Release v4.0.0

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>=3.12.3" \
+    "praisonai>=4.0.0" \
     "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>=3.12.3" \
+    "praisonai>=4.0.0" \
     "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>=3.12.3" \
+    "praisonai>=4.0.0" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

examples/consolidated_params/advanced_workflow_full_features.py

@@ -1,6 +1,6 @@
 """Advanced Workflow with all consolidated params configured."""
 from praisonaiagents import Agent
-from praisonaiagents.workflows import Workflow, WorkflowStep
+from praisonaiagents.workflows import Workflow, Task
 from praisonaiagents.workflows.workflow_configs import (
     WorkflowOutputConfig, WorkflowPlanningConfig, WorkflowMemoryConfig,
 )
@@ -10,21 +10,21 @@ workflow = Workflow(
     name="FullFeaturedWorkflow",
     description="Demonstrates all agent-like consolidated params",
     steps=[
-        WorkflowStep(
+        Task(
             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
         ),
-        WorkflowStep(
+        Task(
             name="analyzer",
             action="Analyze the research",
             agent=Agent(instructions="You are an analyst."),
             reflection="thorough",  # Thorough reflection for analysis
             guardrails="strict",  # Strict validation
         ),
-        WorkflowStep(
+        Task(
             name="writer",
             action="Write the final report",
             agent=Agent(instructions="You are a writer."),

examples/consolidated_params/basic_agents.py

@@ -6,7 +6,7 @@ writer = Agent(instructions="You write content.")
 editor = Agent(instructions="You edit content.")
 
 # Multi-agent with consolidated params
-agents = Agents(
+agents = AgentManager(
     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.workflows import Workflow, WorkflowStep
+from praisonaiagents.workflows import Workflow, Task
 
 # Workflow with defaults
 workflow = Workflow(
     name="StepOverrideWorkflow",
     steps=[
-        WorkflowStep(
+        Task(
             name="step1",
             action="Process with workflow defaults",
             agent=Agent(instructions="You are a processor."),
             # Uses workflow-level web=True (inherited)
         ),
-        WorkflowStep(
+        Task(
             name="step2",
             action="Process with step override",
             agent=Agent(instructions="You are a processor."),

examples/consolidated_params/basic_workflow.py

@@ -1,6 +1,6 @@
 """Basic workflow example with consolidated params."""
 from praisonaiagents import Agent
-from praisonaiagents.workflows import Workflow, WorkflowStep
+from praisonaiagents.workflows import Workflow, Task
 
 # Create agents
 writer = Agent(instructions="You are a content writer.")
@@ -10,8 +10,8 @@ editor = Agent(instructions="You are an editor.")
 workflow = Workflow(
     name="Content Pipeline",
     steps=[
-        WorkflowStep(name="write", agent=writer, action="Write about {{topic}}"),
-        WorkflowStep(name="edit", agent=editor, action="Edit the content", context=["write"]),
+        Task(name="write", agent=writer, action="Write about {{topic}}"),
+        Task(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.workflows import Workflow, WorkflowStep
+from praisonaiagents.workflows import Workflow, Task
 
 # Workflow with agent-like params (knowledge, web, guardrails, reflection)
 workflow = Workflow(
     name="AgentLikeWorkflow",
     steps=[
-        WorkflowStep(
+        Task(
             name="researcher",
             action="Research the topic: {{input}}",
             agent=Agent(instructions="You are a researcher."),
         ),
-        WorkflowStep(
+        Task(
             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 Agents")
-    print("    agents = Agents(agents=[...], context=True)")
+    print("    from praisonaiagents import AgentManager")
+    print("    agents = AgentManager(agents=[...], context=True)")
     print("")
     print("Recommended config for long tasks:")
     print("    context=ManagerConfig(")

examples/context/12_multi_agent_context.py

@@ -9,7 +9,7 @@ Agent-Centric Quick Start:
     from praisonaiagents import Agent, Agents
     from praisonaiagents.context import ManagerConfig
     
-    agents = Agents(
+    agents = AgentManager(
         agents=[agent1, agent2],
         context=ManagerConfig(policy="isolated"),  # or "shared"
     )
@@ -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 Agents(agents=[...], context=ManagerConfig(policy='isolated'))")
+    print("Use AgentManager(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 Agents, Task
+    from praisonaiagents import AgentManager, 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 = Agents(
+    agents = AgentManager(
         agents=[researcher, writer],
         tasks=[task1, task2],
         context=config,  # Shared context config

examples/guardrail_example_fixed.py

@@ -103,7 +103,7 @@ task_with_llm_guardrail = Task(
 
 # Run with GuardrailResult example
 print("=== Running with GuardrailResult guardrail ===")
-agents_gr = Agents(
+agents_gr = AgentManager(
     agents=[agent],
     tasks=[task_with_guardrailresult]
 )
@@ -113,7 +113,7 @@ agents_gr = Agents(
 
