关于这个项目
探索多智能体之间的协作、工具调用与人机交互。
适合在隔离环境中先完成小规模 PoC：准备代表性数据，核对原仓库的运行依赖和许可，记录任务成功率、响应时间、成本与失败样例。部署方式和兼容版本请以原项目文档为准。
接入思路
01业务接口与访问控制02模型 / 检索 / 工具编排03数据与运行可观测性
以上为 FDE前线 建议的应用接入层次，项目内部架构请查阅原作者文档。
开始使用
建议固定版本，在隔离环境中复现原项目 Quick Start，记录依赖、模型服务和数据权限。本站仅索引原项目，不托管或执行仓库代码。
原项目部署文档展开同步的 README 纯文本
<a name="readme-top"></a>
<div align="center">
<img src="https://microsoft.github.io/autogen/0.2/img/ag.svg" alt="AutoGen Logo" width="100">
[](https://twitter.com/pyautogen)
[](https://www.linkedin.com/company/105812540)
[](https://aka.ms/autogen-discord)
[](https://microsoft.github.io/autogen/)
[](https://devblogs.microsoft.com/autogen/)
</div>
# AutoGen [](https://github.com/microsoft/agent-framework)
**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 **⚠️ Project archived and no longer maintained**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 This project has been archived and is no longer actively maintained by Microsoft.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](https://github.com/microsoft/agent-framework). Existing users are encouraged to migrate using the [AutoGen → Microsoft Agent Framework migration guide](https://learn.microsoft.com/en-us/agent-framework/migration-guide/from-autogen/).
>
> 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](https://github.com/microsoft/autogen/releases). If you are upgrading from AutoGen v0.2, please refer to the [Migration Guide](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/migration-guide.html) 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](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/models.html).
```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_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StdioServerParams
async def main() -> None:
model_client = OpenAIChatCompletionClient(model="gpt-4.1")
server_params = StdioServerParams(
command="npx",
args=[
"@playwright/mcp@latest",
"--headless",
],
)
async with McpWorkbench(server_params) as mcp:
agent = AssistantAgent(
"web_browsing_assistant",
model_client=model_client,
workbench=mcp, # For multiple MCP servers, put them in a list.
model_client_stream=True,
max_tool_iterations=10,
)
await Console(agent.run_stream(task="Find out how many contributors for the microsoft/autogen repository"))
asyncio.run(main())
```
> **Warning**: Only connect to trusted MCP servers as they may execute commands
> in your local environment or expose sensitive information.
### Multi-Agent Orchestration
You can use `AgentTool` to create a basic multi-agent orchestration setup.
```python
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.tools import AgentTool
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
async def main() -> None:
model_client = OpenAIChatCompletionClient(model="gpt-4.1")
math_agent = AssistantAgent(
"math_expert",
model_client=model_client,
system_message="You are a math expert.",
description="A math expert assistant.",
model_client_stream=True,
)
math_agent_tool = AgentTool(math_agent, return_value_as_last_message=True)
chemistry_agent = AssistantAgent(
"chemistry_expert",
model_client=model_client,
system_message="You are a chemistry expert.",
description="A chemistry expert assistant.",
model_client_stream=True,
)
chemistry_agent_tool = AgentTool(chemistry_agent, return_value_as_last_message=True)
agent = AssistantAgent(
"assistant",
system_message="You are a general assistant. Use expert tools when needed.",
model_client=model_client,
model_client_stream=True,
tools=[math_agent_tool, chemistry_agent_tool],
max_tool_iterations=10,
)
await Console(agent.run_stream(task="What is the integral of x^2?"))
await Console(agent.run_stream(task="What is the molecular weight of water?"))
asyncio.run(main())
```
For more advanced multi-agent orchestrations and workflows, read
[AgentChat documentation](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html).
### AutoGen Studio
Use AutoGen Studio to prototype and run multi-agent workflows without writing code.
> **Caution**: AutoGen Studio is meant to help you rapidly prototype multi-agent workflows and
> demonstrate an example of end user interfaces built with AutoGen. It is **not meant to be a
> production-ready app**. Developers are encouraged to use the AutoGen framework to build their own
> applications, implementing authentication, security and other features required for deployed
> applications. See the [security note](https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/index.html#a-note-on-security) for more details.
```bash
# Run AutoGen Studio on http://localhost:8080
autogenstudio ui --port 8080 --appdir ./my-app
```
## Why AutoGen?
<div align="center">
<img src="autogen-landing.jpg" alt="AutoGen Landing" width="500">
</div>
Pioneered in Microsoft Research, AutoGen opened the door to experimental multi-agent orchestration patterns that inspired the community. AutoGen is now archived and no longer maintained by Microsoft; the architecture described below remains available for historical/reference purposes. **For new projects, we recommend [Microsoft Agent Framework](https://github.com/microsoft/agent-framework)**, which builds on the lessons learned from AutoGen with enterprise-grade support.
The autogen _framework_ uses a layered and extensible design. Layers have clearly divided responsibilities and build on top of layers below. This design enables you to use the framework at different levels of abstraction, from high-level APIs to low-level components.
- [Core API](./python/packages/autogen-core/) implements message passing, event-driven agents, and local and distributed runtime for flexibility and power. It also support cross-language support for .NET and Python.
