntegration, disableTelemetry, enableTelemetry, getTelemetry } from "./telemetry";
@@ -1122,9 +1107,9 @@ export { MissingDependencyError, MissingEnvVarError, ToolsRegistry, composeMiddl
 export type { InstallHints, PraisonTool, RedactionHooks, RegisteredTool, ToolCapabilities, ToolExecutionContext, ToolExecutionResult, ToolFactory, ToolHooks, ToolInstallStatus, ToolLimits, ToolLogger, ToolMetadata, ToolMiddleware, ToolParameterProperty, ToolParameterSchema } from "./tools/registry";
 export { registerBuiltinTools, tools } from "./tools/tools";
 export { // New: Python-parity Loop and Repeat classes
-  Loop, // Task class
-  Task, AgentFlow, Pipeline, Repeat, Workflow, loop, loopPattern, parallel, repeat, repeatPattern, route } from "./workflows";
-export type { LoopConfig, LoopResult, RepeatConfig, RepeatContext, RepeatResult, StepContextConfig, StepExecutionConfig, StepOutputConfig, StepResult, StepRoutingConfig, TaskConfig, WorkflowContext } from "./workflows";
+  Loop, // WorkflowStep class
+  WorkflowStep, Repeat, Workflow, loop, loopPattern, parallel, repeat, repeatPattern, route } from "./workflows";
+export type { LoopConfig, LoopResult, RepeatConfig, RepeatContext, RepeatResult, StepContextConfig, StepExecutionConfig, StepOutputConfig, StepResult, StepRoutingConfig, WorkflowContext, WorkflowStepConfig } from "./workflows";
 export { createWorkflowFromYAML, loadWorkflowFromFile, parseYAMLWorkflow, validateWorkflowDefinition } from "./workflows/yaml-parser";
 ```
 

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>=4.4.4" \
+    "praisonai>=3.12.2" \
     "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>=4.4.4" \
+    "praisonai>=3.12.2" \
     "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>=4.4.4" \
+    "praisonai>=3.12.2" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

examples/consolidated_params/advanced_workflow_full_features.py

@@ -1,30 +1,30 @@
 """Advanced Workflow with all consolidated params configured."""
 from praisonaiagents import Agent
-from praisonaiagents import AgentFlow, Task
+from praisonaiagents.workflows import Workflow, WorkflowStep
 from praisonaiagents.workflows.workflow_configs import (
     WorkflowOutputConfig, WorkflowPlanningConfig, WorkflowMemoryConfig,
 )
 
 # Full-featured workflow with all consolidated params
-workflow = AgentFlow(
+workflow = Workflow(
     name="FullFeaturedWorkflow",
     description="Demonstrates all agent-like consolidated params",
     steps=[
-        Task(
+        WorkflowStep(
             name="researcher",
             action="Research: {{input}}",
             agent=Agent(instructions="You are a researcher."),
             knowledge=["research_docs/"],  # Step-specific knowledge
             web="duckduckgo",  # Use DuckDuckGo for this step
         ),
-        Task(
+        WorkflowStep(
             name="analyzer",
             action="Analyze the research",
             agent=Agent(instructions="You are an analyst."),
             reflection="thorough",  # Thorough reflection for analysis
             guardrails="strict",  # Strict validation
         ),
-        Task(
+        WorkflowStep(
             name="writer",
             action="Write the final report",
             agent=Agent(instructions="You are a writer."),

examples/consolidated_params/basic_agents.py

@@ -1,12 +1,12 @@
 """Basic Agents (multi-agent) example with consolidated params."""
-from praisonaiagents import Agent, AgentTeam
+from praisonaiagents import Agent, Agents
 
 # Create agents
 writer = Agent(instructions="You write content.")
 editor = Agent(instructions="You edit content.")
 
 # Multi-agent with consolidated params
-agents = AgentTeam(
+agents = Agents(
     agents=[writer, editor],
     memory=True,
     planning=True,

examples/consolidated_params/basic_step_override.py

@@ -1,18 +1,18 @@
 """Basic example showing step-level override of workflow defaults."""
 from praisonaiagents import Agent
-from praisonaiagents import AgentFlow, Task
+from praisonaiagents.workflows import Workflow, WorkflowStep
 
 # Workflow with defaults
-workflow = AgentFlow(
+workflow = Workflow(
     name="StepOverrideWorkflow",
     steps=[
-        Task(
+        WorkflowStep(
             name="step1",
             action="Process with workflow defaults",
             agent=Agent(instructions="You are a processor."),
             # Uses workflow-level web=True (inherited)
         ),
-        Task(
+        WorkflowStep(
             name="step2",
             action="Process with step override",
             agent=Agent(instructions="You are a processor."),

examples/consolidated_params/basic_workflow.py

@@ -1,17 +1,17 @@
 """Basic workflow example with consolidated params."""
 from praisonaiagents import Agent
-from praisonaiagents import AgentFlow, Task
+from praisonaiagents.workflows import Workflow, WorkflowStep
 
 # Create agents
 writer = Agent(instructions="You are a content writer.")
 editor = Agent(instructions="You are an editor.")
 
 # Create workflow with consolidated params
-workflow = AgentFlow(
+workflow = Workflow(
     name="Content Pipeline",
     steps=[
-        Task(name="write", agent=writer, action="Write about {{topic}}"),
-        Task(name="edit", agent=editor, action="Edit the content", context=["write"]),
+        WorkflowStep(name="write", agent=writer, action="Write about {{topic}}"),
+        WorkflowStep(name="edit", agent=editor, action="Edit the content", context=["write"]),
     ],
     output="verbose",
     planning=True,

examples/consolidated_params/basic_workflow_agentlike.py

@@ -1,17 +1,17 @@
 """Basic Workflow with Agent-like consolidated params."""
 from praisonaiagents import Agent
-from praisonaiagents import AgentFlow, Task
+from praisonaiagents.workflows import Workflow, WorkflowStep
 
 # Workflow with agent-like params (knowledge, web, guardrails, reflection)
-workflow = AgentFlow(
+workflow = Workflow(
     name="AgentLikeWorkflow",
     steps=[
-        Task(
+        WorkflowStep(
             name="researcher",
             action="Research the topic: {{input}}",
             agent=Agent(instructions="You are a researcher."),
         ),
-        Task(
+        WorkflowStep(
             name="writer",
             action="Write about the research findings",
             agent=Agent(instructions="You are a writer."),

examples/context/09_context_budgeting.py

@@ -189,8 +189,8 @@ def main():
     print("-" * 40)
     print("Auto-agents mode default: context=False (zero overhead)")
     print("To enable for multi-agent workflows:")
-    print("    from praisonaiagents import AgentTeam")
-    print("    agents = AgentTeam(agents=[...], context=True)")
+    print("    from praisonaiagents import Agents")
+    print("    agents = Agents(agents=[...], context=True)")
     print("")
     print("Recommended config for long tasks:")
     print("    context=ManagerConfig(")

examples/context/12_multi_agent_context.py

@@ -6,10 +6,10 @@ Demonstrates how to use multi-agent context with Agents via context= param,
 and also shows low-level MultiAgentLedger usage for advanced scenarios.
 
 Agent-Centric Quick Start:
-    from praisonaiagents import Agent, AgentTeam
+    from praisonaiagents import Agent, Agents
     from praisonaiagents.context import ManagerConfig
     
-    agents = AgentTeam(
+    agents = Agents(
         agents=[agent1, agent2],
         context=ManagerConfig(policy="isolated"),  # or "shared"
     )
@@ -17,7 +17,7 @@ Agent-Centric Quick Start:
 
 import os
 import tempfile
-from praisonaiagents import Agent, AgentTeam
+from praisonaiagents import Agent, Agents
 from praisonaiagents.context import (
     ManagerConfig,
     MultiAgentLedger,
@@ -49,7 +49,7 @@ def agent_centric_example():
     # Multi-agent setup with isolated context policy
     # (each agent maintains its own context)
     print("Created agents with context=True")
-    print("Use AgentTeam(agents=[...], context=ManagerConfig(policy='isolated'))")
+    print("Use Agents(agents=[...], context=ManagerConfig(policy='isolated'))")
     print("for multi-agent context isolation")
 
 

examples/context/14_agent_context_param.py

@@ -156,7 +156,7 @@ def example_5_multi_agent():
     print("Example 5: Multi-Agent Context Management")
     print("=" * 60)
     
-    from praisonaiagents import AgentTeam, Task
+    from praisonaiagents import Agents, Task
     
     config = ManagerConfig(
         auto_compact=True,
@@ -181,7 +181,7 @@ def example_5_multi_agent():
     task2 = Task(description="Write a summary", agent=writer)
     
     # Create multi-agent system with context management
-    agents = AgentTeam(
+    agents = Agents(
         agents=[researcher, writer],
         tasks=[task1, task2],
         context=config,  # Shared context config

examples/guardrail_example_fixed.py

@@ -4,7 +4,7 @@ Fixed example demonstrating proper guardrail usage with PraisonAI Agents.
 This addresses the issues reported in issue #875.