 # Run with Tuple example
 print("\n=== Running with Tuple[bool, Any] guardrail ===")
-agents_tuple = Agents(
+agents_tuple = AgentManager(
     agents=[agent],
     tasks=[task_with_tuple]
 )
@@ -123,7 +123,7 @@ agents_tuple = Agents(
 
 # Run with LLM guardrail example
 print("\n=== Running with LLM-based guardrail ===")
-agents_llm = Agents(
+agents_llm = AgentManager(
     agents=[agent],
     tasks=[task_with_llm_guardrail]
 )

examples/output_ux/basic_output_example.py

@@ -106,7 +106,7 @@ def example_multi_agent():
         agent=writer
     )
     
-    agents = Agents(
+    agents = AgentManager(
         agents=[researcher, writer],
         tasks=[task1, task2],
         process="sequential",

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

@@ -54,7 +54,7 @@ execution_task = Task(
 )
 
 # Run hierarchical workflow
-agents_system = Agents(
+agents_system = AgentManager(
     agents=[manager_agent, research_agent],
     tasks=[planning_task, execution_task],
     process="sequential", output="verbose"

examples/python/agents/code-agent.py

@@ -84,7 +84,7 @@ def demonstrate_code_agent():
     )
     
     # Create workflow
-    workflow = Agents(
+    workflow = AgentManager(
         agents=[code_writer, code_reviewer, code_executor],
         tasks=[write_task, review_task, execute_task],
         process="sequential", output="verbose"

examples/python/agents/image-agent.py

@@ -36,7 +36,7 @@ task2 = Task(
 )
 
 # Create Agents instance
-agents = Agents(
+agents = AgentManager(
     agents=[image_agent],
     tasks=[task1, task2],
     process="sequential",

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

@@ -36,7 +36,7 @@ task2 = Task(
 )
 
 # Create Agents instance
-agents = Agents(
+agents = AgentManager(
     agents=[image_agent],
     tasks=[task1, task2],
     process="sequential",

examples/python/agents/math-agent.py

@@ -123,7 +123,7 @@ def solve_math_problem_workflow():
         context=[solve_task]
     )
     
-    workflow = Agents(
+    workflow = AgentManager(
         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

@@ -48,7 +48,7 @@ def example_auto_routing():
     )
     
     # Run the tasks
-    agents = Agents(
+    agents = AgentManager(
         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 = Agents(
+    workflow = AgentManager(
         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 = AutoAgents(
+    auto_agents = AutoAgentManager(
         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 = Agents(
+    agents = AgentManager(
         agents=[coder],
         tasks=tasks,
         process="sequential", output="verbose"

examples/python/agents/video-agent.py

@@ -25,7 +25,7 @@ task1 = Task(
 )
 
 # Create Agents instance
-agents = Agents(
+agents = AgentManager(
     agents=[video_agent],
     tasks=[task1],
     process="sequential",

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

@@ -2,5 +2,5 @@ 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 = Agents(agents=[research_agent, summarise_agent])
+agents = AgentManager(agents=[research_agent, summarise_agent])
 agents.launch(path="/agents", port=3030)

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

@@ -2,7 +2,7 @@ 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 = Agents(agents=[research_agent, summarise_agent])
-agents2 = Agents(agents=[research_agent])
+agents = AgentManager(agents=[research_agent, summarise_agent])
+agents2 = AgentManager(agents=[research_agent])
 agents.launch(path="/agents", port=3030)
 agents2.launch(path="/agents2", port=3030)

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

@@ -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 = Agents(
+        workflow = AgentManager(
             agents=list(agents.values()),
             tasks=tasks,
             process="sequential", output="minimal"

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

@@ -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 = Agents(name="MultiAgents", agents=[agent, agent2])
+agents = AgentManager(name="MultiAgents", agents=[agent, agent2])
 agents.launch(port=8080, protocol="mcp")

examples/python/camera/camera-basic.py

@@ -58,7 +58,7 @@ def capture_and_analyze():
             )
             
             # Run analysis
-            agents = Agents(
+            agents = AgentManager(
                 agents=[vision_agent],
                 tasks=[task],
                 process="sequential",

examples/python/camera/camera-continuous.py

@@ -71,7 +71,7 @@ class ContinuousCameraMonitor:
             images=[image_path]
         )
         
