# Qwen-Agent — Multi-Tool AI Agent Framework

> Build AI agents with Alibaba Qwen models featuring tool calling, code execution, RAG, and browser control. Supports MCP protocol and custom tool development.

## Install

Save as a script file and run:

## Quick Use

```bash
pip install qwen-agent
```

```python
from qwen_agent.agents import Assistant

bot = Assistant(
    llm={'model': 'qwen-max'},
    function_list=['code_interpreter', 'image_gen'],
)

messages = [{'role': 'user', 'content': 'Draw a sine wave plot'}]
for response in bot.run(messages):
    print(response)
```

## What is Qwen-Agent?

Qwen-Agent is an agent framework built around Alibaba's Qwen language models. It provides built-in tools (code interpreter, browser, RAG), supports MCP protocol, and includes a GUI for building custom agent applications — from simple chatbots to complex multi-agent workflows.

**Answer-Ready**: Qwen-Agent is an AI agent framework by Alibaba featuring built-in code execution, browser control, RAG retrieval, and MCP protocol support. It works with Qwen models and compatible APIs for building multi-tool agent applications.

**Best for**: Developers building AI agents with Qwen models or compatible APIs. **Works with**: Qwen-Max, Qwen-Plus, any OpenAI-compatible API. **Setup time**: Under 3 minutes.

## Core Features

### 1. Built-In Tools

```python
from qwen_agent.agents import Assistant

# Code Interpreter — execute Python in sandbox
bot = Assistant(
    llm={'model': 'qwen-max'},
    function_list=['code_interpreter'],
)

# RAG — retrieve from documents
bot = Assistant(
    llm={'model': 'qwen-max'},
    function_list=['doc_qa'],
    files=['report.pdf', 'data.csv'],
)
```

### 2. MCP Protocol Support

```python
from qwen_agent.agents import Assistant

bot = Assistant(
    llm={'model': 'qwen-max'},
    mcp_servers={
        'filesystem': {
            'command': 'npx',
            'args': ['-y', '@anthropic/mcp-filesystem', '/tmp']
        }
    },
)
```

### 3. Custom Tool Development

```python
from qwen_agent.tools.base import BaseTool, register_tool

@register_tool('weather')
class WeatherTool(BaseTool):
    description = 'Get current weather for a city'
    parameters = [{'name': 'city', 'type': 'string', 'required': True}]

    def call(self, params, **kwargs):
        city = params['city']
        return f'Sunny, 25C in {city}'
```

### 4. Multi-Agent Workflows

```python
from qwen_agent.agents import GroupChat

researcher = Assistant(llm=cfg, name='Researcher', system_message='You research topics.')
writer = Assistant(llm=cfg, name='Writer', system_message='You write articles.')

group = GroupChat(agents=[researcher, writer])
for response in group.run(messages):
    print(response)
```

### 5. Browser Control

```python
bot = Assistant(
    llm={'model': 'qwen-max'},
    function_list=['browser'],
)
# Agent can navigate, read, and interact with web pages
```

### 6. GUI Application

```bash
python -m qwen_agent.gui --agent-config config.json
# Launches a Gradio-based chat interface
```

## FAQ

**Q: Does it work with non-Qwen models?**
A: Yes, any OpenAI-compatible API works. Set the base_url and api_key accordingly.

**Q: Is it open source?**
A: Yes, Apache 2.0 license. Fully open-source with active development.

**Q: How does MCP support work?**
A: Qwen-Agent can connect to MCP servers as tool providers, similar to Claude Code or Cline.

## Source & Thanks

> Created by [Alibaba Qwen Team](https://github.com/QwenLM). Licensed under Apache 2.0.
>
> [QwenLM/Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) — 6k+ stars

<!-- ZH -->

## 快速使用

```bash
pip install qwen-agent
```

三行代码创建带工具调用的 AI 代理。

## 什么是 Qwen-Agent？

Qwen-Agent 是阿里巴巴基于通义千问模型构建的代理框架。提供内置工具（代码解释器、浏览器、RAG）、支持 MCP 协议，包含 GUI 界面。

**一句话总结**：Qwen-Agent 是阿里 AI 代理框架，内置代码执行、浏览器控制、RAG 检索和 MCP 协议支持。

**适合人群**：使用 Qwen 模型或兼容 API 构建 AI 代理的开发者。**支持**：Qwen-Max、Qwen-Plus、任何 OpenAI 兼容 API。

## 核心功能

### 1. 内置工具
代码解释器、文档 QA、浏览器控制、图片生成。

### 2. MCP 协议支持
连接任意 MCP 服务器作为工具提供者。

### 3. 自定义工具
装饰器注册自定义工具，代理自动发现和调用。

### 4. 多代理工作流
GroupChat 模式，多个代理协作完成复杂任务。

### 5. GUI 界面
内置 Gradio 界面，一键启动聊天应用。

## 常见问题

**Q: 支持非 Qwen 模型吗？**
A: 支持，任何 OpenAI 兼容 API 都可以。

**Q: 开源吗？**
A: 是，Apache 2.0 许可证。

## 来源与致谢

> [QwenLM/Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) — 6k+ stars, Apache 2.0

---
Source: https://tokrepo.com/en/workflows/cfd97f48-99e4-4cf9-b584-180c9fda8905
Author: Prompt Lab