 """
 
-from praisonaiagents import Agent, Task, GuardrailResult, AgentTeam, TaskOutput
+from praisonaiagents import Agent, Task, GuardrailResult, Agents, TaskOutput
 from typing import Tuple, Any
 import trafilatura
 
@@ -103,7 +103,7 @@ task_with_llm_guardrail = Task(
 
 # Run with GuardrailResult example
 print("=== Running with GuardrailResult guardrail ===")
-agents_gr = AgentTeam(
+agents_gr = Agents(
     agents=[agent],
     tasks=[task_with_guardrailresult]
 )
@@ -113,7 +113,7 @@ agents_gr = AgentTeam(
 
 # Run with Tuple example
 print("\n=== Running with Tuple[bool, Any] guardrail ===")
-agents_tuple = AgentTeam(
+agents_tuple = Agents(
     agents=[agent],
     tasks=[task_with_tuple]
 )
@@ -123,7 +123,7 @@ agents_tuple = AgentTeam(
 
 # Run with LLM guardrail example
 print("\n=== Running with LLM-based guardrail ===")
-agents_llm = AgentTeam(
+agents_llm = Agents(
     agents=[agent],
     tasks=[task_with_llm_guardrail]
 )

examples/observability/multi_agent_tracing.py

@@ -14,7 +14,7 @@ Usage:
 
 from praisonai_tools.observability import obs
 from praisonai_tools.observability.base import SpanKind
-from praisonaiagents import Agent, AgentTeam
+from praisonaiagents import Agent, Agents
 
 # Initialize observability
 obs.init()

examples/output_ux/basic_output_example.py

@@ -13,7 +13,7 @@ Features demonstrated:
 
 import sys
 sys.path.insert(0, '/Users/praison/praisonai-package/src/praisonai-agents')
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 
 def get_weather(city: str) -> str:
@@ -106,7 +106,7 @@ def example_multi_agent():
         agent=writer
     )
     
-    agents = AgentTeam(
+    agents = Agents(
         agents=[researcher, writer],
         tasks=[task1, task2],
         process="sequential",

examples/python/agents/autoagents-hierarchical-generation.py

@@ -5,7 +5,7 @@ This example demonstrates hierarchical agent patterns using PraisonAI
 for structured task delegation and coordinated workflows.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import internet_search
 
 print("=== AutoAgents Hierarchical Generation Example ===\n")
@@ -54,7 +54,7 @@ execution_task = Task(
 )
 
 # Run hierarchical workflow
-agents_system = AgentTeam(
+agents_system = Agents(
     agents=[manager_agent, research_agent],
     tasks=[planning_task, execution_task],
     process="sequential", output="verbose"

examples/python/agents/code-agent.py

@@ -5,7 +5,7 @@ This example demonstrates a comprehensive code agent that can write, analyze, de
 It includes self-reflection for improving code quality and multiple specialized tools.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import CodeInterpreter
 
 # Initialize code execution tool
@@ -84,7 +84,7 @@ def demonstrate_code_agent():
     )
     
     # Create workflow
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[code_writer, code_reviewer, code_executor],
         tasks=[write_task, review_task, execute_task],
         process="sequential", output="verbose"

examples/python/agents/image-agent.py

@@ -4,7 +4,7 @@ from praisonaiagents.tools import duckduckgo
 agent = Agent(instructions="You are a Image Analysis Agent", tools=[duckduckgo])
 agent.start("I want to go London next week, find me a good hotel and flight")
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 # Create Image Analysis Agent
 image_agent = Agent(
@@ -36,7 +36,7 @@ task2 = Task(
 )
 
 # Create Agents instance
-agents = AgentTeam(
+agents = Agents(
     agents=[image_agent],
     tasks=[task1, task2],
     process="sequential",

examples/python/agents/image-to-text-agent.py

@@ -4,7 +4,7 @@ from praisonaiagents.tools import duckduckgo
 agent = Agent(instructions="You are a Image Analysis Agent", tools=[duckduckgo])
 agent.start("I want to go London next week, find me a good hotel and flight")
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 # Create Image Analysis Agent
 image_agent = Agent(
@@ -36,7 +36,7 @@ task2 = Task(
 )
 
 # Create Agents instance
-agents = AgentTeam(
+agents = Agents(
     agents=[image_agent],
     tasks=[task1, task2],
     process="sequential",

examples/python/agents/math-agent.py

@@ -5,7 +5,7 @@ This example demonstrates a mathematical problem-solving agent that can handle v
 including calculations, equation solving, and step-by-step explanations.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from typing import Dict, Any
 import math
 import re
@@ -123,7 +123,7 @@ def solve_math_problem_workflow():
         context=[solve_task]
     )
     
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[problem_solver_agent, calculation_agent, math_tutor_agent],
         tasks=[understand_task, solve_task, verify_task],
         process="sequential", output="verbose"

examples/python/agents/multi-provider-agent.py

@@ -6,7 +6,7 @@ agent-based selection for cost optimization and performance.
 """
 
 import os
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.agent import RouterAgent
 from praisonaiagents.llm.model_router import ModelRouter, ModelProfile, TaskComplexity
 
@@ -48,7 +48,7 @@ def example_auto_routing():
     )
     
     # Run the tasks
-    agents = AgentTeam(
+    agents = Agents(
         agents=[research_agent],
         tasks=[simple_task, moderate_task, complex_task],
         process="sequential", output="verbose"
@@ -113,7 +113,7 @@ def example_cost_optimized_workflow():
     )
     
     # Run workflow
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[analyzer, writer],
         tasks=[analysis_task, writing_task],
         process="sequential", output="verbose"
@@ -135,7 +135,7 @@ def example_auto_agents_multi_provider():
     from praisonaiagents.agents import AutoAgents
     
     # Create AutoAgents that will automatically assign appropriate models
-    auto_agents = AutoAgentTeam(
+    auto_agents = AutoAgents(
         instructions="Create a market research report on electric vehicles. Include data analysis, competitor analysis, and future projections.",
         max_agents=3,
         llm="gpt-4o-mini",  # Default model for agent generation
@@ -239,7 +239,7 @@ def example_custom_routing():
     ]
     
     # Run tasks
-    agents = AgentTeam(
+    agents = Agents(
         agents=[coder],
         tasks=tasks,
         process="sequential", output="verbose"

examples/python/agents/video-agent.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 # Create Video Analysis Agent
 video_agent = Agent(
@@ -25,7 +25,7 @@ task1 = Task(
 )
 
 # Create Agents instance
-agents = AgentTeam(
+agents = Agents(
     agents=[video_agent],
     tasks=[task1],
     process="sequential",

examples/python/agents/wikipedia-agent.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import wiki_search, wiki_summary, wiki_page, wiki_random, wiki_language
 
 agent = Agent(

examples/python/api/multi-agents-api.py

@@ -1,6 +1,6 @@
-from praisonaiagents import Agent, AgentTeam, Tools
+from praisonaiagents import Agent, Agents, Tools
 
 research_agent = Agent(name="Research", instructions="You are a research agent to search internet about AI 2024", tools=[Tools.internet_search])
 summarise_agent = Agent(name="Summarise", instructions="You are a summarize agent to summarise in points")
-agents = AgentTeam(agents=[research_agent, summarise_agent])
+agents = Agents(agents=[research_agent, summarise_agent])
 agents.launch(path="/agents", port=3030)

examples/python/api/multi-agents-group-api.py

@@ -1,8 +1,8 @@
-from praisonaiagents import Agent, AgentTeam, Tools
+from praisonaiagents import Agent, Agents, Tools
 
 research_agent = Agent(name="Research", instructions="You are a research agent to search internet about AI 2024", tools=[Tools.internet_search])
 summarise_agent = Agent(name="Summarise", instructions="You are a summarize agent to summarise in points")
-agents = AgentTeam(agents=[research_agent, summarise_agent])
-agents2 = AgentTeam(agents=[research_agent])
+agents = Agents(agents=[research_agent, summarise_agent])
+agents2 = Agents(agents=[research_agent])
 agents.launch(path="/agents", port=3030)
 agents2.launch(path="/agents2", port=3030)

examples/python/api/secondary-market-research-api.py

@@ -32,7 +32,7 @@ import os
 from pathlib import Path
 
 # Import our market research system
-from praisonaiagents import Agent, Task, AgentTeam, Tools
+from praisonaiagents import Agent, Task, Agents, Tools
 
 # Create FastAPI app
 app = FastAPI(
@@ -260,7 +260,7 @@ async def generate_market_research_report(job_id: str, config: MarketResearchCon
         job_status[job_id]["message"] = "Setting up research workflow..."
