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: 15 days 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 (6 months ago)
- Default Branch: main
- Last Pushed: 2026-03-06T20:50:35.000Z (21 days ago)
- Last Synced: 2026-03-06T22:47:01.720Z (21 days ago)
- Topics: agent, ai, ai-agents, browser-automation, javascript, typescript, ui-automation, web
- Language: TypeScript
- Homepage: https://alibaba.github.io/page-agent/
- Size: 1.7 MB
- Stars: 862
- Watchers: 4
- Forks: 82
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: docs/CODE_OF_CONDUCT.md
- Agents: AGENTS.md
Awesome Lists containing this project
- AiTreasureBox - alibaba/page-agent - 03-09_2442_532](https://img.shields.io/github/stars/alibaba/page-agent.svg)|JavaScript in-page GUI agent. Control web interfaces with natural language.| (Repos)
README
# Page Agent
[](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)
The GUI Agent Living in Your Webpage. Control web interfaces with natural language.
π **English** | [δΈζ](./docs/README-zh.md)
π π Demo | π Documentation | π’ Join HN Discussion | π Follow on X
---
## β¨ Features
- **π― Easy integration**
- No need for `browser extension` / `python` / `headless browser`.
- Just in-page javascript. Everything happens in your web page.
- **π Text-based DOM manipulation**
- No screenshots. No multi-modal LLMs or special permissions needed.
- **π§ Bring your own LLMs**
- **π¨ Pretty UI with human-in-the-loop**
- **π Optional [chrome extension](https://alibaba.github.io/page-agent/docs/features/chrome-extension) for multi-page tasks.**
## π‘ Use Cases
- **SaaS AI Copilot** β Ship an AI copilot in your product in lines of code. No backend rewrite.
- **Smart Form Filling** β Turn 20-click workflows into one sentence. Perfect for ERP, CRM, and admin systems.
- **Accessibility** β Make any web app accessible through natural language. Voice commands, screen readers, zero barrier.
- **Multi-page Agent** β Extend your own agent's reach across browser tabs with the optional [chrome extension](https://alibaba.github.io/page-agent/docs/features/chrome-extension).
## π Quick Start
### One-line integration
Fastest way to try PageAgent with our free Demo LLM:
```html
```
> **β οΈ For technical evaluation only.** This demo CDN uses our free [testing LLM API](https://alibaba.github.io/page-agent/docs/features/models#free-testing-api). By using it, you agree to its [terms](https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md).
| Mirrors | URL |
| ------- | ---------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.5.7/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.5.7/files/dist/iife/page-agent.demo.js |
### NPM Installation
```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')
```
For more programmatic usage, see [π Documentations](https://alibaba.github.io/page-agent/docs/introduction/overview).
## π€ Contributing
We welcome contributions from the community! Follow our instructions in [CONTRIBUTING.md](CONTRIBUTING.md) for setup and guidelines.
Please read [Code of Conduct](docs/CODE_OF_CONDUCT.md) before contributing.
Contributions generated entirely by bots or agents without substantial human involvement will not be accepted, and bot accounts may be blocked.
## π Acknowledgments
This project builds upon the excellent work of **[`browser-use`](https://github.com/browser-use/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
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.
Third-party dependencies and their licenses can be found in the package.json
file and in the node_modules directory after installation.
```
## π License
[MIT License](LICENSE)
---
**β Star this repo if you find PageAgent helpful!**
