AutoGen#
AutoGen
A framework for building AI agents and applications
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Project archived and no longer maintained
This project has been archived and is no longer actively maintained by Microsoft.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 and reference purposes.
Use archived repositories with caution. Without ongoing maintenance or security fixes, vulnerabilities in this project and its dependencies may remain unaddressed. Carefully assess these risks before using AutoGen, particularly when handling sensitive data. AutoGen was developed for research and experimentation; we continue to advise against production use.
New users should start with Microsoft Agent Framework. Existing users are encouraged to migrate using the AutoGen to Microsoft Agent Framework migration guide.
An web-based UI for prototyping with agents without writing code. Built on AgentChat.
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.
AgentChat
# 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?.
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.
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:
McpWorkbenchfor using Model-Context Protocol (MCP) servers.OpenAIAssistantAgentfor using Assistant API.DockerCommandLineCodeExecutorfor running model-generated code in a Docker container.GrpcWorkerAgentRuntimefor distributed agents.