--- 🌤️ 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…
---
🌤️ 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
Browser Use 0.13 introduces a new beta agent powered by a Rust core and a browser harness built for current frontier models. It gives the model a real browser/computer action space, persistent tools, and recovery loops inspired by coding agents.
text
Python API -> Rust core -> Browser harness -> Web task done
1. Install Browser Use with the native core runtime (Python>=3.11):
bash
uv add "browser-use[core]"
# or: pip install "browser-use[core]"
browser
The [core] extra installs the native Browser Use runtime for your platform.
# .env
BROWSER_USE_API_KEY=your-key
# GOOGLE_API_KEY=your-key
# ANTHROPIC_API_KEY=your-key
3. Run your first agent:
Browser Use Terminal:bash
uv add "browser-use[core]"
browser
Python Script:
python
from browser_use.beta import Agent, BrowserProfile, ChatBrowserUse
# from browser_use.beta import ChatOpenAI # ChatOpenAI(model='gpt-5.5')
# from browser_use.beta import ChatAnthropic # ChatAnthropic(model='claude-opus-4-8')
import asyncio
async def main():
agent = Agent(
task="Find the number of stars of the browser-use repo",
llm=ChatBrowserUse(model='openai/gpt-5.5'),
# llm=ChatBrowserUse(model='bu-2-0'), # Browser Use's own optimized model
# llm=ChatOpenAI(model='gpt-5.5'),
# llm=ChatAnthropic(model='claude-opus-4-8'), # Sonnet also works well.
browser_profile=BrowserProfile(
headless=False,
allowed_domains=["*.github.com"],
),
)
history = await agent.run()
print(history.final_result())
if __name__ == "__main__":
asyncio.run(main())
Existing Python agent users can keep using from browser_use import Agent. The new Rust-powered beta agent is from browser_use.beta import Agent.
Check out the library docs and the cloud docs for more!
Open Source vs Cloud
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
Demos
📋 Form-Filling
Task = "Fill in this job application with my resume and information."
!Job Application Demo Example code ↗🍎 Grocery-Shopping
Task = "Put this list of items into my instacart."
https://github.com/user-attachments/assets/a6813fa7-4a7c-40a6-b4aa-382bf88b1850
💻 Personal-Assistant.
Task = "Help me find parts for a custom PC."
https://github.com/user-attachments/assets/ac34f75c-057a-43ef-ad06-5b2c9d42bf06
💡See more examples here ↗ and give us a star!
🚀 Template Quickstart
Want to get started even faster? Generate a ready-to-run template:
bash
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 quicklyadvanced- All configuration options with detailed commentstools- Examples of custom tools and extending the agent
bash
uvx browser-use init --template default --output my_agent.py
💻 CLI
Fast, persistent browser automation from the command line:
bash
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](browser_use/skill_cli/README.md) for all commands.
Claude Code Skill
For Claude Code, install the skill to enable AI-assisted browser automation:
bash
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
What's the best model to use?
We optimized ChatBrowserUse() specifically for browser automation tasks. On avg it completes tasks 3-5x faster than other models with SOTA accuracy.
For pricing and other LLM providers, see our supported models documentation.
Can I use Claude / GPT / Gemini through ChatBrowserUse?
Yes. ChatBrowserUse accepts provider-prefixed model ids, so a single BROWSER_USE_API_KEY reaches all of them — no separate OpenAI/Anthropic/Google keys required:
python
from browser_use import Agent, ChatBrowserUse
llm = ChatBrowserUse(model='anthropic/claude-sonnet-4-6') # or 'openai/gpt-5.5', 'google/gemini-3-pro'
agent = Agent(task='...', llm=llm)
For the best speed and cost we still recommend the default bu-* models.
Should I use the Browser Use system prompt with the open-source preview model?
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.
Can I use custom tools with the agent?
Yes! You can add custom tools to extend the agent's capabilities:
python
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,
)
Can I use this for free?
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).
Terms of Service
This open-source library is licensed under the MIT License. For Browser Use services & data policy, see our Terms of Service and Privacy Policy.
How do I handle authentication?
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.
How do I solve CAPTCHAs?
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.
How do I go into production?
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
Tell your computer what to do, and it gets it done.

   

Made with ❤️ in Zurich and San Francisco
-
browser-use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Python ★ 100k 14h agoExplain → -
web-ui
🖥️ Run AI Agent in your browser.
Python ★ 16k 1mo agoExplain → -
browser-harness
Browser Harness | Self-healing harness that enables LLMs to complete any task.
