microsoft /autogen
A programming framework for agentic AI
★ 61,854⑂ 9,408👁 523⑃ 3,965● 3,107▤ 98
More from this author
+36
Daily
+98
Weekly
61,854
stars
9,408
forks
523
watchers
3,965
prs
3,107
issues
98
releases
README
AutoGen
AutoGen is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans.
[!CAUTION]
⚠️ Project archived and no longer maintained
This project has been archived and is no longer actively maintained by Microsoft.
Microsoft is not providing bug fixes, security fixes, new features, or support for this project. The repository remains available for historical/reference purposes.
Use archived repositories with caution. Without ongoing maintenance or security fixes, vulnerabilities in this project and its dependencies may remain unaddressed, increasing the security risks of continued use. Carefully assess these risks before using AutoGen, particularly when handling sensitive data. AutoGen was developed for research and experimentation and as it transitions to archived, we continue to advise against production use.
We thank the AutoGen community for the code, documentation, bug reports, ideas, and discussions that helped shape this project.
New users should start with Microsoft Agent Framework. Existing users are encouraged to migrate using the AutoGen → Microsoft Agent Framework migration guide.
Microsoft Agent Framework (MAF) is the enterprise‑ready successor to AutoGen. Microsoft Agent FrameworkAF in now available as a production-ready release: stable APIs, and a commitment to long-term support. Whether you're building a single assistant or orchestrating a fleet of specialized agents, Microsoft Agent Framework 1.0 gives you enterprise-grade multi-agent orchestration, multi-provider model support, and cross-runtime interoperability via A2A and MCP.
Installation
AutoGen requires Python 3.10 or later.
bash
Install AgentChat and OpenAI client from Extensions
pip install -U "autogen-agentchat" "autogen-ext[openai]"
The current stable version can be found in the releases. If you are upgrading from AutoGen v0.2, please refer to the Migration Guide for detailed instructions on how to update your code and configurations.
bash
Install AutoGen Studio for no-code GUI
pip install -U "autogenstudio"
Quickstart
The following samples call OpenAI API, so you first need to create an account and export your key as export OPENAI_API_KEY="sk-...".
Hello World
Create an assistant agent using OpenAI's GPT-4o model. See other supported models.
python
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
async def main() - None:
model_client = OpenAIChatCompletionClient(model="gpt-4.1")
agent = AssistantAgent("assistant", model_client=model_client)
print(await agent.run(task="Say 'Hello World!'"))
await model_client.close()
asyncio.run(main())
MCP Server
Create a web browsing assistant agent that uses the Playwright MCP server.
python
First run npm install -g @playwright/mcp@latest to install the MCP server.
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_agentcTop issues
#7353Feature: Cryptographic action receipts for enterprise agent governance (AAR)431 comments · 2026-03-06#7405Proposal: GuardrailProvider protocol for tool call interception147 comments · 2026-03-14#7487Multi-agent systems need a 'mission keeper' role — not a Boss Agent, but a dedicated goal integrity node74 comments · 2026-03-29#7492Payment primitive for multi-agent systems - how are teams handling this?63 comments · 2026-03-30#7372Cryptographic governance layer for AutoGen distributed agent runtime62 comments · 2026-03-11#7525Feature: Agent trust verification via MoltBridge for cross-org multi-agent scenarios58 comments · 2026-04-04#7265[Question] Practical reliability patterns for multi-agent production57 comments · 2026-02-24#7748RFC: Cross-agent shared memory store with on-demand capsule recall (agent/group/global scopes)41 comments · 2026-05-25
Discussions
#8477Chopper: a small open model that cuts only the needed sentences out of retrieved text1 comments · 2026-11-13#8473mcp-slim: Zero-dependency MCP stdio proxy for AutoGen (-50% to -98% schema tokens, $ref inlining, SecretGuard)2 comments · 2026-11-12#8471A short checklist for AutoGen teams that write to real systems2 comments · 2026-11-11#8464Handling authorization state drift during agent-to-tool transitions (Architecture Lab)2 comments · 2026-11-09#8443A small offline permission-revocation fixture for tool workflows — independent runs and counterexamples welcome2 comments · 2026-11-07#8432Show and tell: giving an AutoGen team a check tool — so "the other agent reviewed it" becomes a record1 comments · 2026-11-05#8413A wheel turns forward at 40 rpm and looks backward on camera: an interactive sampling puzzle made with an AI assistant0 comments · 2026-11-02#8411Governed memory for AutoGen multi-agent conversations — audit chains, poisoning defense0 comments · 2026-11-02
Latest release
python-v0.7.5 python-v0.7.5 2025-09-30What's Changed Fix docs dotnet core typo by @lach-g in https://github.com/microsoft/autogen/pull/6950 Fix loading streaming Bedrock response with tool usage with empty argument by @pawel-dabro in https://github.com/microsoft/autogen/pull/6979 Support linear memory in RedisMemory by @justin-cechmanek in https://github.com/microsoft/autogen/pull/6972 Fix message ID for correlation between streaming chunks and final mes… by @smalltalkman in https://github.com/microsoft/autogen/pull/6969 fix: extra args not work to disable thinking by @liuyunrui123 in https://github.com/microsoft/autogen