         
         # Create workflow
-        workflow = AgentTeam(
+        workflow = Agents(
             agents=list(agents.values()),
             tasks=tasks,
             process="sequential", output="minimal"

examples/python/api/simple-mcp-multi-agents-server.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, AgentTeam
+from praisonaiagents import Agent, Agents
 from duckduckgo_search import DDGS
 
 def internet_search_tool(query: str):
@@ -15,5 +15,5 @@ def internet_search_tool(query: str):
 agent = Agent(name="SearchAgent", instructions="You Search the internet for information", tools=[internet_search_tool])
 agent2 = Agent(name="SummariseAgent", instructions="You Summarise the information")
 
-agents = AgentTeam(name="MultiAgents", agents=[agent, agent2])
+agents = Agents(name="MultiAgents", agents=[agent, agent2])
 agents.launch(port=8080, protocol="mcp")

examples/python/camera/camera-basic.py

@@ -16,7 +16,7 @@ Environment Variables:
 
 import cv2
 import os
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 
 def capture_and_analyze():
@@ -58,7 +58,7 @@ def capture_and_analyze():
             )
             
             # Run analysis
-            agents = AgentTeam(
+            agents = Agents(
                 agents=[vision_agent],
                 tasks=[task],
                 process="sequential",

examples/python/camera/camera-continuous.py

@@ -18,7 +18,7 @@ import cv2
 import time
 import os
 from datetime import datetime
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 
 class ContinuousCameraMonitor:
@@ -71,7 +71,7 @@ class ContinuousCameraMonitor:
             images=[image_path]
         )
         
-        agents = AgentTeam(
+        agents = Agents(
             agents=[self.vision_agent],
             tasks=[task],
             process="sequential",

examples/python/camera/camera-multi-agent.py

@@ -17,7 +17,7 @@ Environment Variables:
 import cv2
 import os
 from datetime import datetime
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 
 def capture_camera_frame(camera_id=0):
@@ -114,7 +114,7 @@ def analyze_with_multiple_agents():
     )
     
     # Run multi-agent analysis
-    agents = AgentTeam(
+    agents = Agents(
         agents=[security_agent, object_detector, scene_analyst],
         tasks=[security_task, object_task, scene_task],
         process="parallel",  # Run all analyses in parallel

examples/python/camera/camera-video-analysis.py

@@ -18,7 +18,7 @@ import cv2
 import os
 import time
 from datetime import datetime
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 
 class CameraVideoAnalyzer:
@@ -131,7 +131,7 @@ class CameraVideoAnalyzer:
             images=[video_path]  # PraisonAI supports video files in images parameter
         )
         
-        agents = AgentTeam(
+        agents = Agents(
             agents=[self.video_agent],
             tasks=[task],
             process="sequential",

examples/python/concepts/context-engineering-workflow.py

@@ -24,7 +24,7 @@ from pathlib import Path
 project_root = Path(__file__).parent.parent.parent.parent / "src" / "praisonai-agents"
 sys.path.insert(0, str(project_root))
 
-from praisonaiagents import Agent, Task, AgentTeam, create_context_agent
+from praisonaiagents import Agent, Task, Agents, create_context_agent
 
 class ContextEngineeringWorkflow:
     """
@@ -302,7 +302,7 @@ class ContextEngineeringWorkflow:
         print("\n⚙️ Executing Context Engineering Workflow")
         print("-" * 50)
         
-        agents_workflow = AgentTeam(
+        agents_workflow = Agents(
             agents=[
                 self.product_manager,
                 self.architect, 

examples/python/concepts/csv-processing-agents.py

@@ -11,7 +11,7 @@ Author: Generated for GitHub Issue #23
 """
 
 import os
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import read_csv, write_csv
 
 def create_sample_urls_csv():
@@ -81,7 +81,7 @@ def method_1_simple_loop():
     )
     
     # Initialize the agents system
-    agents = AgentTeam(
+    agents = Agents(
         agents=[loop_agent],
         tasks=[loop_task],
         process="workflow",
@@ -145,7 +145,7 @@ def method_2_manual_csv():
     )
     
     # Initialize and run
-    agents = AgentTeam(
+    agents = Agents(
         agents=[csv_agent],
         tasks=[csv_task],
         process="sequential"
@@ -211,7 +211,7 @@ def method_3_url_processing():
     )
     
     # Initialize and run
-    agents = AgentTeam(
+    agents = Agents(
         agents=[url_agent],
         tasks=[url_task],
         process="sequential"
@@ -319,7 +319,7 @@ def method_4_advanced_processing():
     )
     
     # Initialize and run with sequential processing
-    agents = AgentTeam(
+    agents = Agents(
         agents=[validator_agent, processor_agent],
         tasks=[validation_task, processing_task],
         process="sequential"  # Validation must complete before processing

examples/python/concepts/knowledge-agents-task.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 import logging
 import os
 
@@ -35,7 +35,7 @@ knowledge_task = Task(
 )
 
 # Create and start the agents
-agents = AgentTeam(
+agents = Agents(
     agents=[knowledge_agent],
     tasks=[knowledge_task],
     process="sequential",

examples/python/concepts/rag-agents.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 # Define the configuration for the Knowledge instance
 config = {
@@ -29,7 +29,7 @@ rag_task = Task(
 )
 
 # Build Agents
-agents = AgentTeam(
+agents = Agents(
     agents=[rag_agent],
     tasks=[rag_task],
     user_id="user1"

examples/python/concepts/reasoning-extraction.py

@@ -8,7 +8,7 @@ This example demonstrates how to extract and utilize reasoning patterns in Prais
 - Decision rationale extraction
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from typing import Dict, List, Tuple
 from pydantic import BaseModel
 import json
@@ -100,7 +100,7 @@ def demonstrate_reasoning_extraction():
         context=[problem_task]
     )
     
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[cot_agent, reasoning_extractor],
         tasks=[problem_task, extract_task],
         process="sequential", output="verbose"
@@ -183,7 +183,7 @@ def advanced_reasoning_patterns():
         context=[deductive_task, inductive_task, abductive_task]
     )
     
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[cot_agent, reasoning_validator],
         tasks=[deductive_task, inductive_task, abductive_task, validation_task],
         process="sequential", output="verbose"

examples/python/concepts/repetitive-agents.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 agent = Agent(
     instructions="You are a loop agent that creating a loop of tasks.",
@@ -12,7 +12,7 @@ task = Task(
     input_file="tasks.csv"
 )
 
-agents = AgentTeam(
+agents = Agents(
     agents=[agent],
     tasks=[task],
     process="workflow",

examples/python/concepts/routing-patterns.py

@@ -8,7 +8,7 @@ This example demonstrates various routing patterns in PraisonAI including:
 - Dynamic task selection
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from typing import Dict, Any
 import random
 
@@ -77,7 +77,7 @@ def conditional_routing_example():
         agent=processor_agent
     )
     
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[analyzer_agent, processor_agent],
         tasks=[analysis_task, premium_task, standard_task, basic_task],
         process="workflow", output="verbose"
@@ -109,7 +109,7 @@ def loop_pattern_example():
         agent=validator_agent
     )
     
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[processor_agent, validator_agent],
         tasks=[process_task, finalize_task],
         process="workflow", output="verbose"
@@ -183,7 +183,7 @@ def decision_tree_example():
     
     all_tasks = [categorize_task, technical_task, business_task] + terminal_tasks
     
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[analyzer_agent, processor_agent],
         tasks=all_tasks,
         process="workflow", output="verbose"
@@ -269,7 +269,7 @@ def dynamic_routing_example():
         agent=processor_agent
     )
     
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[dynamic_router, processor_agent],
         tasks=[route_task, escalate_task, automate_task, review_task, standard_task],
         process="workflow", output="verbose"

examples/python/concepts/self-reflection-details.py

@@ -8,7 +8,7 @@ This example demonstrates the self-reflection capabilities in PraisonAI agents:
 - Impact on output quality
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from typing import Dict, Any
 import time
 
@@ -162,7 +162,7 @@ def reflection_workflow_example():
         context=[create_task, review_task]
     )
     
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[creator_agent, reviewer_agent, polisher_agent],
         tasks=[create_task, review_task, polish_task],
         process="sequential", output="verbose"

examples/python/concepts/self-reflection-optimization-patterns.py

@@ -5,7 +5,7 @@ This example demonstrates self-reflection capabilities using PraisonAI's
 built-in reflection features for iterative improvement and quality optimization.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import internet_search
 
 print("=== Self-Reflection Optimization Patterns Example ===\n")

examples/python/concepts/simple-csv-url-processor.py

@@ -9,7 +9,7 @@ This is the simplest possible implementation for processing URLs from a CSV file
 Author: Generated for GitHub Issue #23
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import write_csv
 
 def create_url_csv():
@@ -59,7 +59,7 @@ def main():
     )
     
     # Step 4: Run the agents
-    agents = AgentTeam(
+    agents = Agents(
         agents=[url_agent],
         tasks=[url_task],
         process="workflow",

examples/python/conditional_branching_example.py

@@ -12,7 +12,7 @@ The if: pattern enables dynamic workflow paths based on
 runtime conditions and variable values.
