AutoGen

<div class="container"> <div class="row text-center"> <div class="col-sm-12"> <h1 class="hero-title"> AutoGen </h1> <h3> A framework for building AI agents and applications </h3> </div> </div> </div> <div style="margin-top: 2rem;">

::::{grid} :gutter: 2

:::{grid-item-card} {fas}palette;pst-color-primary Studio :shadow: none :margin: 2 0 0 0 :columns: 12 12 12 12

An web-based UI for prototyping with agents without writing code. Built on AgentChat.

bash

pip install -U autogenstudio
autogenstudio ui --port 8080 --appdir ./myapp

Start here if you are new to AutoGen and want to prototype with agents without writing code.

+++

{button-ref}

:color: secondary

Get Started

:::

:::{grid-item-card} :shadow: none :margin: 2 0 0 0 :columns: 12 12 12 12

{fas}people-group;pst-color-primary AgentChat

</div> A programming framework for building conversational single and multi-agent applications. Built on Core. Requires Python 3.10+.

python

# pip install -U "autogen-agentchat" "autogen-ext[openai]"
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

async def main() -> None:
    agent = AssistantAgent("assistant", OpenAIChatCompletionClient(model="gpt-4o"))
    print(await agent.run(task="Say 'Hello World!'"))

asyncio.run(main())

Start here if you are prototyping with agents using Python. Migrating from AutoGen 0.2?.

+++

{button-ref}

:color: secondary

Get Started

:::

:::{grid-item-card} {fas}cube;pst-color-primary Core :shadow: none :margin: 2 0 0 0 :columns: 12 12 12 12

An event-driven programming framework for building scalable multi-agent AI systems. Example scenarios:

Deterministic and dynamic agentic workflows for business processes.
Research on multi-agent collaboration.
Distributed agents for multi-language applications.

Start here if you are getting serious about building multi-agent systems.

+++

{button-ref}

:color: secondary

Get Started

:::

:::{grid-item-card} {fas}puzzle-piece;pst-color-primary Extensions :shadow: none :margin: 2 0 0 0 :columns: 12 12 12 12

Implementations of Core and AgentChat components that interface with external services or other libraries. You can find and use community extensions or create your own. Examples of built-in extensions:

{py:class}~autogen_ext.tools.mcp.McpWorkbench for using Model-Context Protocol (MCP) servers.
{py:class}~autogen_ext.agents.openai.OpenAIAssistantAgent for using Assistant API.
{py:class}~autogen_ext.code_executors.docker.DockerCommandLineCodeExecutor for running model-generated code in a Docker container.
{py:class}~autogen_ext.runtimes.grpc.GrpcWorkerAgentRuntime for distributed agents.

+++

<a class="sd-sphinx-override sd-btn sd-text-wrap sd-btn-secondary reference internal" href="user-guide/extensions-user-guide/discover.html"><span class="doc">Discover Community Extensions</span></a> <a class="sd-sphinx-override sd-btn sd-text-wrap sd-btn-secondary reference internal" href="user-guide/extensions-user-guide/create-your-own.html"><span class="doc">Create New Extension</span></a>

:::

::::

</div>

{toctree}

:maxdepth: 3
:hidden:

user-guide/agentchat-user-guide/index
user-guide/core-user-guide/index
user-guide/extensions-user-guide/index
Studio <user-guide/autogenstudio-user-guide/index>
reference/index