Back to directory

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.

AutoGen

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.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.