AutoGen is a multi-agent AI orchestration framework currently in maintenance mode. It provides layered APIs for prototyping autonomous agent workflows, but new production projects should use Microsoft Agent Framework instead.
Project overview
AutoGen is a multi-agent AI orchestration framework currently in maintenance mode. It provides layered APIs for prototyping autonomous agent workflows, but new production projects should use Microsoft Agent Framework instead.
Project type
MCP · AI Agent
Use cases
Coding & Development · Automation
Deployment
Library integration
License
CC-BY-4.0
Best for
Developers or AI engineers prototyping multi-agent AI applications that require autonomous action or human collaboration.
Teams needing cross-language support for .NET and Python in event-driven agent runtimes.
Key capabilities
An opinionated API for rapid prototyping that supports common multi-agent patterns such as two-agent chats and group chats.
Implements message passing, event-driven agents, and local and distributed runtime, with cross-language support for .NET and Python.
Enables first- and third-party extensions to expand framework capabilities, including LLM clients like OpenAI and AzureOpenAI, and code execution.
Enables connecting agents to MCP servers using McpWorkbench to access tools like Playwright for web browsing.
A no-code GUI for building and running multi-agent workflows to rapidly prototype.
A benchmarking suite for evaluating agent performance.
Limitations and risks
AutoGen is now in maintenance mode. It will not receive new features or enhancements and is community managed going forward.
AutoGen Studio is not meant to be a production-ready app.
Only connect to trusted MCP servers as they may execute commands in your local environment or expose sensitive information.
AutoGen is now community-managed and responses may be limited.
Getting started
Setup requires a Python environment, package installation, and configuring API keys. The first success path involves installing the required packages via pip, exporting an OpenAI API key, and running a Python script.
Evidence and sources
GitHub project description: A programming framework for agentic AI
README: AutoGen is now in maintenance mode. It will not receive new features or enhancements and is community managed going forward.
README: Create an assistant agent using OpenAI's GPT-4o model. See [other supported models](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/models.html…
README: import asyncio from autogen_agentchat.agents import AssistantAgent from autogen_agentchat.ui import Console from autogen_ext.models.openai import OpenAIChatCompletionClient from a…