- [AgentChat API](./python/packages/autogen-agentchat/) implements a simpler but opinionated API for rapid prototyping. This API is built on top of the Core API and is closest to what users of v0.2 are familiar with and supports common multi-agent patterns such as two-agent chat or group chats.
- [Extensions API](./python/packages/autogen-ext/) enables first- and third-party extensions continuously expanding framework capabilities. It support specific implementation of LLM clients (e.g., OpenAI, AzureOpenAI), and capabilities such as code execution.
The ecosystem also supports two essential _developer tools_:
<div align="center">
<img src="https://media.githubusercontent.com/media/microsoft/autogen/refs/heads/main/python/packages/autogen-studio/docs/ags_screen.png" alt="AutoGen Studio Screenshot" width="500">
</div>
- [AutoGen Studio](./python/packages/autogen-studio/) provides a no-code GUI for building multi-agent applications.
- [AutoGen Bench](./python/packages/agbench/) provides a benchmarking suite for evaluating agent performance.
You can use the AutoGen framework and developer tools to create applications for your domain. For example, [Magentic-One](./python/packages/magentic-one-cli/) is a state-of-the-art multi-agent team built using AgentChat API and Extensions API that can handle a variety of tasks that require web browsing, code execution, and file handling.
For community support, visit our [Discord server](https://aka.ms/autogen-discord) or [GitHub Discussions](https://github.com/microsoft/autogen/discussions). Note that AutoGen is now community-managed and responses may be limited.
## Where to go next?
> **Starting a new project?** Head to [Microsoft Agent Framework](https://github.com/microsoft/agent-framework) for the latest multi-agent capabilities with long-term support.
>
> **Existing AutoGen user?** Use the [migration guide](https://learn.microsoft.com/en-us/agent-framework/migration-guide/from-autogen/) to transition, or refer to the resources below for current AutoGen documentation.
<div align="center">
| | [](./python) | [](./dotnet) | [](./python/packages/autogen-studio) |
| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Installation | [](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/installation.html) | [](https://microsoft.github.io/autogen/dotnet/dev/core/installation.html) | [](https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/installation.html) |
| Quickstart | [](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/quickstart.html#) | [](https://microsoft.github.io/autogen/dotnet/dev/core/index.html) | [](https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/usage.html#) |
| Tutorial | [](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/index.html) | [](https://microsoft.github.io/autogen/dotnet/dev/core/tutorial.html) | [](https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/usage.html#) |
| API Reference | [](https://microsoft.github.io/autogen/stable/reference/index.html#) | [](https://microsoft.github.io/autogen/dotnet/dev/api/Microsoft.AutoGen.Contracts.html) | [](https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/usage.html) |
| Packages | [](https://pypi.org/project/autogen-core/) <br> [](https://pypi.org/project/autogen-agentchat/) <br> [](https://pypi.org/project/autogen-ext/) | [](https://www.nuget.org/packages/Microsoft.AutoGen.Contracts/) <br> [](https://www.nuget.org/packages/Microsoft.AutoGen.Core/) <br> [](https://www.nuget.org/packages/Microsoft.AutoGen.Core.Grpc/) <br> [](https://www.nuget.org/packages/Microsoft.AutoGen.RuntimeGateway.Grpc/) | [](https://pypi.org/project/autogenstudio/) |
</div>
Interested in contributing? See [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines. As AutoGen is in maintenance mode, contributions are limited to bug fixes, security patches, and documentation improvements. For feature development, consider contributing to [Microsoft Agent Framework](https://github.com/microsoft/agent-framework).
Have questions? Check out our [Frequently Asked Questions (FAQ)](./FAQ.md) for answers to common queries. Community support is available through [GitHub Discussions](https://github.com/microsoft/autogen/discussions) and the [Discord server](https://aka.ms/autogen-discord), though response times may vary as AutoGen is now community-managed. For actively supported tooling, see [Microsoft Agent Framework](https://github.com/microsoft/agent-framework).
## Legal Notices
Microsoft and any contributors grant you a license to the Microsoft documentation and other content
in this repository under the [Creative Commons Attribution 4.0 International Public License](https://creativecommons.org/licenses/by/4.0/legalcode),
see the [LICENSE](LICENSE) file, and grant you a license to any code in the repository under the [MIT License](https://opensource.org/licenses/MIT), see the
[LICENSE-CODE](LICENSE-CODE) file.
Microsoft, Windows, Microsoft Azure, and/or other Microsoft products and services referenced in the documentation
may be either trademarks or registered trademarks of Microsoft in the United States and/or other countries.
The licenses for this project do not grant you rights to use any Microsoft names, logos, or trademarks.
Microsoft's general trademark guidelines can be found at <http://go.microsoft.com/fwlink/?LinkID=254653>.
Privacy information can be found at <https://go.microsoft.com/fwlink/?LinkId=521839>
Microsoft and any contributors reserve all other rights, whether under their respective copyrights, patents,
or trademarks, whether by implication, estoppel, or otherwise.
<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
<a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
↑ Back to Top ↑
</a>
</p>
社区讨论 0 条公开讨论
分享你的复现经验、适用场景或遇到的问题。
登录参与讨论