page-agent
starsforks
How to install page-agent?
alibaba/page-agent
$git clone https://github.com/alibaba/page-agentThe GUI Agent Living in Your Webpage. One script gives any web page its own AI agent.
README.md
| 1 | # Page Agent |
| 2 | |
| 3 | <picture> |
| 4 | <source media="(prefers-color-scheme: dark)" srcset="https://page-agent.github.io/assets/readme/banner-dark.png"> |
| 5 | <img alt="Page Agent Banner" src="https://page-agent.github.io/assets/readme/banner-light.png"> |
| 6 | </picture> |
| 7 | |
| 8 | [](https://github.com/alibaba/page-agent/actions/workflows/main-ci.yml) |
| 9 | [](https://www.npmjs.com/package/page-agent) |
| 10 | [](https://www.npmjs.com/package/page-agent) |
| 11 | [](https://bundlephobia.com/package/page-agent) |
| 12 | [](https://opensource.org/licenses/MIT) |
| 13 | [](http://www.typescriptlang.org/) |
| 14 | [](https://chromewebstore.google.com/detail/page-agent-ext/akldabonmimlicnjlflnapfeklbfemhj) |
| 15 | [](https://github.com/alibaba/page-agent) |
| 16 | |
| 17 | The GUI Agent Living in Your Webpage. One script gives any web page its own AI agent. |
| 18 | |
| 19 | <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> |
| 20 | |
| 21 | 🌐 **English** | [中文](./docs/README-zh.md) |
| 22 | |
| 23 | <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> |
| 24 | |
| 25 | <!-- demo video --> |
| 26 | |
| 27 | [](https://github.com/user-attachments/assets/a1f2eae2-13fb-4aae-98cf-a3fc1620a6c2) |
| 28 | |
| 29 | --- |
| 30 | |
| 31 | ## ✨ Features |
| 32 | |
| 33 | - **🎯 Easy integration** |
| 34 | - No need for `browser extension` / `python` / `headless browser`. |
| 35 | - Just in-page javascript. Everything happens in your web page. |
| 36 | - **📖 Text-based DOM manipulation** |
| 37 | - No screenshots. No multi-modal LLMs or special permissions needed. |
| 38 | - **🧠 Bring your own LLMs** |
| 39 | - Works with most mainstream models, including locally deployed ones. See [supported models](https://alibaba.github.io/page-agent/docs/features/models). |
| 40 | - **🐙 Optional [chrome extension](https://alibaba.github.io/page-agent/docs/features/chrome-extension) for multi-page tasks.** |
| 41 | - And an [MCP Server (Beta)](https://alibaba.github.io/page-agent/docs/features/mcp-server) to control it from outside |
| 42 | |
| 43 | ## 💡 Use Cases |
| 44 | |
| 45 | - **SaaS AI Copilot** — Ship an AI copilot in your product in lines of code. No backend rewrite. |
| 46 | - **Smart Form Filling** — Turn 20-click workflows into one sentence. Perfect for ERP, CRM, and admin systems. |
| 47 | - **Accessibility** — Make any web app accessible through natural language. Voice commands, screen readers, zero barrier. |
| 48 | - **Multi-page Agent** — Extend your own web agent's reach across browser tabs via the [Chrome extension](https://alibaba.github.io/page-agent/docs/features/chrome-extension). |
| 49 | - **MCP** - Allow your agent clients to control your browser. |
| 50 | |
| 51 | ## 🚀 Quick Start |
| 52 | |
| 53 | ### One-line integration |
| 54 | |
| 55 | Fastest way to try PageAgent with our free Demo LLM: |
| 56 | |
| 57 | ```html |
| 58 | <script |
| 59 | src="https://cdn.jsdelivr.net/npm/page-agent@1.12.2/dist/iife/page-agent.demo.js" |
| 60 | crossorigin="anonymous" |
| 61 | ></script> |
| 62 | |
| 63 | <!-- China CDN mirror if y |
People who liked this also viewed
6 picksType
- playwright-mcpPlaywright MCP fork that works with Cloudflare Browser RenderingMCP ServersApr 2026
- Playwright MCPBrowser automation for agents via accessibility snapshotsMCP Servers6 days ago
- chrome-devtools-mcpChrome DevTools for coding agentsMCP ServersJul 2026
- browser-operator-coreBrowser Operator - The AI browser with built in Multi-Agent platform! Open source alternative to ChatGPT Atlas, Perplexity Comet, Dia and Microsoft CoPilot Edge BrowserMCP ServersMar 2026
- fetcher-mcpMCP server for fetch web page content using Playwright headless browser.MCP ServersJan 2026
- mcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browserMCP ServersApr 2025