 """
 
-from praisonaiagents import AgentFlow, WorkflowContext, StepResult
+from praisonaiagents import Workflow, WorkflowContext, StepResult
 from praisonaiagents.workflows import if_, loop
 
 
@@ -39,7 +39,7 @@ def basic_if_example():
         return StepResult(output="Application rejected")
     
     # Test with passing score
-    workflow_pass = AgentFlow(
+    workflow_pass = Workflow(
         steps=[
             if_(
                 condition="{{score}} >= 70",
@@ -54,7 +54,7 @@ def basic_if_example():
     workflow_pass.start("Evaluate application")
     
     # Test with failing score
-    workflow_fail = AgentFlow(
+    workflow_fail = Workflow(
         steps=[
             if_(
                 condition="{{score}} >= 70",
@@ -90,7 +90,7 @@ def string_condition_example():
         return StepResult(output="Inactive user archived")
     
     # Test with active status
-    workflow = AgentFlow(
+    workflow = Workflow(
         steps=[
             if_(
                 condition="{{status}} == active",
@@ -105,7 +105,7 @@ def string_condition_example():
     workflow.start("Process user")
     
     # Test with inactive status
-    workflow2 = AgentFlow(
+    workflow2 = Workflow(
         steps=[
             if_(
                 condition="{{status}} == active",
@@ -141,7 +141,7 @@ def contains_condition_example():
         return StepResult(output="Content approved")
     
     # Test with flagged content
-    workflow1 = AgentFlow(
+    workflow1 = Workflow(
         steps=[
             if_(
                 condition="error in {{message}}",
@@ -156,7 +156,7 @@ def contains_condition_example():
     workflow1.start("Filter content")
     
     # Test with clean content
-    workflow2 = AgentFlow(
+    workflow2 = Workflow(
         steps=[
             if_(
                 condition="error in {{message}}",
@@ -200,7 +200,7 @@ def if_inside_loop_example():
         print(f"  📦 {name}: Standard service activated")
         return StepResult(output=f"Standard service for {name}")
     
-    workflow = AgentFlow(
+    workflow = Workflow(
         steps=[
             loop(
                 steps=[
@@ -258,7 +258,7 @@ def nested_conditions_example():
     
     # Outer condition: Is premium?
     # Inner condition (if premium): Is VIP?
-    workflow = AgentFlow(
+    workflow = Workflow(
         steps=[
             if_(
                 condition="{{tier}} == premium",
@@ -278,7 +278,7 @@ def nested_conditions_example():
     print("\nTest 1: Premium tier, high spend")
     workflow.start("Determine support level")
     
-    workflow2 = AgentFlow(
+    workflow2 = Workflow(
         steps=[
             if_(
                 condition="{{tier}} == premium",
@@ -298,7 +298,7 @@ def nested_conditions_example():
     print("\nTest 2: Premium tier, low spend")
     workflow2.start("Determine support level")
     
-    workflow3 = AgentFlow(
+    workflow3 = Workflow(
         steps=[
             if_(
                 condition="{{tier}} == premium",
@@ -340,7 +340,7 @@ def no_else_example():
         return StepResult(output="Continued")
     
     # Only send notification if opted in
-    workflow = AgentFlow(
+    workflow = Workflow(
         steps=[
             if_(
                 condition="{{notify}} == true",
@@ -355,7 +355,7 @@ def no_else_example():
     print("\nTest 1: notify = true")
     workflow.start("Process with notification")
     
-    workflow2 = AgentFlow(
+    workflow2 = Workflow(
         steps=[
             if_(
                 condition="{{notify}} == true",

examples/python/custom_tools/example_latency_tracking.py

@@ -4,7 +4,7 @@ Example: Using Latency Tracking Tool with PraisonAI
 This example shows how to track latency without modifying core files.
 """
 
-from praisonaiagents import Agent, AgentTeam
+from praisonaiagents import Agent, Agents
 from latency_tracker_tool import (
     latency_tracking_tool, 
     create_tracked_agent,

examples/python/custom_tools/mcp_server_latency_example.py

@@ -5,7 +5,7 @@ This shows how to add latency tracking to an MCP server
 without modifying PraisonAI core files.
 """
 
-from praisonaiagents import Agent, AgentTeam
+from praisonaiagents import Agent, Agents
 from hosted_server import HostedMCPServer  # Import from local file
 from latency_tracker_tool import tracker, get_latency_metrics
 import json

examples/python/data/cot-agents.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import cot_save, cot_upload_to_huggingface
 from pydantic import BaseModel
 import os
@@ -128,7 +128,7 @@ upload_to_huggingface_task = Task(
 )
 
 # Initialize workflow
-agents = AgentTeam(
+agents = Agents(
     agents=[qa_generator, total_questions_evaluator, cot_generator, upload_to_huggingface],
     tasks=[generate_task, evaluate_total_questions_task, generate_cot_task, upload_to_huggingface_task],
     process="workflow",

examples/python/eval/README.md

@@ -1,43 +0,0 @@
-# EvaluationLoop Examples
-
-Examples demonstrating iterative evaluation and improvement patterns.
-
-## Quick Start
-
-```bash
-pip install praisonaiagents
-export OPENAI_API_KEY=your-key
-```
-
-## Examples
-
-| File | Description |
-|------|-------------|
-| `basic_evaluation_loop.py` | Simple loop: Run → Judge → Improve |
-| `multi_step_task_loop.py` | Sequential tasks with context passing |
-| `recipe_optimization_loop.py` | CLI-based recipe optimization |
-
-## Pattern
-
-```
-┌─────────┐     ┌─────────┐     ┌──────────┐
-│  Agent  │ ──► │  Judge  │ ──► │ Feedback │
-│  runs   │     │ scores  │     │ improves │
-└─────────┘     └─────────┘     └──────────┘
-     ▲                               │
-     └───────────────────────────────┘
-           (repeat until 8.0+)
-```
-
-## Run Examples
-
-```bash
-# Basic loop
-python basic_evaluation_loop.py
-
-# Multi-step with context
-python multi_step_task_loop.py
-
-# CLI recipe loop
-python recipe_optimization_loop.py "research AI trends"
-```

examples/python/eval/basic_evaluation_loop.py

@@ -1,73 +0,0 @@
-"""
-Basic EvaluationLoop Example
-
-Demonstrates the iterative evaluation loop pattern:
-Run agent → Judge output → Improve → Repeat until threshold met.
-
-Usage:
-    pip install praisonaiagents
-    export OPENAI_API_KEY=your-key
-    python basic_evaluation_loop.py
-"""
-from praisonaiagents import Agent
-from praisonaiagents.eval import EvaluationLoop
-
-
-def on_iteration(result):
-    """Callback showing progress after each iteration."""
-    status = "✅" if result.score >= 8.0 else "⚠️" if result.score >= 6.0 else "❌"
-    print(f"{status} Iteration {result.iteration}: {result.score:.1f}/10")
-    if result.findings:
-        print(f"   → {result.findings[0][:60]}...")
-
-
-def main():
-    # Create an agent
-    agent = Agent(
-        name="writer",
-        instructions="You are a technical content writer. Write clear, accurate explanations."
-    )
-
-    # Run evaluation loop
-    loop = EvaluationLoop(
-        agent=agent,
-        criteria="""
-        Evaluate the response on:
-        1. CLARITY: Is the explanation easy to understand?
-        2. ACCURACY: Is the technical content correct?
-        3. COMPLETENESS: Does it cover the key aspects?
-        4. EXAMPLES: Does it include practical examples?
-        
-        Score 1-10 based on all criteria.
-        """,
-        threshold=8.0,
-        max_iterations=5,
-        on_iteration=on_iteration,
-        verbose=False,
-    )
-
-    print("╔════════════════════════════════════════════════════════════╗")
-    print("║            Basic EvaluationLoop Example                     ║")
-    print("║  Pattern: Run → Judge → Improve → Repeat                   ║")
-    print("║  Target: 8.0/10 score                                       ║")
-    print("╚════════════════════════════════════════════════════════════╝\n")
-
-    result = loop.run("Explain how API rate limiting works and why it matters")
-
-    print("\n" + "─" * 60)
-    print("RESULTS:")
-    print("─" * 60)
-    print(f"Success: {result.success}")
-    print(f"Final Score: {result.final_score:.1f}/10")
-    print(f"Iterations: {result.num_iterations}")
-    print(f"Score History: {[f'{s:.1f}' for s in result.score_history]}")
-    print(f"Duration: {result.total_duration_seconds:.2f}s")
-
-    print("\n" + "─" * 60)
-    print("FINAL OUTPUT (first 500 chars):")
-    print("─" * 60)
-    print(result.final_output[:500] + "..." if len(result.final_output) > 500 else result.final_output)
-
-
-if __name__ == "__main__":
-    main()

examples/python/eval/multi_step_task_loop.py

@@ -1,144 +0,0 @@
-"""
-Multi-Step Task Loop Example
-
-Demonstrates evaluating sequential task steps where each step can
-reference output from previous steps.
-
-Pattern:
-1. Research → Evaluate → Improve
-2. Analyze (using research) → Evaluate → Improve  
-3. Report (using analysis) → Evaluate → Improve
-
-Usage:
-    pip install praisonaiagents
-    export OPENAI_API_KEY=your-key
-    python multi_step_task_loop.py
-"""
-from praisonaiagents import Agent
-from praisonaiagents.eval import EvaluationLoop
-
-
-def on_iteration(result):
-    """Show iteration progress."""
-    status = "✅" if result.score >= 8.0 else "⚠️" if result.score >= 6.0 else "❌"
-    print(f"  {status} Iteration {result.iteration}: {result.score:.1f}/10")
-
-
-def run_step(step_name: str, agent: Agent, task: str, criteria: str, context: str = "") -> dict:
-    """Run a single step through an evaluation loop."""
