browser-use Agent工作流

uvx browser-use install # Run if you don't have Chromium installed

**2. [Optional] Get your API key from [Browser Use Cloud](https://cloud.browser-use.com/new-api-key?utm_source=github&utm_medium=readme-quickstart-api-key):**

🤖 LLM Quickstart

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

<br/>

👋 Human Quickstart

1. Create environment and install Browser-Use with uv (Python>=3.11): ```bash uv init && uv add browser-use && uv sync

💡See [more examples here ↗](https://docs.browser-use.com/examples) and give us a star!

<br/>

🚀 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

<br/>

Demos

.env

BROWSER_USE_API_KEY=your-key

GOOGLE_API_KEY=your-key

ANTHROPIC_API_KEY=your-key

**3. Run your first agent:**

Integrations, hosting, custom tools, MCP, and more on our [Docs ↗](https://docs.browser-use.com)

<br/>

Open Source vs Cloud

<picture> <source media="(prefers-color-scheme: light)" srcset="static/accuracy_by_model_light.png"> <source media="(prefers-color-scheme: dark)" srcset="static/accuracy_by_model_dark.png"> <img alt="BU Bench V1 - LLM Success Rates" src="static/accuracy_by_model_light.png" width="100%"> </picture>

We benchmark Browser Use across 100 real-world browser tasks. Full benchmark is open source: browser-use/benchmark.

Use the Open-Source Agent - You need custom tools or deep code-level integration - We recommend pairing with our cloud browsers for leading stealth, proxy rotation, and scaling - Or self-host the open-source agent fully on your own machines

Use the Fully-Hosted Cloud Agent (recommended) - Much more powerful agent for complex tasks (see plot above) - Easiest way to start and scale - Best stealth with proxy rotation and captcha solving - 1000+ integrations (Gmail, Slack, Notion, and more) - Persistent filesystem and memory

<br/>

FAQ

<details> <summary><b>What's the best model to use?</b></summary>

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. </details>

<details> <summary><b>Should I use the Browser Use system prompt with the open-source preview model?</b></summary>

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. </details>

<details> <summary><b>Can I use custom tools with the agent?</b></summary>

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

from browser_use import Tools

tools = Tools()

@tools.action(description='Description of what this tool does.')
def custom_tool(param: str) -> str:
    return f"Result: {param}"

agent = Agent(
    task="Your task",
    llm=llm,
    browser=browser,
    tools=tools,
)

</details>

<details> <summary><b>Can I use this for free?</b></summary>

Yes! Browser-Use is open source and free to use. You only need to choose an LLM provider (like OpenAI, Google, ChatBrowserUse, or run local models with Ollama). </details>

<details> <summary><b>Terms of Service</b></summary>

This open-source library is licensed under the MIT License. For Browser Use services & data policy, see our Terms of Service and Privacy Policy. </details>

<details> <summary><b>How do I handle authentication?</b></summary>

Check out our authentication examples: - Using real browser profiles - Reuse your existing Chrome profile with saved logins - If you want to use temporary accounts with inbox, choose AgentMail - To sync your auth profile with the remote browser, run curl -fsSL https://browser-use.com/profile.sh | BROWSER_USE_API_KEY=XXXX sh (replace XXXX with your API key)

These examples show how to maintain sessions and handle authentication seamlessly. </details>

<details> <summary><b>How do I solve CAPTCHAs?</b></summary>

For CAPTCHA handling, you need better browser fingerprinting and proxies. Use Browser Use Cloud which provides stealth browsers designed to avoid detection and CAPTCHA challenges. </details>

<details> <summary><b>How do I go into production?</b></summary>

Chrome can consume a lot of memory, and running many agents in parallel can be tricky to manage.

For production use cases, use our Browser Use Cloud API which handles: - Scalable browser infrastructure - Memory management - Proxy rotation - Stealth browser fingerprinting - High-performance parallel execution </details>

<br/>