wehub-resource-sync
132 lines
6.8 KiB
Markdown
132 lines
6.8 KiB
Markdown
<!-- WEHUB_ZH_README -->
|
||
> [!NOTE]
|
||
> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。
|
||
> [English](./README.en.md) · [原始项目](https://github.com/alibaba/page-agent) · [上游 README](https://github.com/alibaba/page-agent/blob/HEAD/README.md)
|
||
> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。
|
||
|
||
# Page Agent
|
||
|
||
<picture>
|
||
<source media="(prefers-color-scheme: dark)" srcset="https://page-agent.github.io/assets/readme/banner-dark.png">
|
||
<img alt="Page Agent Banner" src="https://page-agent.github.io/assets/readme/banner-light.png">
|
||
</picture>
|
||
|
||
[](https://github.com/alibaba/page-agent/actions/workflows/main-ci.yml)
|
||
[](https://www.npmjs.com/package/page-agent)
|
||
[](https://www.npmjs.com/package/page-agent)
|
||
[](https://bundlephobia.com/package/page-agent)
|
||
[](https://opensource.org/licenses/MIT)
|
||
[](http://www.typescriptlang.org/)
|
||
[](https://chromewebstore.google.com/detail/page-agent-ext/akldabonmimlicnjlflnapfeklbfemhj)
|
||
[](https://github.com/alibaba/page-agent)
|
||
|
||
驻留在网页中的 GUI Agent。只需一段脚本，即可为任意网页赋予专属 AI Agent。
|
||
|
||
<a href="https://trendshift.io/repositories/22551?utm_source=repository-badge&utm_medium=badge&utm_campaign=badge-repository-22551" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/repositories/22551" alt="alibaba%2Fpage-agent | Trendshift" width="180"/></a>
|
||
|
||
🌐 **English** | [中文](./docs/README-zh.md)
|
||
|
||
<a href="https://alibaba.github.io/page-agent/" target="_blank"><b>🚀 Demo</b></a> | <a href="https://alibaba.github.io/page-agent/docs/introduction/overview" target="_blank"><b>📖 Docs</b></a> | <a href="https://news.ycombinator.com/item?id=47264138" target="_blank"><b>📢 HN Discussion</b></a> | <a href="https://x.com/simonluvramen" target="_blank"><b>𝕏 Follow on X</b></a>
|
||
|
||
<!-- demo video -->
|
||
|
||
[](https://github.com/user-attachments/assets/a1f2eae2-13fb-4aae-98cf-a3fc1620a6c2)
|
||
|
||
---
|
||
|
||
## ✨ Features
|
||
|
||
- **🎯 轻松集成**
|
||
- 无需 `browser extension` / `python` / `headless browser`。
|
||
- 纯页面内 JavaScript，一切都在你的网页中完成。
|
||
- **📖 基于文本的 DOM 操作**
|
||
- 无需截图，也无需多模态 LLM 或特殊权限。
|
||
- **🧠 自带 LLM（Bring your own LLMs）**
|
||
- 兼容大多数主流模型，包括本地部署的模型。请参阅[支持的模型](https://alibaba.github.io/page-agent/docs/features/models).
|
||
- **🐙 可选 [Chrome 扩展](https://alibaba.github.io/page-agent/docs/features/chrome-extension)，用于多页面任务。**
|
||
- 还提供 [MCP Server（Beta）](https://alibaba.github.io/page-agent/docs/features/mcp-server)，可从外部进行控制
|
||
|
||
## 💡 Use Cases
|
||
|
||
- **SaaS AI Copilot** — 几行代码即可在产品中上线 AI 副驾驶，无需重写后端。
|
||
- **智能表单填写** — 将 20 次点击的工作流压缩为一句话，非常适合 ERP、CRM 和管理系统。
|
||
- **无障碍访问** — 通过自然语言让任意 Web 应用可用：语音指令、屏幕阅读器，零门槛。
|
||
- **多页面 Agent** — 通过 [Chrome 扩展](https://alibaba.github.io/page-agent/docs/features/chrome-extension).，将你的 Web Agent 扩展到多个浏览器标签页。
|
||
- **MCP** — 让你的 Agent 客户端控制浏览器。
|
||
|
||
## 🚀 Quick Start
|
||
|
||
### 一行集成
|
||
|
||
使用免费 Demo LLM 体验 PageAgent 的最快方式：
|
||
|
||
```html
|
||
<script
|
||
src="https://cdn.jsdelivr.net/npm/page-agent@1.12.1/dist/iife/page-agent.demo.js"
|
||
crossorigin="anonymous"
|
||
></script>
|
||
```
|
||
|
||
> **⚠️ 仅供技术评估。** 此演示 CDN 使用我们免费的[测试 LLM API](https://alibaba.github.io/page-agent/docs/features/models#free-testing-api).。使用即表示你同意其[条款](https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md).
|
||
> 添加 `?autoInit=false` 可在加载脚本时不自动创建演示 Agent。随后可用 `new window.PageAgent(...)` 自行实例化。
|
||
|
||
| 镜像 | URL |
|
||
| ------- | ----------------------------------------------------------------------------------- |
|
||
| 全球 | https://cdn.jsdelivr.net/npm/page-agent@1.12.1/dist/iife/page-agent.demo.js |
|
||
| 中国 | https://registry.npmmirror.com/page-agent/1.12.1/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: 'qwen3.5-plus',
|
||
baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
|
||
apiKey: 'YOUR_API_KEY',
|
||
language: 'en-US',
|
||
})
|
||
|
||
await agent.execute('Click the login button')
|
||
```
|
||
|
||
更多编程式用法请参阅[📖 文档](https://alibaba.github.io/page-agent/docs/introduction/overview).
|
||
|
||
## 🤝 参与贡献
|
||
|
||
欢迎社区贡献！指南请参阅 [CONTRIBUTING.md](CONTRIBUTING.md)，本地开发流程请参阅 [docs/developer-guide.md](docs/developer-guide.md)。
|
||
|
||
用 PageAgent 做出了酷东西？欢迎在 [Show and Tell](https://github.com/alibaba/page-agent/discussions/categories/show-and-tell). 分享 🙌
|
||
|
||
请阅读[维护者说明](https://github.com/alibaba/page-agent/issues/349)，了解原则与当前状态。
|
||
|
||
完全由**机器人或 AI** 生成、缺乏实质性人工参与的贡献**不会被接受**。
|
||
|
||
## ⚖️ 许可证
|
||
|
||
[MIT License](LICENSE)
|
||
|
||
## 👏 致谢
|
||
|
||
本项目建立在 **[`browser-use`](https://github.com/browser-use/browser-use)**. 的优秀工作之上。
|
||
|
||
`PageAgent` 面向**客户端 Web 增强**，而非服务端自动化。
|
||
|
||
```
|
||
DOM processing components and prompt are derived from browser-use:
|
||
|
||
Browser Use <https://github.com/browser-use/browser-use>
|
||
Copyright (c) 2024 Gregor Zunic
|
||
Licensed under the MIT License
|
||
|
||
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.
|
||
```
|
||
|
||
**⭐ 如果觉得 PageAgent 有用，欢迎给本仓库点 Star！**
|