-    print(f"\n{'─'*60}")
-    print(f"STEP: {step_name}")
-    print(f"{'─'*60}")
-    
-    # Include context from previous step if provided
-    full_task = task
-    if context:
-        full_task = f"{task}\n\nContext from previous step:\n{context[:1000]}"
-    
-    loop = EvaluationLoop(
-        agent=agent,
-        criteria=criteria,
-        threshold=8.0,
-        max_iterations=3,
-        on_iteration=on_iteration,
-        verbose=False,
-    )
-    
-    result = loop.run(full_task)
-    
-    print(f"  → Final: {result.final_score:.1f}/10 ({result.num_iterations} iterations)")
-    
-    return {
-        "name": step_name,
-        "output": result.final_output,
-        "score": result.final_score,
-        "success": result.success,
-        "iterations": result.num_iterations,
-    }
-
-
-def main():
-    print("╔════════════════════════════════════════════════════════════╗")
-    print("║         Multi-Step Task Loop Example                       ║")
-    print("║  Pattern: Step1 → Step2 → Step3 (with context passing)    ║")
-    print("║  Each step: Run → Judge → Improve until 8.0+              ║")
-    print("╚════════════════════════════════════════════════════════════╝")
-
-    # Create specialized agents
-    researcher = Agent(
-        name="researcher",
-        instructions="You are a research specialist. Find and summarize key information."
-    )
-    
-    analyst = Agent(
-        name="analyst", 
-        instructions="You are an analyst. Identify patterns, insights, and implications."
-    )
-    
-    writer = Agent(
-        name="writer",
-        instructions="You are a report writer. Create clear, actionable summaries."
-    )
-
-    # Define task steps
-    steps = [
-        {
-            "name": "Research",
-            "agent": researcher,
-            "task": "Research the top 3 trends in AI for 2024-2025. Provide brief descriptions.",
-            "criteria": "Covers 3 distinct trends with accurate descriptions.",
-        },
-        {
-            "name": "Analysis",
-            "agent": analyst,
-            "task": "Analyze the implications of these AI trends for software development.",
-            "criteria": "Identifies actionable insights and potential challenges.",
-        },
-        {
-            "name": "Report",
-            "agent": writer,
-            "task": "Create a brief executive summary (3-4 bullet points) for a CTO.",
-            "criteria": "Concise, actionable, appropriate for executive audience.",
-        },
-    ]
-
-    # Run all steps with context passing
-    results = []
-    context = ""
-    
-    for step in steps:
-        result = run_step(
-            step_name=step["name"],
-            agent=step["agent"],
-            task=step["task"],
-            criteria=step["criteria"],
-            context=context,
-        )
-        results.append(result)
-        context = result["output"]  # Pass output as context to next step
-
-    # Summary
-    print("\n" + "═"*60)
-    print("SUMMARY")
-    print("═"*60)
-    
-    total_iterations = sum(r["iterations"] for r in results)
-    avg_score = sum(r["score"] for r in results) / len(results)
-    all_success = all(r["success"] for r in results)
-    
-    for r in results:
-        status = "✅" if r["success"] else "❌"
-        print(f"  {status} {r['name']}: {r['score']:.1f}/10 ({r['iterations']} iterations)")
-    
-    print(f"\n  Total Iterations: {total_iterations}")
-    print(f"  Average Score: {avg_score:.1f}/10")
-    print(f"  All Steps Passed: {'Yes' if all_success else 'No'}")
-
-    print("\n" + "─"*60)
-    print("FINAL REPORT OUTPUT:")
-    print("─"*60)
-    print(results[-1]["output"][:600])
-
-
-if __name__ == "__main__":
-    main()

examples/python/eval/recipe_optimization_loop.py

@@ -1,183 +0,0 @@
-"""
-Recipe Optimization Loop (CLI-based)
-
-Demonstrates the 5-cycle recipe improvement pattern using CLI commands:
-    Create (once) → Run → Judge → Optimize (loop 5x)
-
-Usage:
-    pip install praisonai
-    export OPENAI_API_KEY=your-key
-    export TAVILY_API_KEY=your-key
-    python recipe_optimization_loop.py "research AI trends in healthcare"
-"""
-import subprocess
-import sys
-import os
-import json
-from pathlib import Path
-
-
-def run_cli(cmd: str, cwd: str = None) -> tuple[int, str, str]:
-    """Run a CLI command and return (exit_code, stdout, stderr)."""
-    result = subprocess.run(
-        cmd,
-        shell=True,
-        capture_output=True,
-        text=True,
-        cwd=cwd,
-    )
-    return result.returncode, result.stdout, result.stderr
-
-
-def create_recipe(goal: str, work_dir: str) -> str:
-    """Create a recipe once. Returns recipe name."""
-    print(f"\n{'═'*60}")
-    print("STEP 1: CREATE RECIPE (once)")
-    print(f"{'═'*60}")
-    print(f"Goal: {goal}")
-    
-    cmd = f'praisonai recipe create "{goal}" --no-optimize'
-    code, stdout, stderr = run_cli(cmd, cwd=work_dir)
-    
-    if code != 0:
-        print(f"❌ Failed to create recipe: {stderr}")
-        return None
-    
-    # Extract recipe name from output
-    for line in stdout.split('\n'):
-        if 'Created recipe:' in line:
-            recipe_name = line.split('Created recipe:')[1].strip()
-            print(f"✅ Created: {recipe_name}")
-            return recipe_name
-    
-    print(f"✅ Recipe created")
-    return None
-
-
-def run_recipe(recipe_name: str, trace_name: str, work_dir: str) -> tuple[bool, str]:
-    """Run the recipe and save trace. Returns (success, output)."""
-    cmd = f'praisonai recipe run {recipe_name} --save --name {trace_name}'
-    code, stdout, stderr = run_cli(cmd, cwd=work_dir)
-    
-    success = code == 0 and 'status: completed' in stdout.lower()
-    return success, stdout
-
-
-def judge_recipe(trace_name: str, work_dir: str) -> tuple[float, str]:
-    """Judge the trace. Returns (score, feedback)."""
-    cmd = f'praisonai recipe judge {trace_name}'
-    code, stdout, stderr = run_cli(cmd, cwd=work_dir)
-    
-    # Extract score from output
-    score = 0.0
-    for line in stdout.split('\n'):
-        if 'Overall Score:' in line:
-            try:
-                score = float(line.split(':')[1].strip().split('/')[0])
-            except:
-                pass
-    
-    return score, stdout
-
-
-def optimize_recipe(recipe_name: str, iterations: int, work_dir: str) -> tuple[float, str]:
-    """Optimize the recipe. Returns (final_score, output)."""
-    cmd = f'praisonai recipe optimize {recipe_name} --iterations {iterations}'
-    code, stdout, stderr = run_cli(cmd, cwd=work_dir)
-    
-    # Extract final score
-    score = 0.0
-    for line in stdout.split('\n'):
-        if 'Final score:' in line or 'score:' in line.lower():
-            try:
-                score = float(line.split(':')[1].strip().split('/')[0])
-            except:
-                pass
-    
-    return score, stdout
-
-
-def run_optimization_loop(goal: str, num_cycles: int = 5, threshold: float = 8.0):
-    """Run the full Create → Run → Judge → Optimize loop."""
-    
-    print("╔════════════════════════════════════════════════════════════╗")
-    print("║       Recipe Optimization Loop (CLI-based)                 ║")
-    print("║  Pattern: Create (once) → Run → Judge → Optimize (loop)   ║")
-    print(f"║  Cycles: {num_cycles} | Threshold: {threshold}/10                         ║")
-    print("╚════════════════════════════════════════════════════════════╝")
-    
-    # Create work directory
-    work_dir = Path("/tmp/recipe-optimization-loop")
-    work_dir.mkdir(parents=True, exist_ok=True)
-    os.chdir(work_dir)
-    
-    # Step 1: Create recipe (once)
-    recipe_name = create_recipe(goal, str(work_dir))
-    if not recipe_name:
-        print("Failed to create recipe. Exiting.")
-        return
-    
-    # Step 2-N: Run → Judge → Optimize loop
-    results = []
-    
-    for cycle in range(1, num_cycles + 1):
-        print(f"\n{'─'*60}")
-        print(f"CYCLE {cycle}/{num_cycles}")
-        print(f"{'─'*60}")
-        
-        trace_name = f"cycle-{cycle}"
-        
-        # Run
-        print(f"  📝 Running recipe...")
-        success, run_output = run_recipe(recipe_name, trace_name, str(work_dir))
-        run_status = "✅" if success else "⚠️"
-        print(f"  {run_status} Run complete")
-        
-        # Judge
-        print(f"  ⚖️ Judging output...")
-        score, judge_output = judge_recipe(trace_name, str(work_dir))
-        score_status = "✅" if score >= threshold else "⚠️" if score >= 6.0 else "❌"
-        print(f"  {score_status} Score: {score}/10")
-        
-        # Check if threshold met
-        if score >= threshold:
-            print(f"  🎉 Threshold {threshold}/10 reached!")
-            results.append({"cycle": cycle, "score": score, "status": "passed"})
-            break
-        
-        # Optimize
-        print(f"  🔧 Optimizing recipe...")