Python ★ 15k 1h agoExplain → -
video-use
Edit videos with coding agents
Python ★ 10.0k 1mo agoExplain → -
workflow-use
⚙️ Create and run workflows (RPA 2.0)
Python ★ 4.1k 1d agoExplain → -
macOS-use
Make Mac apps accessible for AI agents
Python ★ 2.0k 1y agoExplain → -
awesome-prompts
Table of awesome Browser Use prompts
★ 929 1y agoExplain → -
vibetest-use
Vibetest MCP - automated QA testing using Browser-Use agents
Python ★ 804 9mo agoExplain → -
agent-sdk
No description.
Python ★ 686 2mo agoExplain → -
desktop
Browser Use Desktop App
TypeScript ★ 602 18d agoExplain → -
terminal
Terminal UI to get stuff done in the browser
Rust ★ 571 1d agoExplain → -
qa-use
No description.
TypeScript ★ 563 10mo agoExplain → -
browser-harness-js
Self-healing browser harness that enables LLMs to complete any task
TypeScript ★ 464 2mo agoExplain → -
bux
Browser Use Box: a 24/7 Claude Code agent for Playwright-style browser automation with Browser Use Cloud, Telegram, and a real browser on any box you own.
Python ★ 388 3d agoExplain → -
cdp-use
🩹Pure CDP but type-safe in Python
Python ★ 298 9d agoExplain → -
browsercode
The browser-native agent framework
TypeScript ★ 202 1d agoExplain → -
awesome-projects
List of Open Source projects built on Browser Use
★ 128 9mo agoExplain → -
bubus
📢 Production-ready python event bus library with support for async and sync handlers, forwarding betwen busses w/ parent event tracking + loop prevention, FIFO and concurrency options, and WAL persistence. Powers the browser-use library.
Python ★ 114 1mo agoExplain → -
benchmark
No description.
Python ★ 101 28d agoExplain → -
eval
No description.
Jupyter Notebook ★ 44 1y agoExplain → -
n8n-nodes-browser-use
No description.
TypeScript ★ 42 1mo agoExplain → -
contact-use
✉️ Use the power of browser-use to contact any person or organization... by any means necessary
HTML ★ 36 10mo agoExplain → -
browser-agent-template
Fork-and-deploy Vercel eve agent that browses the web with a Browser Use cloud browser.
TypeScript ★ 32 3d agoExplain → -
browser-use-node ▣
Browser Use Node SDK
TypeScript ★ 30 3mo agoExplain → -
stress-tests
A collection of particularly difficult test scenarios for evaluating browser-use.
HTML ★ 27 1mo agoExplain → -
agent-studio
No description.
TypeScript ★ 27 10mo agoExplain → -
template-library
Template library for browser-use CLI
Python ★ 23 1mo agoExplain → -
online-mind2web
No description.
Python ★ 18 2mo agoExplain → -
sdk
Browser Use Cloud SDK
TypeScript ★ 16 10h agoExplain → -
chat-ui-example
AI chat app using Browser Use v3 SDK
TypeScript ★ 15 1mo agoExplain → -
browser-use-python ▣
Browser Use Python SDK
Python ★ 15 3mo agoExplain → -
nicehack69
The nicest hackaton | Browser Use hits 69k⭐
★ 12 9mo agoExplain → -
go-harnessless
Go rewrite of harnessless: daemon-based Chrome DevTools Protocol bridge with goroutines, channels, and sync.RWMutex for concurrent browser automation
Go ★ 10 2mo agoExplain → -
gemini-demo
demo of gemini-3 filling out a mock application form
Python ★ 9 1mo agoExplain → -
docs ▣
No description.
MDX ★ 9 1y agoExplain → -
webagents.md
Let websites expose tools for AI agents to call directly in the browser.
Python ★ 9 4mo agoExplain → -
browser-use-examples
No description.
TypeScript ★ 8 1mo agoExplain → -
profile-use-releases
No description.
★ 5 2mo agoExplain → -
cc_compaction
No description.
Python ★ 4 2mo agoExplain → -
vc-use
No description.
★ 4 11mo agoExplain → -
mix-eval-go
Go-based evaluation orchestrator for running Mix Eval tasks using browser automation agents
Go ★ 3 4mo agoExplain → -
.github
No description.
★ 2 7mo agoExplain → -
browser-use-rsi
No description.
Python ★ 2 9mo agoExplain → -
plugins
Browser Use plugins for coding agents (browser-harness, video-use)
★ 1 2d agoExplain → -
media
No description.
Python ★ 1 1mo agoExplain → -
evaluation-endpoint
A way to connect external apps to internal evaluations in a way that keeps sensitive data private
★ 1 11mo agoExplain → -
eve
Give a Vercel eve agent a Browser Use cloud browser — npm package + scaffold.
TypeScript ★ 0 3d agoExplain →
No repos match these filters.