# Browser Use — AI Browser Automation

> Open-source Python library for AI-driven browser automation. Works with Claude, GPT, and Gemini to fill forms, scrape data, and navigate websites.

## Install

Save as a script file and run:

## Quick Use

```bash
uv init && uv add browser-use && uv sync
```

```python
from browser_use import Agent, Browser, ChatBrowserUse
import asyncio

async def main():
    agent = Agent(
        task="Find the price of the mass of the largest meteorite found this year",
        llm=ChatBrowserUse(),
        browser=Browser(),
    )
    await agent.run()

asyncio.run(main())
```

---

## Intro

Browser Use makes websites accessible to AI agents. Give it a task in natural language, and it controls a real browser — clicking, typing, scrolling, extracting data — using a DOM + Vision hybrid approach. Works with Claude, GPT, Gemini, and local models. 84,000+ GitHub stars, the standard open-source solution for AI browser automation.

---

## Key Features

- **Multi-model support**: Claude, GPT, Gemini, ChatBrowserUse (optimized), local models
- **Real browser control**: Click, type, scroll, screenshot, navigate
- **Form automation**: Job applications, data entry, checkout flows
- **Web research**: Find, compile, and summarize information
- **Custom tools**: Extensible architecture for specialized tasks
- **CLI interface**: Persistent browser sessions from terminal

## Supported Models

| Model | Best For |
|-------|---------|
| ChatBrowserUse | Browser automation (purpose-built, cheapest) |
| Claude Sonnet | Complex reasoning tasks |
| Gemini Flash | Fast, cost-effective tasks |
| Local models | Privacy-sensitive automation |

## CLI Usage

```bash
browser-use open https://example.com   # Navigate
browser-use state                       # See clickable elements
browser-use click 5                     # Click element #5
browser-use type "Hello world"          # Type text
browser-use screenshot output.png       # Capture page
```

## Project Templates

```bash
# Generate a starter project
uvx browser-use init --template default
# Templates: default, advanced, tools
```

---



### FAQ

**Q: What is Browser Use?**
A: Open-source Python library for AI-driven browser automation. Works with Claude, GPT, and Gemini to fill forms, scrape data, and navigate websites.

**Q: How do I install Browser Use?**
A: Check the Quick Use section above for step-by-step installation instructions. Most assets can be set up in under 2 minutes.

## Source & Thanks

> Created by [browser-use](https://github.com/browser-use). Licensed under MIT.
> [browser-use](https://github.com/browser-use/browser-use) — ⭐ 84,800+
> Docs: [docs.browser-use.com](https://docs.browser-use.com)

Thanks to the Browser Use team for building the leading open-source AI browser automation library.

---
Source: https://tokrepo.com/en/workflows/52993269-0cbd-49e2-bb6a-54f429a5feab
Author: Script Depot