browser-use
Open-source Python library enabling AI agents to interact with web browsers.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 118.1k
- Source
- mcp-github
- Repository
- github.com/browser-use/browser-use
Overview
Browser Use is an open-source Python library that allows AI agents to use browsers like humans: opening pages, clicking elements, typing text, filling out forms, and extracting data. It also offers Browser Use Cloud service, providing private browsers, CAPTCHA solving, and residential proxies for just $0.02 per hour. Additionally, a managed proxy API is available. Ideal for developers and enterprises needing automated web interactions.
Capabilities
- ▪Open web pages
- ▪Click elements
- ▪Input text
- ▪Fill out forms
- ▪Extract data
- ▪Solve CAPTCHA
Use cases
Setup
Install or upgrade browser-use to the latest stable version using Python 3.12, run `browser-use skill install` to register the skill, and connect it to your browser.
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with Browser Use Cloud?
Get the quick start guide at https://docs.browser-use.com/cloud/agent/quickstart.
Which LLMs are supported?
Supports multiple LLMs including Claude Code, Codex, Hermes, OpenClaw, and more.
Related skills
coop-anything
An MCP server that converts single-player games into cooperative multiplayer experiences.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.