Browser Use: the open-source layer that makes LLMs truly control the browser
In one sentence Browser Use is an open-source Python library enabling GPT-4, Claude and Gemini to reliably control a Chromium browser via Playwright. 30k GitHub stars in the first month. First truly usable browser control layer without custom extensions. Enables reliable web agent tasks on any website.
Making an AI browse the internet seems easy until you actually try. The problems are many: how do you describe the page to the model? How do you handle popups? How do you avoid CAPTCHAs? How do you save state between pages?
Browser Use solves all these problems in a clean Python package. Install the library, write a few lines of code, and you can have your favorite LLM (GPT-4, Claude, Gemini) execute real tasks in the browser: fill forms, make purchases, collect data, navigate web applications.
It requires no custom browser extensions, no special site APIs, works on any modern web page. Behind the scenes it uses Playwright, the industry-standard browser automation tool, but adds a "vision" layer for the model: annotated screenshots, structured DOM, clickable coordinates.
In one month it collects 30,000 GitHub stars, becoming the reference point for anyone who wants to build a web agent. It precedes Anthropic's Computer Use in public availability.
Companies
—
Tools
—
Tags
Sources