browser-use0.7.9
Published
Make websites accessible for AI agents
pip install browser-use
Package Downloads
Authors
Project URLs
Requires Python
<4.0,>=3.11
Dependencies
- aiofiles
>=24.1.0 - aiohttp
==3.12.15 - anthropic
<1.0.0,>=0.58.2 - anyio
>=4.9.0 - authlib
>=1.6.0 - bubus
>=1.5.6 - cdp-use
>=1.4.0 - google-api-core
>=2.25.0 - google-api-python-client
>=2.174.0 - google-auth-oauthlib
>=1.2.2 - google-auth
>=2.40.3 - google-genai
<2.0.0,>=1.29.0 - groq
>=0.30.0 - html2text
>=2025.4.15 - httpx
>=0.28.1 - mcp
>=1.10.1 - ollama
>=0.5.1 - openai
<2.0.0,>=1.99.2 - pillow
>=11.2.1 - portalocker
<3.0.0,>=2.7.0 - posthog
>=3.7.0 - psutil
>=7.0.0 - pydantic
>=2.11.5 - pyobjc
>=11.0; platform_system == "darwin" - pyotp
>=2.9.0 - pypdf
>=5.7.0 - python-dotenv
>=1.0.1 - reportlab
>=4.0.0 - requests
>=2.32.3 - screeninfo
>=0.8.1; platform_system != "darwin" - typing-extensions
>=4.12.2 - uuid7
>=0.1.0 - agentmail
>=0.0.53; extra == "all" - boto3
>=1.38.45; extra == "all" - botocore
>=1.37.23; extra == "all" - click
>=8.1.8; extra == "all" - imgcat
>=0.6.0; extra == "all" - langchain-openai
>=0.3.26; extra == "all" - rich
>=14.0.0; extra == "all" - textual
>=3.2.0; extra == "all" - boto3
>=1.38.45; extra == "aws" - click
>=8.1.8; extra == "cli" - rich
>=14.0.0; extra == "cli" - textual
>=3.2.0; extra == "cli" - anyio
>=4.9.0; extra == "eval" - browserbase
==1.4.0; extra == "eval" - datamodel-code-generator
>=0.26.0; extra == "eval" - hyperbrowser
==0.47.0; extra == "eval" - lmnr
[all]==0.7.10; extra == "eval" - psutil
>=7.0.0; extra == "eval" - agentmail
>=0.0.53; extra == "examples" - botocore
>=1.37.23; extra == "examples" - imgcat
>=0.6.0; extra == "examples" - langchain-openai
>=0.3.26; extra == "examples" - imageio
[ffmpeg]>=2.37.0; extra == "video" - numpy
>=2.3.2; extra == "video"
Enable AI to control your browser
Deutsch | Español | français | 日本語 | 한국어 | Português | Русский | 中文
🤖 Quickstart
With uv (Python>=3.11):
# We ship every day - use the latest version!
uv pip install browser-use
Download chromium using playwright's shortcut:
uvx playwright install chromium --with-deps --no-shell
Create a .env file and add your API key. Don't have one? Start with a free Gemini key.
GEMINI_API_KEY=
Run your first agent:
from browser_use import Agent, ChatGoogle
from dotenv import load_dotenv
load_dotenv()
agent = Agent(
task="Find the number of stars of the browser-use repo",
llm=ChatGoogle(model="gemini-2.5-flash"),
# browser=Browser(use_cloud=True), # Uses Browser-Use cloud for the browser
)
agent.run_sync()
Check out the library docs and cloud docs for more settings.
Demos
Task: Add grocery items to cart, and checkout.
Task: Read my CV & find ML jobs, save them to a file, and then start applying for them in new tabs, if you need help, ask me.
https://github.com/user-attachments/assets/171fb4d6-0355-46f2-863e-edb04a828d04
See more examples and give us a star!
MCP Integration
This gives Claude Desktop access to browser automation tools for web scraping, form filling, and more. See the MCP docs.
{
"mcpServers": {
"browser-use": {
"command": "uvx",
"args": ["browser-use[cli]", "--mcp"],
"env": {
"OPENAI_API_KEY": "sk-..."
}
}
}
}
Tell your computer what to do, and it gets it done.