Skip to main content

​
AgentTeam

Defined in the agents module.
AI Agent Multi-agent coordinator that manages and delegates work to multiple agents. AgentTeam orchestrates the execution of tasks across multiple Agent instances, supporting sequential, parallel, and hierarchical execution patterns.

​
Constructor

​
agents
Any
required
No description available.
​
tasks
Any
No description available.
​
process
Any
default:"'sequential'"
No description available.
​
manager_llm
Any
No description available.
​
name
Optional
No description available.
​
variables
Optional
No description available.
​
llm
Optional
No description available.
​
memory
Optional
default:"False"
No description available.
​
planning
Optional
default:"False"
No description available.
​
context
Optional
default:"False"
No description available.
​
output
Optional
No description available.
​
execution
Optional
No description available.
​
hooks
Optional
No description available.
​
autonomy
Optional
No description available.
​
knowledge
Optional
No description available.
​
guardrails
Optional
No description available.
​
web
Optional
No description available.
​
reflection
Optional
No description available.
​
caching
Optional
No description available.

​
Methods

add_task()

Instance method.

clean_json_output()

Instance method.

context_manager()

ContextManager instance for unified context management across all agents.

default_completion_checker()

Instance method.

aexecute_task()

Async version of execute_task method

arun_task()

Async version of run_task method

arun_all_tasks()

Async version of run_all_tasks method

astart()

Async version of start method.

save_output_to_file()

Instance method.

execute_task()

Synchronous version of execute_task method

run_task()

Synchronous version of run_task method

run_all_tasks()

Synchronous version of run_all_tasks method

get_task_status()

Instance method.

get_all_tasks_status()

Instance method.

get_task_result()

Instance method.

get_task_details()

Instance method.

get_agent_details()

Instance method.

start()

Start agent execution with verbose output (beginner-friendly).

run()

Run agents silently (production use).

set_state()

Set a state value

get_state()

Get a state value

update_state()

Update multiple state values

clear_state()

Clear all state values

has_state()

Check if a state key exists

get_all_state()

Get a copy of the entire state dictionary

delete_state()

Delete a state key if it exists. Returns True if deleted, False if key didn’t exist.

increment_state()

Increment a numeric state value. Creates the key with default if it doesn’t exist.

append_to_state()

Append a value to a list state. Creates the list if it doesn’t exist.

save_session_state()

Save current state to memory for session persistence

restore_session_state()

Restore state from memory for session persistence. Returns True if restored.

get_token_usage_summary()

Get a summary of token usage across all agents and tasks.

get_detailed_token_report()

Get a detailed token usage report.

display_token_usage()

Display token usage in a formatted table.

launch()

Launch all agents as a single API endpoint (HTTP) or an MCP server.

current_plan()

Get the current plan.

todo_list()

Get the current todo list.

get_plan_markdown()

Get the current plan as markdown.

get_todo_markdown()

Get the current todo list as markdown.

update_plan_step_status()

Update the status of a plan step.

​
Usage

from praisonaiagents import Agent, AgentTeam, Task
    
    researcher = Agent(role="Researcher", instructions="Research topics")
    writer = Agent(role="Writer", instructions="Write content")
    
    task1 = Task(description="Research AI trends", agent=researcher)
    task2 = Task(description="Write article", agent=writer)
    
    team = AgentTeam(
        agents=[researcher, writer],
        tasks=[task1, task2],
        process="sequential"
    )
    result = team.start()

​
Notes

The class was renamed from AgentManager to AgentTeam in v1.0. AgentManager and Agents remain as silent aliases for backward compatibility.

​
Source

View on GitHub

praisonaiagents/agents/agents.py at line 172

Agents Concept

Single Agent Guide

Multi-Agent Guide

Agent Configuration

Auto Agents