-        agents = Agents(
+        agents = AgentManager(
             agents=[self.vision_agent],
             tasks=[task],
             process="sequential",

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

@@ -114,7 +114,7 @@ def analyze_with_multiple_agents():
     )
     
     # Run multi-agent analysis
-    agents = Agents(
+    agents = AgentManager(
         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

@@ -131,7 +131,7 @@ class CameraVideoAnalyzer:
             images=[video_path]  # PraisonAI supports video files in images parameter
         )
         
-        agents = Agents(
+        agents = AgentManager(
             agents=[self.video_agent],
             tasks=[task],
             process="sequential",

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

@@ -302,7 +302,7 @@ class ContextEngineeringWorkflow:
         print("\n⚙️ Executing Context Engineering Workflow")
         print("-" * 50)
         
-        agents_workflow = Agents(
+        agents_workflow = AgentManager(
             agents=[
                 self.product_manager,
                 self.architect, 

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

@@ -81,7 +81,7 @@ def method_1_simple_loop():
     )
     
     # Initialize the agents system
-    agents = Agents(
+    agents = AgentManager(
         agents=[loop_agent],
         tasks=[loop_task],
         process="workflow",
@@ -145,7 +145,7 @@ def method_2_manual_csv():
     )
     
     # Initialize and run
-    agents = Agents(
+    agents = AgentManager(
         agents=[csv_agent],
         tasks=[csv_task],
         process="sequential"
@@ -211,7 +211,7 @@ def method_3_url_processing():
     )
     
     # Initialize and run
-    agents = Agents(
+    agents = AgentManager(
         agents=[url_agent],
         tasks=[url_task],
         process="sequential"
@@ -319,7 +319,7 @@ def method_4_advanced_processing():
     )
     
     # Initialize and run with sequential processing
-    agents = Agents(
+    agents = AgentManager(
         agents=[validator_agent, processor_agent],
         tasks=[validation_task, processing_task],
         process="sequential"  # Validation must complete before processing

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

@@ -35,7 +35,7 @@ knowledge_task = Task(
 )
 
 # Create and start the agents
-agents = Agents(
+agents = AgentManager(
     agents=[knowledge_agent],
     tasks=[knowledge_task],
     process="sequential",

examples/python/concepts/rag-agents.py

@@ -29,7 +29,7 @@ rag_task = Task(
 )
 
 # Build Agents
-agents = Agents(
+agents = AgentManager(
     agents=[rag_agent],
     tasks=[rag_task],
     user_id="user1"

examples/python/concepts/reasoning-extraction.py

@@ -100,7 +100,7 @@ def demonstrate_reasoning_extraction():
         context=[problem_task]
     )
     
-    workflow = Agents(
+    workflow = AgentManager(
         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 = Agents(
+    workflow = AgentManager(
         agents=[cot_agent, reasoning_validator],
         tasks=[deductive_task, inductive_task, abductive_task, validation_task],
         process="sequential", output="verbose"

examples/python/concepts/repetitive-agents.py

@@ -12,7 +12,7 @@ task = Task(
     input_file="tasks.csv"
 )
 
-agents = Agents(
+agents = AgentManager(
     agents=[agent],
     tasks=[task],
     process="workflow",

examples/python/concepts/routing-patterns.py

@@ -77,7 +77,7 @@ def conditional_routing_example():
         agent=processor_agent
     )
     
-    workflow = Agents(
+    workflow = AgentManager(
         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 = Agents(
+    workflow = AgentManager(
         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 = Agents(
+    workflow = AgentManager(
         agents=[analyzer_agent, processor_agent],
         tasks=all_tasks,
         process="workflow", output="verbose"
@@ -269,7 +269,7 @@ def dynamic_routing_example():
         agent=processor_agent
     )
     
-    workflow = Agents(
+    workflow = AgentManager(
         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

@@ -162,7 +162,7 @@ def reflection_workflow_example():
         context=[create_task, review_task]
     )
     
-    workflow = Agents(
+    workflow = AgentManager(
         agents=[creator_agent, reviewer_agent, polisher_agent],
         tasks=[create_task, review_task, polish_task],
         process="sequential", output="verbose"

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

@@ -59,7 +59,7 @@ def main():
     )
     
     # Step 4: Run the agents
-    agents = Agents(
+    agents = AgentManager(
         agents=[url_agent],
         tasks=[url_task],
         process="workflow",

examples/python/data/cot-agents.py

@@ -128,7 +128,7 @@ upload_to_huggingface_task = Task(
 )
 
 # Initialize workflow
-agents = Agents(
+agents = AgentManager(
     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/general/async_example.py

