page-agent

alibabaMIT活跃维护

用自然语言直接操控网页界面的 JavaScript 页面内 GUI 智能体,把浏览器自动化从写选择器变成说人话,适合做网页操作助手和自动化流程。

JavaScript in-page GUI agent. Control web interfaces with natural language.

v1.12.4发布于 2026-09-06 07:46 UTC29,658star +8 / 7 天2,641fork同步于 2026-11-10 17:21 UTC

怎么上手

由 README 提炼,执行前请确认
npm install page-agent
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')
硬件要求按 README 说明

README 未说明显存或 GPU 要求;模型可本地部署,但未给出具体硬件规格

下载:源码 zip·GitHub Releases(安装包)本站不镜像安装包

项目说明

由 README 自动翻译提炼

在网页里跑的 JS GUI Agent,用自然语言直接操控页面交互

用自然语言直接操控网页界面的 JavaScript 页面内 GUI 智能体,把浏览器自动化从写选择器变成说人话,适合做网页操作助手和自动化流程。

核心能力

  • 纯页面内 JavaScript 注入,无需浏览器扩展或 Python
  • 基于文本 DOM 操作,不依赖截图和多模态模型
  • 支持自带主流及本地部署 LLM,可配 baseURL 和 apiKey
  • 可选 Chrome 扩展支持跨标签页多页面任务
  • 提供 Beta 版 MCP Server 供外部客户端控制浏览器

容易踩的坑

CDN 一行接入用的是官方免费测试 LLM,README 标注仅供技术评估,正式使用需换成自己的模型和 API Key;多页面任务需额外安装 Chrome 扩展,MCP Server 仍为 Beta;国内访问 jsDelivr 可能失败,需改用 npmmirror 镜像地址

内容由模型根据 README 生成,可能不完整或不准确,以官方文档为准。看原文 README

最近发版

5 个版本v1.12.4
  1. v1.12.4🌟v1.12.4最新正式版2026-09-06 · 2026-09-06 07:46 UTC

    What's Changed

    Full Changelog: https://github.com/alibaba/page-agent/compare/v1.12.3...v1.12.4

  2. v1.12.3🌟v1.12.32026-09-05 · 2026-09-05 17:47 UTC
    查看更新说明

    What's Changed

    New Contributors

    Full Changelog: https://github.com/alibaba/page-agent/compare/v1.12.2...v1.12.3

  3. v1.12.2🌟v1.12.22026-07-16 · 2026-07-16 07:41 UTC
    查看更新说明

    What's Changed

    New Contributors

    Full Changelog: https://github.com/alibaba/page-agent/compare/v1.12.1...v1.12.2

  4. v1.12.1🌟v1.12.12026-07-10 · 2026-07-10 09:13 UTC
    查看更新说明

    What's Changed

    Full Changelog: https://github.com/alibaba/page-agent/compare/v1.12.0...v1.12.1

  5. v1.12.0🌟v1.12.02026-07-09 · 2026-07-09 07:54 UTC
    查看更新说明

    What's Changed

    Stateless extension tab sync - TabsController pulls tab state on demand instead of long-lived ports, so the MV3 service worker stays stateless and survives idle kills without stalling the side panel.

    Tab status in agent context - Tab summaries now include each tab's loading status for the LLM.

    Full Changelog: https://github.com/alibaba/page-agent/compare/v1.11.0...v1.12.0

用户点评

登录用户的真实使用记录,可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译

    Page Agent

    CI npm downloads Minzipped bundle size (excluding Zod) license typescript Chrome Web Store Rating GitHub stars

    The GUI Agent Living in Your Webpage. One script gives any web page its own AI agent.

    🌐 English | 中文

    🚀 Demo | 📖 Docs | 📢 HN Discussion | 𝕏 Follow on X

    Watch the demo


    ✨ Features

    • 🎯 Easy integration
      • No need for browser extension / python / headless browser.
      • Just in-page javascript. Everything happens in your web page.
    • 📖 Text-based DOM manipulation
      • No screenshots. No multi-modal LLMs or special permissions needed.
    • 🧠 Bring your own LLMs
      • Works with most mainstream models, including locally deployed ones. See supported models.
    • 🐙 Optional chrome extension for multi-page tasks.

    💡 Use Cases

    • SaaS AI Copilot — Ship an AI copilot in your product in lines of code. No backend rewrite.
    • Smart Form Filling — Turn 20-click workflows into one sentence. Perfect for ERP, CRM, and admin systems.
    • Accessibility — Make any web app accessible through natural language. Voice commands, screen readers, zero barrier.
    • Multi-page Agent — Extend your own web agent's reach across browser tabs via the Chrome extension.
    • MCP - Allow your agent clients to control your browser.

    🚀 Quick Start

    One-line integration

    Fastest way to try PageAgent with our free Demo LLM:

    <script
        src="https://cdn.jsdelivr.net/npm/[email protected]/dist/iife/page-agent.demo.js"
        crossorigin="anonymous"
    ></script>
    
    <!-- China CDN mirror if you can't access jsDelivr -->
    <!-- https://registry.npmmirror.com/page-agent/1.12.4/files/dist/iife/page-agent.demo.js -->
    

    ⚠️ For technical evaluation only. This demo CDN uses our free testing LLM API. By using it, you agree to its terms.

    Add ?autoInit=false to load the script without creating the demo agent automatically. You can then instantiate it with new window.PageAgent(...) and your own LLMs.

    NPM Installation

    npm install page-agent
    
    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')
    

    For more programmatic usage, see 📖 Documentations.

    🤝 Contributing

    We welcome contributions from the community! See CONTRIBUTING.md for guidelines and docs/developer-guide.md for local development workflows.

    Built something cool with PageAgent? Share it in Show and Tell. 🙌

    Please read the maintainer's note on principles and current state.

    Contributions generated entirely by bots or AI without substantial human involvement will not be accepted.

    ⚖️ License

    MIT License

    👏 Acknowledgments

    This project builds upon the excellent work of browser-use.

    PageAgent is designed for client-side web enhancement, not server-side automation.

    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.
    

    ⭐ Star this repo if you find PageAgent helpful!