# AutoGen — Microsoft Multi-Agent Conversation Framework

> Framework by Microsoft Research for building multi-agent conversational AI systems. Agents chat with each other to solve tasks collaboratively. Supports human-in-the-loop and code execution. 40,000+ stars.

## Install

Save as a script file and run:

## Quick Use

```bash
pip install autogen-agentchat autogen-ext
```

```python
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_ext.models.openai import OpenAIChatCompletionClient

model = OpenAIChatCompletionClient(model="claude-sonnet-4-20250514", api_key="sk-ant-...")

coder = AssistantAgent("coder", model_client=model,
    system_message="You write Python code to solve tasks.")
reviewer = AssistantAgent("reviewer", model_client=model,
    system_message="You review code for bugs and improvements.")

team = RoundRobinGroupChat([coder, reviewer], max_turns=4)
result = await team.run(task="Write a function to find prime numbers up to N")
```

---

## Intro

AutoGen is a framework by Microsoft Research for building multi-agent conversational AI systems with 40,000+ GitHub stars. Multiple AI agents with different roles chat with each other to collaboratively solve complex tasks — a coder writes code, a reviewer checks it, a planner coordinates, and a human approves. AutoGen v0.4 (latest) features an event-driven architecture, pluggable components, and first-class support for human-in-the-loop workflows. Best for teams building complex multi-agent systems where agents need to debate, iterate, and collaborate. Works with: Claude, GPT-4, any OpenAI-compatible model. Setup time: under 3 minutes.

---

## Core Concepts

### Agents
Each agent has a role and system message:

```python
planner = AssistantAgent("planner", model_client=model,
    system_message="Break down complex tasks into steps. Coordinate with coder and reviewer.")
coder = AssistantAgent("coder", model_client=model,
    system_message="Write clean, tested Python code.")
reviewer = AssistantAgent("reviewer", model_client=model,
    system_message="Review code for bugs, edge cases, and improvements.")
```

### Teams

**Round Robin** — agents take turns:
```python
team = RoundRobinGroupChat([planner, coder, reviewer], max_turns=6)
```

**Selector** — a model picks who speaks next:
```python
team = SelectorGroupChat([planner, coder, reviewer],
    model_client=model)  # Model decides speaking order
```

### Human-in-the-Loop

```python
from autogen_agentchat.agents import UserProxyAgent

human = UserProxyAgent("human")
team = RoundRobinGroupChat([coder, reviewer, human], max_turns=10)
# Pauses for human input when human's turn comes
```

### Code Execution
Agents can write and run code in sandboxed environments:

```python
from autogen_ext.code_executors.docker import DockerCommandLineCodeExecutor

executor = DockerCommandLineCodeExecutor()
coder = AssistantAgent("coder", model_client=model,
    code_executor=executor)
```

### Tool Use

```python
from autogen_core import FunctionTool

def search_web(query: str) -> str:
    'Search the web for information.'
    return tavily_search(query)

search_tool = FunctionTool(search_web, description="Search the web")
agent = AssistantAgent("researcher", model_client=model, tools=[search_tool])
```

### Real-World Example: Research Paper

```python
researcher = AssistantAgent("researcher", tools=[search_tool])
writer = AssistantAgent("writer", system_message="Write academic-style content")
editor = AssistantAgent("editor", system_message="Edit for clarity and accuracy")
human = UserProxyAgent("professor")

team = SelectorGroupChat([researcher, writer, editor, human])
result = await team.run(task="Write a literature review on LLM agents in software engineering")
```

### Key Stats
- 40,000+ GitHub stars
- By Microsoft Research
- Event-driven architecture (v0.4)
- Human-in-the-loop support
- Docker code execution sandbox

### FAQ

**Q: What is AutoGen?**
A: A Microsoft Research framework for building multi-agent AI systems where agents converse and collaborate to solve complex tasks, with human-in-the-loop support.

**Q: Is AutoGen free?**
A: Yes, open-source under MIT license.

**Q: How is AutoGen different from CrewAI?**
A: AutoGen focuses on agent conversations and debate. CrewAI focuses on role-based task delegation. AutoGen is more flexible for complex multi-turn interactions.

---

## Source & Thanks

> Created by [Microsoft Research](https://github.com/microsoft). Licensed under MIT.
>
> [autogen](https://github.com/microsoft/autogen) — ⭐ 40,000+

Thanks to Microsoft Research for pioneering multi-agent conversations.

---

<!-- ZH -->

## 快速使用

```bash
pip install autogen-agentchat autogen-ext
```

```python
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import RoundRobinGroupChat

coder = AssistantAgent("coder", model_client=model)
reviewer = AssistantAgent("reviewer", model_client=model)
team = RoundRobinGroupChat([coder, reviewer], max_turns=4)
result = await team.run(task="写一个质数查找函数")
```

---

## 简介

AutoGen 是微软研究院开发的多 Agent 对话框架，GitHub 40,000+ stars。多个 AI Agent 通过对话协作解决复杂任务。支持人在环路和沙盒代码执行。适合需要 Agent 辩论、迭代和协作的复杂多 Agent 系统。

---

## 来源与感谢

> Created by [Microsoft Research](https://github.com/microsoft). Licensed under MIT.
>
> [autogen](https://github.com/microsoft/autogen) — ⭐ 40,000+

---
Source: https://tokrepo.com/en/workflows/dd1827b4-2401-4ecc-a1b4-a3cc813e06f5
Author: Agent Toolkit