@@ -156,7 +156,7 @@ workflow_async_task = Task(
 def run_sync_example():
     """Run synchronous example"""
     display_instruction("\nRunning Synchronous Example...", console)
-    agents = Agents(
+    agents = AgentManager(
         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 = Agents(
+    agents = AgentManager(
         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 = Agents(
+    agents = AgentManager(
         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 = Agents(
+    agents = AgentManager(
         agents=[sync_agent, async_agent],
         tasks=[workflow_sync_task, workflow_async_task],
         process="workflow"

examples/python/general/async_example_full.py

@@ -111,7 +111,7 @@ async def run_parallel_tasks():
     )
     
     # Create a single Agents instance with both agents
-    agents = Agents(
+    agents = AgentManager(
         agents=[async_agent, summary_agent],
         tasks=parallel_tasks + [summary_task],
         process="sequential"

examples/python/general/async_example_full_multigroups.py

@@ -99,7 +99,7 @@ async_task = Task(
 async def run_single_task():
     """Run single async task"""
     print("\nRunning Single Async Task...")
-    agents = Agents(
+    agents = AgentManager(
         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 = Agents(
+    agents = AgentManager(
         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 = Agents(
+    summary_agents = AgentManager(
         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 = AutoAgents(
+agents = AutoAgentManager(
     instructions="Search for information about AI Agents",
     tools=[duckduckgo],
     process="sequential",  # or "hierarchical"

examples/python/general/autonomous-agent.py

@@ -86,7 +86,7 @@ feedback_task = Task(
 )
 
 # Create workflow manager
-workflow = Agents(
+workflow = AgentManager(
     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

@@ -46,5 +46,5 @@ execution_agent_task = Task(
     agent=execution_agent
 )
 
-agents = Agents(agents=[code_agent, execution_agent], tasks=[code_agent_task, execution_agent_task])
+agents = AgentManager(agents=[code_agent, execution_agent], tasks=[code_agent_task, execution_agent_task])
 agents.start()

examples/python/general/evaluator-optimiser.py

@@ -53,7 +53,7 @@ evaluate_task = Task(
 )
 
 # Create workflow manager
-workflow = Agents(
+workflow = AgentManager(
     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 = Agents(
+    agents = AgentManager(
         agents=[researcher, writer],
         tasks=[task1, task2, task3, task4],
         process="sequential",

examples/python/general/example_custom_tools.py

@@ -141,7 +141,7 @@ validate_task = Task(
 )
 
 # 4. Workflow
-agents = Agents(
+agents = AgentManager(
     agents=[data_agent],
     tasks=[collect_task, validate_task],
     process="workflow"

examples/python/general/example_sequential.py

@@ -92,7 +92,7 @@ task4 = Task(
 )
 
 # Create and run agents manager
-agents = Agents(
+agents = AgentManager(
     agents=[researcher, writer],
     tasks=[task1, task2, task3, task4],
     output="minimal",

examples/python/general/human_approval_example.py

@@ -109,7 +109,7 @@ def main():
     ]
     
     # Create and run process
-    process = Agents(
+    process = AgentManager(
         agents=[agent],
         tasks=tasks, output="verbose"
     )
@@ -166,7 +166,7 @@ async def async_demo():
         expected_output="Async execution result"
     )
     
-    process = Agents(
+    process = AgentManager(
         agents=[agent],
         tasks=[task], output="verbose"
     )

examples/python/general/langchain_example.py

@@ -21,7 +21,7 @@ task = Task(
 )
 
 # Create and start the workflow
-agents = Agents(
+agents = AgentManager(
     agents=[agent],
     tasks=[task], output="verbose"
 )

examples/python/general/memory_example.py

@@ -101,7 +101,7 @@ def main():
     )
 
     # Initialize Agents with memory configuration
-    agents = Agents(
+    agents = AgentManager(
         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 = Agents(
+    # agents = AgentManager(
     #     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 = Agents(
+agents = AgentManager(
     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

@@ -2,5 +2,5 @@ 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 = Agents(agents=[research_agent, summarise_agent])
+agents = AgentManager(agents=[research_agent, summarise_agent])
 agents.start()

examples/python/general/multimodal.py

@@ -43,7 +43,7 @@ task3 = Task(
 )
 
 # Create Agents instance
-agents = Agents(
+agents = AgentManager(
     agents=[vision_agent],
     tasks=[task1, task2, task3],
     process="sequential"

examples/python/general/orchestrator-workers.py

@@ -93,7 +93,7 @@ synthesize_task = Task(
 )
 
 # Create workflow manager
-workflow = Agents(
+workflow = AgentManager(
     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

