https://github.com/alibaba/page-agent
JavaScript in-page GUI agent. Control web interfaces with natural language.
https://github.com/alibaba/page-agent
agent ai ai-agents browser-automation javascript typescript ui-automation web
Last synced: 1 day ago
JSON representation
JavaScript in-page GUI agent. Control web interfaces with natural language.
- Host: GitHub
- URL: https://github.com/alibaba/page-agent
- Owner: alibaba
- License: mit
- Created: 2025-09-23T09:30:17.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2026-01-19T12:51:57.000Z (16 days ago)
- Last Synced: 2026-01-19T13:43:24.358Z (16 days ago)
- Topics: agent, ai, ai-agents, browser-automation, javascript, typescript, ui-automation, web
- Language: TypeScript
- Homepage: https://alibaba.github.io/page-agent/
- Size: 1.47 MB
- Stars: 588
- Watchers: 4
- Forks: 52
- Open Issues: 19
-
Metadata Files:
- Readme: README-zh.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Agents: AGENTS.md
Awesome Lists containing this project
README
# PageAgent 🤖🪄
[](https://opensource.org/licenses/MIT) [](http://www.typescriptlang.org/) [](https://www.npmjs.com/package/page-agent) [](https://bundlephobia.com/package/page-agent) [](https://github.com/alibaba/page-agent)
纯 JS 实现的 GUI agent。使用自然语言操作你的 Web 应用。无须后端、客户端、浏览器插件。
🌐 [English](./README.md) | **中文**
---
## ✨ Features
- **🎯 轻松集成**
- 无需 Python，无需无头浏览器，无需浏览器插件。纯页面内脚本。
- **🔐 端侧运行**
- **🧠 HTML 脱水**
- **💬 自然语言接口**
- **🎨 HITL 交互界面**
以及 😉
- **🧪 实验性的 Chrome 扩展，支持跨页面控制** - `packages/extension`
👉 [**🗺️ Roadmap**](https://github.com/alibaba/page-agent/issues/96)
## 🚀 快速开始
### 一行代码集成
通过我们免费的 Demo LLM 快速体验 PageAgent：
```html
```
> - **⚠️ 仅用于技术评估。** Demo LLM 有速率和使用限制，可能随时变更。
> - **🌷 建议使用自己的 LLM API。**
| Mirrors | URL |
| ------- | ---------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.1.0/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.1.0/files/dist/iife/page-agent.demo.js |
### NPM 安装
```bash
npm install page-agent
```
```javascript
import { PageAgent } from 'page-agent'
const agent = new PageAgent({
model: 'deepseek-chat',
baseURL: 'https://api.deepseek.com',
apiKey: 'YOUR_API_KEY',
language: 'zh-CN',
})
await agent.execute('点击登录按钮')
```
适用于无法使用 NPM 的环境，我们也提供了 IIFE 构建的 CDN 方式。[@see CDN Usage](https://alibaba.github.io/page-agent/#/docs/integration/cdn-setup)
## 🏗️ 架构设计
PageAgent adopts a simplified monorepo structure:
```
packages/
├── core/ # ** Core agent logic without UI(npm: @page-agent/core) **
├── page-agent/ # Exported agent and demo(npm: page-agent)
├── llms/ # LLM 客户端 (npm: @page-agent/llms)
├── page-controller/ # DOM 操作 & 蒙层 & 模拟鼠标 (npm: @page-agent/page-controller)
├── ui/ # 面板 & i18n (npm: @page-agent/ui)
└── website/ # 文档站点
```
## 🤝 贡献
欢迎社区贡献！请参阅 [CONTRIBUTING.md](CONTRIBUTING.md) 了解环境配置和本地开发说明。
请在贡献前阅读[行为准则](CODE_OF_CONDUCT.md)。
## 👏 致谢
本项目基于 **[`browser-use`](https://github.com/browser-use/browser-use)** 的优秀工作构建。
`PageAgent` 专为**客户端网页增强**设计，不是服务端自动化工具。
```
DOM processing components and prompt are derived from browser-use:
Browser Use
Copyright (c) 2024 Gregor Zunic
Licensed under the MIT License
Original browser-use project:
We gratefully acknowledge the browser-use project and its contributors for their
excellent work on web automation and DOM interaction patterns that helped make
this project possible.
Third-party dependencies and their licenses can be found in the package.json
file and in the node_modules directory after installation.
```
## 📄 许可证
[MIT License](LICENSE)
---
**⭐ 如果觉得 PageAgent 有用或有趣，请给项目点个星！**