browser-use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Browser Use is an agent skill that enables AI assistants to interact with websites by opening pages, clicking elements, typing text, and filling forms just like a human would. Developers can integrate it into agents like Claude Code, Codex, or Cursor to automate web-based workflows through simple natural language prompts. It works as both a Python library for programmatic automation and as an installable skill for existing AI agents, supporting multiple LLM providers including OpenAI, Anthropic, Google, and Browser Use's own optimized models. The skill excels at tasks like form completion, data extraction, web scraping, and multi-step browser workflows.
Key Features
Use Cases
- 01Automatically filling out job applications with resume data and personal information
- 02Extracting structured follower data from social media platforms and exporting to CSV
- 03Monitoring websites on a schedule and collecting pricing or inventory data
- 04Comparing products across multiple e-commerce sites and generating comparison tables
- 05Uploading content to platforms like YouTube with automated form completion
- 06Running parallel QA tests across different web applications
Related Skills
View moresuperpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
skills
Public repository for Agent Skills
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
browser-use — FAQ
What is Browser Use and what does it do?+
Browser Use is an agent skill and Python library that lets AI agents control web browsers like humans do—opening pages, clicking buttons, typing, and filling forms. You describe a task in natural language, and the agent completes it autonomously.
How do I install Browser Use as an agent skill?+
Paste the setup prompt into your AI agent (Claude Code, Codex, Cursor, etc.): 'Install or upgrade browser-use to the latest stable version with uv using Python 3.12, run browser-use skill install to register the skill, and connect it to my browser.' The agent will handle the installation automatically.
Which AI clients and agents work with Browser Use?+
Browser Use works with Claude Code, Codex, Cursor, Hermes, OpenClaw, and other AI coding assistants. As a Python library, it integrates with any LLM provider including OpenAI, Anthropic, Google, and Browser Use's own optimized models.
Do I need API keys to use Browser Use?+
Yes, you need an LLM provider API key. You can use a Browser Use Cloud API key, or bring your own from OpenAI (OPENAI_API_KEY), Anthropic (ANTHROPIC_API_KEY), or Google (GOOGLE_API_KEY). Add the key to your .env file.
Is Browser Use free to use?+
Yes, the open-source library is free under the MIT License. You only pay for LLM API usage from your chosen provider (OpenAI, Anthropic, Google, etc.). Browser Use Cloud is a paid hosted service with advanced features like captcha solving and proxy rotation.
What Python version does Browser Use require?+
Browser Use requires Python 3.11 or higher. The recommended installation uses Python 3.12 with uv for best compatibility.
How do I install browser-use?+
Open the source repository on GitHub and follow its README. browser-use is a skill — MCP Agents Market links you directly to the official repo.
Is browser-use free?+
browser-use is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.