@@ -75,7 +75,7 @@ aggregate_task = Task(
 async def main():
 
     # Create workflow manager
-    workflow = Agents(
+    workflow = AgentManager(
         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 = Agents(
+workflow = AgentManager(
     agents=[agent1, agent2, agent3],
     tasks=[initial_task, analysis_task, final_task],
     process="workflow",  # Use workflow process type

examples/python/general/structured_agents_example.py

@@ -44,7 +44,7 @@ analysis_task = Task(
 )
 
 # Initialize and run agents
-agents = Agents(
+agents = AgentManager(
     agents=[researcher, analyst],
     tasks=[research_task, analysis_task],
     process="sequential",

examples/python/general/tools-class.py

@@ -106,7 +106,7 @@ task = Task(
 )
 
 # Create and start the workflow
-agents = Agents(
+agents = AgentManager(
     agents=[agent],
     tasks=[task], output="verbose"
 )

examples/python/general/tools_example.py

@@ -22,7 +22,7 @@ news_task = Task(
 
 
 # Run agent
-agents = Agents(
+agents = AgentManager(
     agents=[news_agent],
     tasks=[news_task],
     process="sequential"

examples/python/general/workflow_example_basic.py

@@ -64,7 +64,7 @@ validate_task = Task(
 )
 
 # 4. AI Agents Workflow
-agents = Agents(
+agents = AgentManager(
     agents=[data_agent],
     tasks=[collect_task, validate_task],
     process="workflow"

examples/python/general/workflow_example_detailed.py

@@ -225,7 +225,7 @@ process_task = Task(
 )
 
 # Create Agents instance with workflow process
-workflow = Agents(
+workflow = AgentManager(
     agents=[data_agent, process_agent],
     tasks=[collect_task, validate_task, process_task],
     process="workflow"

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

@@ -181,7 +181,7 @@ llm_guardrail_task = Task(
 )
 
 # Execute tasks with guardrails
-agents = Agents(
+agents = AgentManager(
     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/input/advanced_dynamic_input.py

@@ -137,7 +137,7 @@ class DynamicAgentSystem:
         
         # Run the system
         print(f"\n🚀 Starting {process} analysis for '{inputs['topic']}'...")
-        praison_agents = Agents(
+        praison_agents = AgentManager(
             agents=agents,
             tasks=tasks,
             process=process,

examples/python/input/environment_variable_input.py

@@ -46,7 +46,7 @@ print(f"  - Max Retries: {max_retries}")
 print("\n" + "="*50 + "\n")
 
 # Run agents
-agents = Agents(agents=[agent], tasks=[task])
+agents = AgentManager(agents=[agent], tasks=[task])
 result = agents.start()
 
 # Save to environment-specified location if provided

examples/python/input/medium_complexity_input.py

@@ -47,7 +47,7 @@ analyze_task = Task(
 )
 
 # Run sequential process
-agents = Agents(
+agents = AgentManager(
     agents=[search_agent, analysis_agent],
     tasks=[search_task, analyze_task],
     process="sequential"

examples/python/input/simple_input.py

@@ -26,5 +26,5 @@ task = Task(
 )
 
 # Run
-agents = Agents(agents=[agent], tasks=[task])
+agents = AgentManager(agents=[agent], tasks=[task])
 agents.start()

examples/python/input/streamlit_ui_input.py

@@ -125,7 +125,7 @@ if st.button("🚀 Submit", type="primary", use_container_width=True):
                     )
                     
                     # Run agents
-                    agents = Agents(
+                    agents = AgentManager(
                         agents=[agent],
                         tasks=[task],
                         process=process_type

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

@@ -12,6 +12,6 @@ whatsapp_agent = Agent(
     tools=MCP("python /Users/praison/whatsapp-mcp/whatsapp-mcp-server/main.py")
 )
 
-agents = Agents(agents=[airbnb_agent, whatsapp_agent])
+agents = AgentManager(agents=[airbnb_agent, whatsapp_agent])
 
 agents.start()

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

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

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

@@ -57,7 +57,7 @@ query_task = Task(
 )
 
 # Run with graph memory integration
-agents_system = Agents(
+agents_system = AgentManager(
     agents=[knowledge_agent],
     tasks=[build_task, query_task],
     memory=True,

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

@@ -58,7 +58,7 @@ search_task = Task(
 )
 
 # Run with memory optimization
-agents_system = Agents(
+agents_system = AgentManager(
     agents=[research_agent],
     tasks=[build_memory_task, search_task],
     memory=True,

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

@@ -82,7 +82,7 @@ def main():
     
