> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Agent Team • AI Agent SDK
> AgentTeam: Multi-agent coordinator that manages and delegates work to multiple agents.
# AgentTeam
> Defined in the [**agents**](../modules/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.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
%%{init: {'theme': 'base', 'themeVariables': { 'primaryColor': '#8B0000', 'primaryTextColor': '#fff', 'primaryBorderColor': '#710101', 'lineColor': '#189AB4', 'secondaryColor': '#189AB4', 'tertiaryColor': '#fff' }}}%%
graph LR
input["Input Data"] --> agent["Agent: AgentTeam"]
agent --> output["Output Result"]
style agent fill:#8B0000,color:#fff
style input fill:#8B0000,color:#fff
style output fill:#8B0000,color:#fff
```
## Constructor
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
## Methods
Instance method.
Instance method.
ContextManager instance for unified context management across all agents.
Instance method.
Async version of execute\_task method
Async version of run\_task method
Async version of run\_all\_tasks method
Async version of start method.
Instance method.
Synchronous version of execute\_task method
Synchronous version of run\_task method
Synchronous version of run\_all\_tasks method
Instance method.
Instance method.
Instance method.
Instance method.
Instance method.
Start agent execution with verbose output (beginner-friendly).
Run agents silently (production use).
Set a state value
Get a state value
Update multiple state values
Clear all state values
Check if a state key exists
Get a copy of the entire state dictionary
Delete a state key if it exists. Returns True if deleted, False if key didn't exist.
Increment a numeric state value. Creates the key with default if it doesn't exist.
Append a value to a list state. Creates the list if it doesn't exist.
Save current state to memory for session persistence
Restore state from memory for session persistence. Returns True if restored.
Get a summary of token usage across all agents and tasks.
Get a detailed token usage report.
Display token usage in a formatted table.
Launch all agents as a single API endpoint (HTTP) or an MCP server.
Get the current plan.
Get the current todo list.
Get the current plan as markdown.
Get the current todo list as markdown.
Update the status of a plan step.
## Usage
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
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
`praisonaiagents/agents/agents.py` at line 172
***
## Related Documentation