# Browser Use Browser Use is an open-source [[Python]] library that enables [[AI Agents]] to control web browsers through natural language instructions. It connects [[Large Language Models (LLMs)]] to browser automation powered by [[Playwright]], allowing agents to navigate pages, click elements, fill forms, extract data, and perform multi-step web workflows autonomously. It supports multiple LLM providers including [[OpenAI]], [[Anthropic]], Google Gemini, AWS Bedrock, Groq, Ollama, and any OpenAI-compatible API. It also offers its own optimized model (`ChatBrowserUse`) designed specifically for browser automation tasks, claiming 3-5x faster task completion than general-purpose models. The library integrates with [[LangChain]] and provides a simple agent-based API where you define a task in plain text and the agent handles browser interaction. It supports custom browser configurations, persistent sessions, and cookie management. Browser Use also offers a commercial cloud platform (Browser Use Cloud) with stealth browsers, CAPTCHA solving, and managed infrastructure for production deployments. The open-source library can connect to cloud-hosted browsers via sandboxes for easier deployment. See also: [[Browser Use CLI]] for the command-line interface companion tool. ## References - https://docs.browser-use.com - https://github.com/browser-use/browser-use ## Related - [[AI Agents Web Browsing]] - [[Vercel Agent Browser]] - [[Browser Use CLI]] - [[Playwright]] - [[Scrapling]] - [[AI Agents]] - [[AI Agent Skills]] - [[Agentic loops]] - [[LangChain]] - [[Python]] - [[Large Language Models (LLMs)]] - [[WebMCP]]