     # Configure with Gemini embeddings
     # Option 1: Using stable text-embedding-004
-    agents = Agents(
+    agents = AgentManager(
         agents=[researcher, retriever],
         tasks=[store_task, retrieve_task],
         memory={
@@ -97,7 +97,7 @@ def main():
     )
     
     # Alternative: Using experimental model with advanced features
-    # agents = Agents(
+    # agents = AgentManager(
     #     agents=[researcher, retriever],
     #     tasks=[store_task, retrieve_task],
     #

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

@@ -149,7 +149,7 @@ def main():
     )
     
     # Run the multi-agent system with graph memory
-    agents_system = Agents(
+    agents_system = AgentManager(
         agents=[researcher],
         tasks=[build_knowledge_task, query_knowledge_task, expand_knowledge_task],
         memory=True,

examples/python/mongodb/mongodb_comprehensive_example.py

@@ -186,7 +186,7 @@ def main():
     print("🚀 Starting Comprehensive MongoDB Business System...")
     print("=" * 60)
     
-    business_system = Agents(
+    business_system = AgentManager(
         agents=[data_manager, knowledge_curator, business_analyst, customer_service],
         tasks=business_tasks,
         memory=True,

examples/python/mongodb/mongodb_knowledge_example.py

@@ -122,7 +122,7 @@ def main():
     print("🚀 Starting MongoDB Knowledge Management System...")
     print("=" * 60)
     
-    knowledge_system = Agents(
+    knowledge_system = AgentManager(
         agents=[research_agent, knowledge_agent],
         tasks=knowledge_tasks,
         memory=True, output="verbose"

examples/python/mongodb/mongodb_memory_example.py

@@ -90,7 +90,7 @@ def main():
     print("🚀 Starting MongoDB Memory Research System...")
     print("=" * 60)
     
-    research_system = Agents(
+    research_system = AgentManager(
         agents=[research_agent],
         tasks=research_tasks,
         memory=True,

examples/python/mongodb/mongodb_tools_example.py

@@ -111,7 +111,7 @@ def main():
     print("🚀 Starting MongoDB Tools Demo System...")
     print("=" * 60)
     
-    mongodb_system = Agents(
+    mongodb_system = AgentManager(
         agents=[db_agent, analysis_agent],
         tasks=mongodb_tasks, output="verbose"
     )

examples/python/monitoring/02_multi_agent_workflow_monitoring.py

@@ -101,7 +101,7 @@ def main():
     with track_api_call("multi_agent_workflow"):
         print("\n🚀 Starting multi-agent workflow...")
         
-        workflow = Agents(
+        workflow = AgentManager(
             agents=[researcher, analyst, writer],
             tasks=[research_task, analysis_task, report_task], 
             process="sequential", output="verbose"

examples/python/monitoring/10_comprehensive_dashboard.py

@@ -139,7 +139,7 @@ def simulate_complex_workflow():
     
     # Execute workflow
     with track_api_call("complex_workflow_execution"):
-        workflow = Agents(
+        workflow = AgentManager(
             agents=[planner, executor, reviewer],
             tasks=[planning_task, execution_task, review_task],
             process="sequential", output="minimal"

examples/python/performance_monitoring_demo.py

@@ -213,7 +213,7 @@ def execute_monitored_task(agent, task_description):
         agent=agent
     )
     
-    agents_workflow = Agents(
+    agents_workflow = AgentManager(
         agents=[agent],
         tasks=[task], output="minimal"
     )

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

@@ -203,7 +203,7 @@ for request in sample_requests:
     )
     
     # Execute the workflow with conditional routing
-    workflow_agents = Agents(
+    workflow_agents = AgentManager(
         agents=[
             intake_agent, specialist_agent, review_agent, 
             coordinator_agent

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

@@ -83,7 +83,7 @@ coordination_task = Task(
 )
 
 # Create Hierarchical Process
-agents = Agents(
+agents = AgentManager(
     agents=[manager, researcher, data_analyst, writer],
     tasks=[research_task, analysis_task, writing_task, coordination_task],
     process="hierarchical",  # Hierarchical process type

examples/python/save_output/02_task_output_file.py

@@ -23,7 +23,7 @@ task = Task(
 )
 
 # Run
-agents = Agents(agents=[writer], tasks=[task])
+agents = AgentManager(agents=[writer], tasks=[task])
 result = agents.start()
 
 print("✅ Task completed!")

examples/python/sessions/comprehensive-session-management.py

@@ -62,7 +62,7 @@ research_task1 = Task(
 )
 