-        opt_score, opt_output = optimize_recipe(recipe_name, 1, str(work_dir))
-        print(f"  → Optimized score: {opt_score}/10")
-        
-        results.append({
-            "cycle": cycle,
-            "initial_score": score,
-            "optimized_score": opt_score,
-            "status": "optimized" if opt_score > score else "no_change"
-        })
-    
-    # Summary
-    print(f"\n{'═'*60}")
-    print("SUMMARY")
-    print(f"{'═'*60}")
-    
-    for r in results:
-        if "initial_score" in r:
-            print(f"  Cycle {r['cycle']}: {r['initial_score']} → {r['optimized_score']}/10")
-        else:
-            print(f"  Cycle {r['cycle']}: {r['score']}/10 ✅ PASSED")
-    
-    final_score = results[-1].get("optimized_score", results[-1].get("score", 0))
-    success = final_score >= threshold
-    
-    print(f"\n  Final Score: {final_score}/10")
-    print(f"  Success: {'Yes ✅' if success else 'No ❌'}")
-    print(f"  Recipe: {work_dir}/{recipe_name}")
-    
-    return results
-
-
-if __name__ == "__main__":
-    goal = sys.argv[1] if len(sys.argv) > 1 else "research latest AI trends and create a summary report"
-    run_optimization_loop(goal, num_cycles=5, threshold=8.0)

examples/python/general/advanced-callback-systems.py

@@ -5,7 +5,7 @@ This example demonstrates callback systems using PraisonAI's built-in
 callback functionality for monitoring agent interactions and tool usage.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.display_callback import register_display_callback
 from praisonaiagents.tools import internet_search
 

examples/python/general/async_example.py

@@ -1,7 +1,7 @@
 import asyncio
 import time
 from typing import List, Dict
-from praisonaiagents import Agent, Task, AgentTeam, TaskOutput
+from praisonaiagents import Agent, Task, Agents, TaskOutput
 from praisonaiagents.main import (
     display_error,
     display_interaction,
@@ -156,7 +156,7 @@ workflow_async_task = Task(
 def run_sync_example():
     """Run synchronous example"""
     display_instruction("\nRunning Synchronous Example...", console)
-    agents = AgentTeam(
+    agents = Agents(
         agents=[sync_agent],
         tasks=[sync_task],
         process="sequential"
@@ -167,7 +167,7 @@ def run_sync_example():
 async def run_async_example():
     """Run asynchronous example"""
     display_instruction("\nRunning Asynchronous Example...", console)
-    agents = AgentTeam(
+    agents = Agents(
         agents=[async_agent],
         tasks=[async_task],
         process="sequential"
@@ -178,7 +178,7 @@ async def run_async_example():
 async def run_mixed_example():
     """Run mixed sync/async example"""
     display_instruction("\nRunning Mixed Sync/Async Example...", console)
-    agents = AgentTeam(
+    agents = Agents(
         agents=[sync_agent, async_agent],
         tasks=[sync_task, async_task],
         process="sequential"
@@ -189,7 +189,7 @@ async def run_mixed_example():
 async def run_workflow_example():
     """Run workflow example with both sync and async tasks"""
     display_instruction("\nRunning Workflow Example...", console)
-    agents = AgentTeam(
+    agents = Agents(
         agents=[sync_agent, async_agent],
         tasks=[workflow_sync_task, workflow_async_task],
         process="workflow"

examples/python/general/async_example_full.py

@@ -1,7 +1,7 @@
 import asyncio
 import time
 from typing import List, Dict
-from praisonaiagents import Agent, Task, AgentTeam, TaskOutput
+from praisonaiagents import Agent, Task, Agents, TaskOutput
 from duckduckgo_search import DDGS
 from pydantic import BaseModel
 
@@ -111,7 +111,7 @@ async def run_parallel_tasks():
     )
     
     # Create a single Agents instance with both agents
-    agents = AgentTeam(
+    agents = Agents(
         agents=[async_agent, summary_agent],
         tasks=parallel_tasks + [summary_task],
         process="sequential"

examples/python/general/async_example_full_multigroups.py

@@ -1,7 +1,7 @@
 import asyncio
 import time
 from typing import List, Dict
-from praisonaiagents import Agent, Task, AgentTeam, TaskOutput
+from praisonaiagents import Agent, Task, Agents, TaskOutput
 from duckduckgo_search import DDGS
 from pydantic import BaseModel
 
@@ -99,7 +99,7 @@ async_task = Task(
 async def run_single_task():
     """Run single async task"""
     print("\nRunning Single Async Task...")
-    agents = AgentTeam(
+    agents = Agents(
         agents=[async_agent],
         tasks=[async_task],
         process="sequential"
@@ -182,7 +182,7 @@ Present the summary in a clear, structured format with sections for findings, pa
     )
     
     # First run parallel search tasks
-    agents = AgentTeam(
+    agents = Agents(
         agents=[async_agent],
         tasks=parallel_tasks,  # Only run search tasks first
         process="sequential"
@@ -206,7 +206,7 @@ Present the summary in a clear, structured format with sections for findings, pa
     summary_task.context = completed_tasks
     
     # Run summarization task with summary agent
-    summary_agents = AgentTeam(
+    summary_agents = Agents(
         agents=[summary_agent],  # Use summary agent for synthesis
         tasks=[summary_task],
         process="sequential"

examples/python/general/auto_agents_example.py

@@ -18,7 +18,7 @@ from praisonaiagents import AutoAgents
 from praisonaiagents.tools import duckduckgo
 
 # Basic usage - AutoAgents analyzes complexity and creates optimal agents
-agents = AutoAgentTeam(
+agents = AutoAgents(
     instructions="Search for information about AI Agents",
     tools=[duckduckgo],
     process="sequential",  # or "hierarchical"

examples/python/general/autonomous-agent.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 import time
 
 def get_environment_state():
@@ -86,7 +86,7 @@ feedback_task = Task(
 )
 
 # Create workflow manager
-workflow = AgentTeam(
+workflow = Agents(
     agents=[llm_caller, action_agent, feedback_agent],
     tasks=[monitor_task, action_task, feedback_task],
     process="workflow", output="verbose"

examples/python/general/code_agents_example.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 import json
 from e2b_code_interpreter import Sandbox
 
@@ -46,5 +46,5 @@ execution_agent_task = Task(
     agent=execution_agent
 )
 
-agents = AgentTeam(agents=[code_agent, execution_agent], tasks=[code_agent_task, execution_agent_task])
+agents = Agents(agents=[code_agent, execution_agent], tasks=[code_agent_task, execution_agent_task])
 agents.start()

examples/python/general/evaluator-optimiser.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 # Create generator and evaluator agents
 generator = Agent(
@@ -53,7 +53,7 @@ evaluate_task = Task(
 )
 
 # Create workflow manager
-workflow = AgentTeam(
+workflow = Agents(
     agents=[generator, evaluator],
     tasks=[generate_task, evaluate_task],
     process="workflow", output="verbose"

examples/python/general/example_callback.py

@@ -183,7 +183,7 @@ def main():
     )
 
     # Create and run agents manager
-    agents = AgentTeam(
+    agents = Agents(
         agents=[researcher, writer],
         tasks=[task1, task2, task3, task4],
         process="sequential",

examples/python/general/example_custom_tools.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from typing import List, Dict, Union
 from duckduckgo_search import DDGS
 from langchain_community.tools import YouTubeSearchTool
@@ -141,7 +141,7 @@ validate_task = Task(
 )
 
 # 4. Workflow
-agents = AgentTeam(
+agents = Agents(
     agents=[data_agent],
     tasks=[collect_task, validate_task],
     process="workflow"

examples/python/general/example_sequential.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam, error_logs
+from praisonaiagents import Agent, Task, Agents, error_logs
 from duckduckgo_search import DDGS
 
 def my_callback(output):
@@ -92,7 +92,7 @@ task4 = Task(
 )
 
 # Create and run agents manager
-agents = AgentTeam(
+agents = Agents(
     agents=[researcher, writer],
     tasks=[task1, task2, task3, task4],
     output="minimal",

examples/python/general/human_approval_example.py

@@ -24,7 +24,7 @@ import sys
 # Add the local development path to use the current implementation
 sys.path.append(os.path.join(os.path.dirname(__file__), '..', '..', '..', 'src', 'praisonai-agents'))
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import python_tools, file_tools, shell_tools
 from praisonaiagents.main import register_approval_callback
 from praisonaiagents.approval import (
@@ -109,7 +109,7 @@ def main():
     ]
     
     # Create and run process
-    process = AgentTeam(
+    process = Agents(
         agents=[agent],
         tasks=tasks, output="verbose"
     )
@@ -166,7 +166,7 @@ async def async_demo():
         expected_output="Async execution result"
     )
     
-    process = AgentTeam(
+    process = Agents(
         agents=[agent],
         tasks=[task], output="verbose"
     )

examples/python/general/langchain_example.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from langchain_community.tools import YouTubeSearchTool
 from langchain_community.utilities import WikipediaAPIWrapper
 
@@ -21,7 +21,7 @@ task = Task(
 )
 
 # Create and start the workflow
-agents = AgentTeam(
+agents = Agents(
     agents=[agent],
     tasks=[task], output="verbose"
 )

examples/python/general/memory_example.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 import logging
 import os
 
@@ -101,7 +101,7 @@ def main():
     )
 
     # Initialize Agents with memory configuration
-    agents = AgentTeam(
+    agents = Agents(
         agents=[researcher, retriever],
         tasks=[store_task, verify_task, query_task, query_both_task],  # Use same verbose level as memory
         memory={
@@ -115,7 +115,7 @@ def main():
         }
     )
 
-    # agents = AgentTeam(
+    # agents = Agents(
     #     agents=[researcher, retriever],
     #     tasks=[store_task, verify_task, query_task, query_both_task],
     #     # Use same verbose level as memory

examples/python/general/memory_simple.py

@@ -54,7 +54,7 @@ blog_task = Task(
     agent=blog_agent
 )
 
-agents = AgentTeam(
+agents = Agents(
     agents=[fact_agent, research_agent, blog_agent],
     tasks=[fact_task, research_task, research_task2, research_task3, research_task4, blog_task],
     memory=True

examples/python/general/mini_agents_example.py

@@ -1,6 +1,6 @@
-from praisonaiagents import Agent, AgentTeam, Tools
+from praisonaiagents import Agent, Agents, Tools
 
 research_agent = Agent(instructions="You are a research agent to search internet about AI 2024", tools=[Tools.internet_search])
 summarise_agent = Agent(instructions="You are a summarize agent to summarise in points")
-agents = AgentTeam(agents=[research_agent, summarise_agent])
+agents = Agents(agents=[research_agent, summarise_agent])
 agents.start()

examples/python/general/multimodal.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 # Create Vision Analysis Agent
 vision_agent = Agent(
@@ -43,7 +43,7 @@ task3 = Task(
