> ## 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.

# Agents

> Class reference for Agents

> Defined in the [**agents**](https://praison.ai/docs/sdk/reference/praisonaiagents/modules/agents.md) module.

```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: Agents"]
    agent --> output["Output Result"]
    style agent fill:#8B0000,color:#fff
    style input fill:#8B0000,color:#fff
    style output fill:#8B0000,color:#fff
```

## 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.

**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

> [card] [add\_task()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-add_task.md)
>
> Instance method.

> [card] [clean\_json\_output()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-clean_json_output.md)
>
> Instance method.

> [card] [context\_manager()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-context_manager.md)
>
> ContextManager instance for unified context management across all agents.

> [card] [default\_completion\_checker()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-default_completion_checker.md)
>
> Instance method.

> [card] [aexecute\_task()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-aexecute_task.md)
>
> Async version of execute\_task method

> [card] [arun\_task()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-arun_task.md)
>
> Async version of run\_task method

> [card] [arun\_all\_tasks()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-arun_all_tasks.md)
>
> Async version of run\_all\_tasks method

> [card] [astart()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-astart.md)
>
> Async version of start method.

> [card] [save\_output\_to\_file()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-save_output_to_file.md)
>
> Instance method.

> [card] [execute\_task()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-execute_task.md)
>
> Synchronous version of execute\_task method

> [card] [run\_task()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-run_task.md)
>
> Synchronous version of run\_task method

> [card] [run\_all\_tasks()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-run_all_tasks.md)
>
> Synchronous version of run\_all\_tasks method

> [card] [get\_task\_status()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_task_status.md)
>
> Instance method.

> [card] [get\_all\_tasks\_status()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_all_tasks_status.md)
>
> Instance method.

> [card] [get\_task\_result()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_task_result.md)
>
> Instance method.

> [card] [get\_task\_details()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_task_details.md)
>
> Instance method.

> [card] [get\_agent\_details()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_agent_details.md)
>
> Instance method.

> [card] [start()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-start.md)
>
> Start agent execution with verbose output (beginner-friendly).

> [card] [run()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-run.md)
>
> Run agents silently (production use).

> [card] [set\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-set_state.md)
>
> Set a state value

> [card] [get\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_state.md)
>
> Get a state value

> [card] [update\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-update_state.md)
>
> Update multiple state values

> [card] [clear\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-clear_state.md)
>
> Clear all state values

> [card] [has\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-has_state.md)
>
> Check if a state key exists

> [card] [get\_all\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_all_state.md)
>
> Get a copy of the entire state dictionary

> [card] [delete\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-delete_state.md)
>
> Delete a state key if it exists. Returns True if deleted, False if key didn't exist.

> [card] [increment\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-increment_state.md)
>
> Increment a numeric state value. Creates the key with default if it doesn't exist.

> [card] [append\_to\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-append_to_state.md)
>
> Append a value to a list state. Creates the list if it doesn't exist.

> [card] [save\_session\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-save_session_state.md)
>
> Save current state to memory for session persistence

> [card] [restore\_session\_state()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-restore_session_state.md)
>
> Restore state from memory for session persistence. Returns True if restored.

> [card] [get\_token\_usage\_summary()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_token_usage_summary.md)
>
> Get a summary of token usage across all agents and tasks.

> [card] [get\_detailed\_token\_report()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_detailed_token_report.md)
>
> Get a detailed token usage report.

> [card] [display\_token\_usage()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-display_token_usage.md)
>
> Display token usage in a formatted table.

> [card] [launch()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-launch.md)
>
> Launch all agents as a single API endpoint (HTTP) or an MCP server.

> [card] [current\_plan()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-current_plan.md)
>
> Get the current plan.

> [card] [todo\_list()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-todo_list.md)
>
> Get the current todo list.

> [card] [get\_plan\_markdown()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_plan_markdown.md)
>
> Get the current plan as markdown.

> [card] [get\_todo\_markdown()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-get_todo_markdown.md)
>
> Get the current todo list as markdown.

> [card] [update\_plan\_step\_status()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Agents-update_plan_step_status.md)
>
> Update the status of a plan step.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.