 # Create agents with session
-agents_session1 = Agents(
+agents_session1 = AgentManager(
     agents=[research_agent],
     tasks=[research_task1],
     session=session1, output="verbose"
@@ -101,7 +101,7 @@ analysis_task = Task(
     context_variables={"previous_research": str(result1)}
 )
 
-agents_session2 = Agents(
+agents_session2 = AgentManager(
     agents=[analysis_agent],
     tasks=[analysis_task], 
     session=session2, output="verbose"
@@ -151,7 +151,7 @@ synthesis_task = Task(
     }
 )
 
-agents_recovery = Agents(
+agents_recovery = AgentManager(
     agents=[synthesis_agent],
     tasks=[synthesis_task],
     session=recovery_session, output="verbose"
@@ -201,7 +201,7 @@ review_task = Task(
     }
 )
 
-agents_reviewer = Agents(
+agents_reviewer = AgentManager(
     agents=[review_agent],
     tasks=[review_task],
     session=reviewer_session, output="verbose"

examples/python/stateful/01_basic_state_management.py

@@ -144,7 +144,7 @@ task4 = Task(
 )
 
 # Create workflow (global variable for state access in tools)
-workflow = Agents(
+workflow = AgentManager(
     agents=[project_manager, developer, finance_manager],
     tasks=[task1, task2, task3, task4],
     process="sequential"

examples/python/stateful/02_state_in_tool_functions.py

@@ -265,7 +265,7 @@ task6 = Task(
 )
 
 # Create workflow (global variable for state access in tools)
-workflow = Agents(
+workflow = AgentManager(
     agents=[progress_tracker, data_processor, error_handler, config_manager],
     tasks=[task1, task2, task3, task4, task5, task6],
     process="sequential"

examples/python/stateful/03_conditional_task_execution.py

@@ -366,7 +366,7 @@ report_task = Task(
 )
 
 # Create workflow
-workflow = Agents(
+workflow = AgentManager(
     agents=[finance_agent, cost_manager, development_agent, performance_agent, report_agent],
     tasks=[
         budget_decision_task,

examples/python/stateful/04_session_state_persistence.py

@@ -228,7 +228,7 @@ initial_tasks = [
 ]
 
 # Create workflow with memory enabled
-workflow = Agents(
+workflow = AgentManager(
     agents=[data_processor, status_monitor, task_runner, report_generator],
     tasks=initial_tasks,
     process="sequential",
@@ -300,7 +300,7 @@ resumed_tasks = [
 ]
 
 # Create new workflow instance for resumed session
-resumed_workflow = Agents(
+resumed_workflow = AgentManager(
     agents=[data_processor, status_monitor, task_runner, report_generator],
     tasks=resumed_tasks,
     process="sequential",

examples/python/stateful/05_loop_control_with_state.py

@@ -355,7 +355,7 @@ report_task = Task(
 )
 
 # Create workflow
-workflow = Agents(
+workflow = AgentManager(
     agents=[batch_processor, data_collector, validator, reporter],
     tasks=[batch_loop_task, retry_loop_task, pagination_loop_task, validation_loop_task, report_task],
     process="sequential"

examples/python/stateful/06_advanced_state_operations.py

@@ -540,7 +540,7 @@ tasks = [
 ]
 
 # Create workflow
-workflow = Agents(
+workflow = AgentManager(
     agents=[state_manager, cache_manager, metrics_calculator, report_generator],
     tasks=tasks,
     process="sequential"

examples/python/stateful/advanced-state-management-patterns.py

@@ -63,7 +63,7 @@ finalize_task = Task(
 )
 
 # Run with state management
-agents_system = Agents(
+agents_system = AgentManager(
     agents=[state_agent],
     tasks=[init_task, continue_task, finalize_task],
     memory=True, output="verbose"

examples/python/stateful/workflow-state-example.py

@@ -6,7 +6,7 @@ Demonstrates advanced state management in multi-agent workflows with
 persistence, conditional execution, and cross-task communication.
 """
 
-from praisonaiagents import Agents, Agent, Task
+from praisonaiagents import AgentManager, Agent, Task
 
 def research_tool(topic: str, num_sources: int = 5):
     """Simulated research tool that updates workflow state"""
@@ -85,7 +85,7 @@ def main():
     )
     
     # Create stateful workflow
-    workflow = Agents(
+    workflow = AgentManager(
         agents=[researcher, analyzer, writer],
         tasks=[research_task, analysis_task, report_task],
         memory=True,

examples/python/tasks/advanced-task-management.py

@@ -195,7 +195,7 @@ final_report = Task(
 )
 