 )
 
 # Create Agents instance
-agents = AgentTeam(
+agents = Agents(
     agents=[vision_agent],
     tasks=[task1, task2, task3],
     process="sequential"

examples/python/general/orchestrator-workers.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 import time
 
 def get_time_check():
@@ -93,7 +93,7 @@ synthesize_task = Task(
 )
 
 # Create workflow manager
-workflow = AgentTeam(
+workflow = Agents(
     agents=[router, worker1, worker2, worker3, synthesizer],
     tasks=[router_task, worker1_task, worker2_task, worker3_task, synthesize_task],
     process="workflow", output="verbose"

examples/python/general/parallelisation.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from datetime import datetime
 import asyncio
 
@@ -75,7 +75,7 @@ aggregate_task = Task(
 async def main():
 
     # Create workflow manager
-    workflow = AgentTeam(
+    workflow = Agents(
         agents=[agent1, agent2, agent3, aggregator],
         tasks=[task1, task2, task3, aggregate_task],
         process="workflow"

examples/python/general/prompt_chaining.py

@@ -64,7 +64,7 @@ final_task = Task(
 )
 
 # Create the workflow manager
-workflow = AgentTeam(
+workflow = Agents(
     agents=[agent1, agent2, agent3],
     tasks=[initial_task, analysis_task, final_task],
     process="workflow",  # Use workflow process type

examples/python/general/structured_agents_example.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam, Tools
+from praisonaiagents import Agent, Task, Agents, Tools
 from pydantic import BaseModel
 
 class AnalysisReport(BaseModel):
@@ -44,7 +44,7 @@ analysis_task = Task(
 )
 
 # Initialize and run agents
-agents = AgentTeam(
+agents = Agents(
     agents=[researcher, analyst],
     tasks=[research_task, analysis_task],
     process="sequential",

examples/python/general/tools-class.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 import os
 import requests
 from typing import Any, Dict, List, Optional
@@ -106,7 +106,7 @@ task = Task(
 )
 
 # Create and start the workflow
-agents = AgentTeam(
+agents = Agents(
     agents=[agent],
     tasks=[task], output="verbose"
 )

examples/python/general/tools_example.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import get_article, get_news_sources, get_articles_from_source, get_trending_topics
 
 # Create Wikipedia agent
@@ -22,7 +22,7 @@ news_task = Task(
 
 
 # Run agent
-agents = AgentTeam(
+agents = Agents(
     agents=[news_agent],
     tasks=[news_task],
     process="sequential"

examples/python/general/workflow_example_basic.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from typing import List, Dict
 from duckduckgo_search import DDGS
 
@@ -64,7 +64,7 @@ validate_task = Task(
 )
 
 # 4. AI Agents Workflow
-agents = AgentTeam(
+agents = Agents(
     agents=[data_agent],
     tasks=[collect_task, validate_task],
     process="workflow"

examples/python/general/workflow_example_detailed.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 import random
 from typing import List, Dict, Union
 import json
@@ -225,7 +225,7 @@ process_task = Task(
 )
 
 # Create Agents instance with workflow process
-workflow = AgentTeam(
+workflow = Agents(
     agents=[data_agent, process_agent],
     tasks=[collect_task, validate_task, process_task],
     process="workflow"

examples/python/guardrails/comprehensive-guardrails-example.py

@@ -12,7 +12,7 @@ Features demonstrated:
 - Quality assurance workflows
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.task import TaskOutput
 from typing import Tuple, Any
 import re
@@ -181,7 +181,7 @@ llm_guardrail_task = Task(
 )
 
 # Execute tasks with guardrails
-agents = AgentTeam(
+agents = Agents(
     agents=[email_agent, content_agent, business_agent, research_agent, llm_guardrail_agent],
     tasks=[email_task, content_task, business_task, research_task, llm_guardrail_task], output="verbose"
 )

examples/python/guardrails/production-guardrails-patterns.py

@@ -5,7 +5,7 @@ This example demonstrates production guardrail patterns using PraisonAI's
 built-in validation and safety mechanisms for secure agent operations.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import internet_search
 
 print("=== Production Guardrails Patterns Example ===\n")

examples/python/input/advanced_dynamic_input.py

@@ -5,7 +5,7 @@ This example demonstrates an advanced system that dynamically creates agents and
 based on user inputs, including conditional logic, custom configurations, and file output.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import duckduckgo
 import os
 from typing import Dict, List
@@ -137,7 +137,7 @@ class DynamicAgentSystem:
         
         # Run the system
         print(f"\n🚀 Starting {process} analysis for '{inputs['topic']}'...")
-        praison_agents = AgentTeam(
+        praison_agents = Agents(
             agents=agents,
             tasks=tasks,
             process=process,

examples/python/input/environment_variable_input.py

@@ -6,7 +6,7 @@ to create flexible agent configurations that can be pre-configured via environme
 """
 
 import os
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 # Set via environment or use default
 default_topic = os.getenv("RESEARCH_TOPIC", "AI trends")
@@ -46,7 +46,7 @@ print(f"  - Max Retries: {max_retries}")
 print("\n" + "="*50 + "\n")
 
 # Run agents
-agents = AgentTeam(agents=[agent], tasks=[task])
+agents = Agents(agents=[agent], tasks=[task])
 result = agents.start()
 
 # Save to environment-specified location if provided

examples/python/input/medium_complexity_input.py

@@ -5,7 +5,7 @@ This example shows how to use multiple user inputs to create a more sophisticate
 agent system with tools, multiple agents, and context passing between tasks.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import duckduckgo
 
 # Get multiple inputs
@@ -47,7 +47,7 @@ analyze_task = Task(
 )
 
 # Run sequential process
-agents = AgentTeam(
+agents = Agents(
     agents=[search_agent, analysis_agent],
     tasks=[search_task, analyze_task],
     process="sequential"

examples/python/input/simple_input.py

@@ -5,7 +5,7 @@ This example demonstrates how to use basic user input to create dynamic agents a
 The user is prompted for a search query, and the agent searches for information about it.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 # Get user input
 user_query = input("What would you like to search for? ")
@@ -26,5 +26,5 @@ task = Task(
 )
 
 # Run
-agents = AgentTeam(agents=[agent], tasks=[task])
+agents = Agents(agents=[agent], tasks=[task])
 agents.start()

examples/python/input/streamlit_ui_input.py

@@ -10,7 +10,7 @@ To run this example:
 """
 
 import streamlit as st
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import duckduckgo
 
 # Set page configuration
@@ -125,7 +125,7 @@ if st.button("🚀 Submit", type="primary", use_container_width=True):
                     )
                     
                     # Run agents
-                    agents = AgentTeam(
+                    agents = Agents(
                         agents=[agent],
                         tasks=[task],
                         process=process_type

examples/python/mcp/whatapp-multi-agents-mcp.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, AgentTeam, MCP
+from praisonaiagents import Agent, Agents, MCP
 
 airbnb_agent = Agent(
     instructions="""Search for Apartments in Paris for 2 nights on Airbnb. 04/28 - 04/30 for 2 adults""",
@@ -12,6 +12,6 @@ whatsapp_agent = Agent(
     tools=MCP("python /Users/praison/whatsapp-mcp/whatsapp-mcp-server/main.py")
 )
 
-agents = AgentTeam(agents=[airbnb_agent, whatsapp_agent])
+agents = Agents(agents=[airbnb_agent, whatsapp_agent])
 
 agents.start()

examples/python/mcp/whatsapp-mcp-ui.py

@@ -1,4 +1,4 @@
-from praisonaiagents import Agent, AgentTeam, MCP
+from praisonaiagents import Agent, Agents, MCP
 import gradio as gr
 
 def search_airbnb(query):
@@ -14,7 +14,7 @@ def search_airbnb(query):
         tools=MCP("python /Users/praison/whatsapp-mcp/whatsapp-mcp-server/main.py")
     )
 
-    agents = AgentTeam(agents=[airbnb_agent, whatsapp_agent])
+    agents = Agents(agents=[airbnb_agent, whatsapp_agent])
 
     result = agents.start()
     return f"## Airbnb Search Results\n\n{result}"

examples/python/memory/advanced-graph-memory-integration.py

@@ -5,7 +5,7 @@ This example demonstrates graph memory capabilities with PraisonAI agents
 for knowledge graph construction and relationship-aware memory retrieval.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import internet_search
 
 print("=== Advanced Graph Memory Integration Example ===\n")
@@ -57,7 +57,7 @@ query_task = Task(
 )
 
 # Run with graph memory integration
-agents_system = AgentTeam(
+agents_system = Agents(
     agents=[knowledge_agent],
     tasks=[build_task, query_task],
     memory=True,

examples/python/memory/advanced-memory-search-optimization.py

@@ -5,7 +5,7 @@ This example demonstrates memory search optimization using PraisonAI's
 built-in memory capabilities with semantic search and quality filtering.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import internet_search
 
 print("=== Advanced Memory Search and Optimization Example ===\n")
@@ -58,7 +58,7 @@ search_task = Task(
 )
 
 # Run with memory optimization
-agents_system = AgentTeam(
+agents_system = Agents(
     agents=[research_agent],
     tasks=[build_memory_task, search_task],
     memory=True,

examples/python/memory/gemini-embedding-example.py

@@ -20,7 +20,7 @@ Prerequisites:
 """
 
 import os
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 def main():
     """Demonstrate Gemini embedding usage"""
@@ -82,7 +82,7 @@ def main():
     
     # Configure with Gemini embeddings
     # Option 1: Using stable text-embedding-004
-    agents = AgentTeam(
+    agents = Agents(
         agents=[researcher, retriever],
         tasks=[store_task, retrieve_task],
         memory={
@@ -97,7 +97,7 @@ def main():
     )
     
     # Alternative: Using experimental model with advanced features
-    # agents = AgentTeam(
+    # agents = Agents(
     #     agents=[researcher, retriever],
     #     tasks=[store_task, retrieve_task],
     #

examples/python/memory/graph-memory-agent.py

@@ -16,7 +16,7 @@ Setup:
 """
 
 import os
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 def main():
     # Example with Neo4j (uncomment and configure as needed)
@@ -149,7 +149,7 @@ def main():
     )
     
     # Run the multi-agent system with graph memory
-    agents_system = AgentTeam(
+    agents_system = Agents(
         agents=[researcher],
         tasks=[build_knowledge_task, query_knowledge_task, expand_knowledge_task],
         memory=True,

examples/python/mongodb/mongodb_comprehensive_example.py

@@ -20,7 +20,7 @@ Features demonstrated:
 """
 
 import os
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import mongodb_tools
 
 # Ensure OpenAI API key is set
@@ -186,7 +186,7 @@ def main():
     print("🚀 Starting Comprehensive MongoDB Business System...")
