# AutoGen

AutoGen is a Python framework, now in community-maintained mode, for building multi-agent AI applications in which agents act autonomously or work alongside people.

It offers a layered design from a low-level Core API implementing message passing and agent lifecycles up to a higher-level AgentChat API for assembling assistant agents, tool use and multi-agent orchestration; a Playwright-based MCP server example shows an agent browsing the web, and a no-code AutoGen Studio lets someone prototype a multi-agent workflow through a GUI, though the project describes Studio as a demonstration rather than a production-ready application.

Microsoft now directs new projects toward its successor, Microsoft Agent Framework, describing it as adding stable APIs, multi-provider model support and cross-runtime interoperability through A2A and MCP, while existing AutoGen users can keep using the current architecture with community support.

Requires Python 3.10 or later. CC-BY-4.0 licensed.

Website: https://microsoft.github.io/autogen/