 # Create workflow with conditional execution
-workflow = Agents(
+workflow = AgentManager(
     agents=[research_agent, quality_checker, analyst, decision_maker, report_writer],
     tasks=[
         initial_research, 

examples/python/telemetry/production-telemetry-example.py

@@ -139,7 +139,7 @@ for i, request in enumerate(customer_requests):
         try:
             # Customer service response
             with telemetry.trace_agent_execution("CustomerServiceAgent") as agent_trace:
-                agents = Agents(
+                agents = AgentManager(
                     agents=[customer_service_agent],
                     tasks=[customer_task],
                     output="minimal"  # Reduce verbosity for telemetry demo
@@ -162,7 +162,7 @@ for i, request in enumerate(customer_requests):
                         context=[customer_task]
                     )
                     
-                    tech_agents = Agents(
+                    tech_agents = AgentManager(
                         agents=[technical_support_agent],
                         tasks=[tech_task], output="minimal"
                     )
@@ -182,7 +182,7 @@ for i, request in enumerate(customer_requests):
                     agent=quality_assurance_agent
                 )
                 
-                qa_agents = Agents(
+                qa_agents = AgentManager(
                     agents=[quality_assurance_agent],
                     tasks=[qa_task], output="minimal"
                 )

examples/python/token-metrics/01_basic_token_tracking.py

@@ -4,7 +4,7 @@ This example demonstrates the simplest way to enable token metrics
 tracking using just Agent(metrics=True). The token usage summary 
 will be automatically displayed when tasks complete!
 """
-from praisonaiagents import Agents, Agent, Task
+from praisonaiagents import AgentManager, Agent, Task
 
 def main():
     # Create a simple agent with metrics=True - that's it!
@@ -25,7 +25,7 @@ def main():
     )
     
     # Initialize the agents system
-    agents = Agents(
+    agents = AgentManager(
         agents=[research_agent],
         tasks=[research_task], output="verbose"
     )

examples/python/token-metrics/02_session_metrics.py

@@ -4,7 +4,7 @@ This example shows how to track token usage across multiple agents
 with the simplified Agent(metrics=True) approach. Metrics are 
 automatically displayed when any agent has metrics enabled!
 """
-from praisonaiagents import Agents, Agent, Task
+from praisonaiagents import AgentManager, Agent, Task
 
 def main():
     # Create multiple agents - just add metrics=True to enable tracking
@@ -41,7 +41,7 @@ def main():
     )
     
     # Initialize the agents system
-    agents = Agents(
+    agents = AgentManager(
         agents=[analyst_agent, writer_agent],
         tasks=[analysis_task, writing_task], output="verbose"
     )

examples/python/token-metrics/03_cost_estimation.py

@@ -4,7 +4,7 @@ This example demonstrates automatic token metrics and cost tracking
 using just Agent(metrics=True). All tracking and display is automatic!
 For custom cost calculations, you can still access the detailed reports.
 """
-from praisonaiagents import Agents, Agent, Task
+from praisonaiagents import AgentManager, Agent, Task
 
 def main():
     # Create agents with metrics=True for automatic cost tracking
@@ -56,7 +56,7 @@ def main():
     )
     
     # Initialize and run
-    agents = Agents(
+    agents = AgentManager(
         agents=[research_agent, strategy_agent],
         tasks=[research_task, strategy_task], output="verbose"
     )

examples/python/token-metrics/04_telemetry_integration.py

@@ -6,7 +6,7 @@ telemetry system for comprehensive monitoring and analytics.
 Demonstrates privacy-first tracking and export capabilities.
 """
 
-from praisonaiagents import Agents, Agent, Task
+from praisonaiagents import AgentManager, Agent, Task
 import json
 
 def export_metrics_to_file(agents, filename="token_metrics_export.json"):
@@ -126,7 +126,7 @@ def main():
     )
     
     # Initialize with telemetry awareness
-    agents = Agents(
+    agents = AgentManager(
         agents=[data_agent, monitor_agent],
         tasks=[processing_task, monitoring_task], output="verbose"
     )

examples/python/token-metrics/05_advanced_agent_integration.py

@@ -8,7 +8,7 @@ This example demonstrates advanced token tracking features including:
 - Token budget enforcement
 """
 
-from praisonaiagents import Agents, Agent, Task
+from praisonaiagents import AgentManager, Agent, Task
 import time
 
 class TokenBudgetManager:
@@ -197,7 +197,7 @@ def main():
     )
     
     # Initialize agents system
-    agents = Agents(
+    agents = AgentManager(
         agents=[researcher_agent, summarizer_agent, optimizer_agent],
         tasks=[research_task, summary_task, optimization_task], output="verbose"
     )