Browser Automation Agent

---

🌤️ Want to skip the setup? Use our cloud for faster, scalable, stealth-enabled browser automation!

🤖 LLM Quickstart

1. Direct your favorite coding agent (Cursor, Claude Code, etc) to Agents.md
2. Prompt away!

👋 Human Quickstart

1. Create environment and install Browser-Use with uv (Python>=3.11):

uv init && uv add browser-use && uv sync
# uvx browser-use install  # Run if you don't have Chromium installed

2. [Optional] Get your API key from Browser Use Cloud:

# .env
BROWSER_USE_API_KEY=your-key
# GOOGLE_API_KEY=your-key
# ANTHROPIC_API_KEY=your-key

3. Run your first agent:

from browser_use import Agent, Browser, ChatBrowserUse
# from browser_use import ChatGoogle  # ChatGoogle(model='gemini-3-flash-preview')
# from browser_use import ChatAnthropic  # ChatAnthropic(model='claude-sonnet-4-6')
import asyncio

async def main():
    browser = Browser(
        # use_cloud=True,  # Use a stealth browser on Browser Use Cloud
    )

    agent = Agent(
        task="Find the number of stars of the browser-use repo",
        llm=ChatBrowserUse(),
        # llm=ChatGoogle(model='gemini-3-flash-preview'),
        # llm=ChatAnthropic(model='claude-sonnet-4-6'),
        browser=browser,
    )
    await agent.run()

if __name__ == "__main__":
    asyncio.run(main())

Check out the library docs and the cloud docs for more!

Demos

📋 Form-Filling

Task = "Fill in this job application with my resume and information."

Example code ↗

🍎 Grocery-Shopping

Task = "Put this list of items into my instacart."

https://github.com/user-attachments/assets/a6813fa7-4a7c-40a6-b4aa-382bf88b1850

Example code ↗

💻 Personal-Assistant.

Task = "Help me find parts for a custom PC."

https://github.com/user-attachments/assets/ac34f75c-057a-43ef-ad06-5b2c9d42bf06

Example code ↗

💡See more examples here ↗ and give us a star!

🚀 Template Quickstart

Want to get started even faster? Generate a ready-to-run template:

uvx browser-use init --template default

This creates a browser_use_default.py file with a working example. Available templates:

• default - Minimal setup to get started quickly
• advanced - All configuration options with detailed comments
• tools - Examples of custom tools and extending the agent

You can also specify a custom output path:

uvx browser-use init --template default --output my_agent.py

💻 CLI

Fast, persistent browser automation from the command line:

browser-use open https://example.com    # Navigate to URL
browser-use state                       # See clickable elements
browser-use click 5                     # Click element by index
browser-use type "Hello"                # Type text
browser-use screenshot page.png         # Take screenshot
browser-use close                       # Close browser

The CLI keeps the browser running between commands for fast iteration. See CLI docs for all commands.

Claude Code Skill

For Claude Code, install the skill to enable AI-assisted browser automation:

mkdir -p ~/.claude/skills/browser-use
curl -o ~/.claude/skills/browser-use/SKILL.md \
  https://raw.githubusercontent.com/browser-use/browser-use/main/skills/browser-use/SKILL.md

Integrations, hosting, custom tools, MCP, and more on our Docs ↗

FAQ

We optimized ChatBrowserUse() specifically for browser automation tasks. On avg it completes tasks 3-5x faster than other models with SOTA accuracy.

Pricing (per 1M tokens):

• Input tokens: $0.20
• Cached input tokens: $0.02
• Output tokens: $2.00

For other LLM providers, see our supported models documentation.

Yes. If you use ChatBrowserUse(model='browser-use/bu-30b-a3b-preview') with a normal Agent(...), Browser Use still sends its default agent system prompt for you.

You do not need to add a separate custom "Browser Use system message" just because you switched to the open-source preview model. Only use extend_system_message or override_system_message when you intentionally want to customize the default behavior for your task.

If you want the best default speed/accuracy, we still recommend the newer hosted bu-* models. If you want the open-source preview model, the setup stays the same apart from the model= value.

Yes! You can add custom tools to extend the agent's capabilities:

from browser_use import Tools

tools = Tools()

@tools.action(descripti