     print("=" * 60)
     
-    business_system = AgentTeam(
+    business_system = Agents(
         agents=[data_manager, knowledge_curator, business_analyst, customer_service],
         tasks=business_tasks,
         memory=True,

examples/python/mongodb/mongodb_knowledge_example.py

@@ -19,7 +19,7 @@ Features demonstrated:
 """
 
 import os
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 # Ensure OpenAI API key is set
 if not os.environ.get("OPENAI_API_KEY"):
@@ -122,7 +122,7 @@ def main():
     print("🚀 Starting MongoDB Knowledge Management System...")
     print("=" * 60)
     
-    knowledge_system = AgentTeam(
+    knowledge_system = Agents(
         agents=[research_agent, knowledge_agent],
         tasks=knowledge_tasks,
         memory=True, output="verbose"

examples/python/mongodb/mongodb_memory_example.py

@@ -19,7 +19,7 @@ Features demonstrated:
 """
 
 import os
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 
 # Ensure OpenAI API key is set
 if not os.environ.get("OPENAI_API_KEY"):
@@ -90,7 +90,7 @@ def main():
     print("🚀 Starting MongoDB Memory Research System...")
     print("=" * 60)
     
-    research_system = AgentTeam(
+    research_system = Agents(
         agents=[research_agent],
         tasks=research_tasks,
         memory=True,

examples/python/mongodb/mongodb_tools_example.py

@@ -19,7 +19,7 @@ Features demonstrated:
 """
 
 import os
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import mongodb_tools
 
 # Ensure OpenAI API key is set
@@ -111,7 +111,7 @@ def main():
     print("🚀 Starting MongoDB Tools Demo System...")
     print("=" * 60)
     
-    mongodb_system = AgentTeam(
+    mongodb_system = Agents(
         agents=[db_agent, analysis_agent],
         tasks=mongodb_tasks, output="verbose"
     )

examples/python/monitoring/02_multi_agent_workflow_monitoring.py

@@ -10,7 +10,7 @@ Demonstrates performance monitoring in a multi-agent workflow:
 Shows how to monitor complex multi-agent systems.
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.telemetry import (
     monitor_function, track_api_call, get_function_stats, 
     analyze_function_flow, generate_comprehensive_report
@@ -101,7 +101,7 @@ def main():
     with track_api_call("multi_agent_workflow"):
         print("\n🚀 Starting multi-agent workflow...")
         
-        workflow = AgentTeam(
+        workflow = Agents(
             agents=[researcher, analyst, writer],
             tasks=[research_task, analysis_task, report_task], 
             process="sequential", output="verbose"

examples/python/monitoring/07_hierarchical_agents_monitoring.py

@@ -11,7 +11,7 @@ Shows how to monitor complex organizational agent structures.
 """
 
 import time
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.telemetry import (
     monitor_function, track_api_call, get_function_stats,
     visualize_execution_flow, generate_comprehensive_report

examples/python/monitoring/10_comprehensive_dashboard.py

@@ -13,7 +13,7 @@ Shows how to create a comprehensive performance monitoring solution.
 import time
 import json
 from datetime import datetime, timedelta
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.telemetry import (
     monitor_function, track_api_call, performance_monitor,
     get_performance_report, get_function_stats, get_api_stats,
@@ -139,7 +139,7 @@ def simulate_complex_workflow():
     
     # Execute workflow
     with track_api_call("complex_workflow_execution"):
-        workflow = AgentTeam(
+        workflow = Agents(
             agents=[planner, executor, reviewer],
             tasks=[planning_task, execution_task, review_task],
             process="sequential", output="minimal"

examples/python/nested_workflows_example.py

@@ -11,7 +11,7 @@ These patterns enable complex data processing pipelines
 while maintaining clean, readable workflow definitions.
 """
 
-from praisonaiagents import AgentFlow, WorkflowContext, StepResult
+from praisonaiagents import Workflow, WorkflowContext, StepResult
 from praisonaiagents.workflows import loop, parallel, route
 
 
@@ -51,7 +51,7 @@ def nested_loop_example():
         var_name="row"
     )
     
-    workflow = AgentFlow(
+    workflow = Workflow(
         steps=[outer_loop],
         variables={
             "rows": [
@@ -101,7 +101,7 @@ def parallel_inside_loop_example():
     parallel_analysis = parallel([security_scan, performance_test, code_review])
     
     # Loop through projects, running parallel analysis for each
-    workflow = AgentFlow(
+    workflow = Workflow(
         steps=[
             loop(
                 steps=[parallel_analysis],
@@ -161,7 +161,7 @@ def route_inside_loop_example():
         item_type = item.get("type", "unknown")
         return StepResult(output=item_type)
     
-    workflow = AgentFlow(
+    workflow = Workflow(
         steps=[
             loop(
                 steps=[get_type, type_router],
@@ -214,7 +214,7 @@ def three_level_nesting_example():
     # Level 1: Process each department (contains team loop)
     dept_loop = loop(steps=[team_loop], over="departments", var_name="dept")
     
-    workflow = AgentFlow(
+    workflow = Workflow(
         steps=[dept_loop],
         variables={
             "departments": [

examples/python/performance_monitoring_demo.py

@@ -21,7 +21,7 @@ Features Demonstrated:
 
 import time
 import random
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import duckduckgo
 from praisonaiagents.telemetry import (
     monitor_function, track_api_call, performance_monitor,
@@ -213,7 +213,7 @@ def execute_monitored_task(agent, task_description):
         agent=agent
     )
     
-    agents_workflow = AgentTeam(
+    agents_workflow = Agents(
         agents=[agent],
         tasks=[task], output="minimal"
     )

examples/python/processes/advanced-workflow-patterns.py

@@ -12,7 +12,7 @@ Features demonstrated:
 - State-based workflow management
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import duckduckgo
 import random
 
@@ -203,7 +203,7 @@ for request in sample_requests:
     )
     
     # Execute the workflow with conditional routing
-    workflow_agents = AgentTeam(
+    workflow_agents = Agents(
         agents=[
             intake_agent, specialist_agent, review_agent, 
             coordinator_agent

examples/python/processes/hierarchical-process-example.py

@@ -12,7 +12,7 @@ Features demonstrated:
 - Process-level orchestration
 """
 
-from praisonaiagents import Agent, Task, AgentTeam
+from praisonaiagents import Agent, Task, Agents
 from praisonaiagents.tools import duckduckgo
 
 # Create Manager Agent
@@ -83,7 +83,7 @@ coordination_task = Task(
 )
 
 # Create Hierarchical Process
-agents = AgentTeam(
+agents = Agents(
     agents=[manager, researcher, data_analyst, writer],
     tasks=[research_task, analysis_task, writing_task, coordination_task],
     process="hierarchical",  # Hierarchical process type