AI agent browser automation — open pages, click, type, fill forms, and extract data.
Give your AI agent a real browser it can control. browser-use combines Playwright with an LLM backend so your agent can see pages, make decisions, and take action — all from a Python script or your favorite AI coding tool.
Install or upgrade browser-use to the latest stable version with uv using Python 3.12. After installation, create a .env file with your LLM API key, then verify the setup by running a simple browser task that opens a page and extracts the title.
Start with the default prompt. Use the environment options below for install commands tailored to your setup.
Pick the install command and prompt that matches where you run your AI agent.
Install or upgrade browser-use to the latest stable version with uv using Python 3.12. After installation, help me create a .env file with my LLM API key, then verify the setup by opening https://web-access.pro and summarizing the page.
Install or upgrade browser-use to the latest stable version with uv using Python 3.12. After installation, help me create a .env file with my LLM API key, then verify the setup by opening https://web-access.pro and summarizing the page.
Install browser-use from https://github.com/browser-use/browser-use. Use uv add browser-use with Python 3.12, or pip install browser-use. Set up an .env file with your LLM API key, then verify the setup by opening a test page.
Prefer to type the commands yourself? Here are the exact lines.
uv add browser-use
Requires Python 3.11+. uv manages the virtual environment and dependencies automatically.
pip install browser-use
Works with any Python 3.11+ environment. Consider using a virtual environment first.
After installation and API key setup, run one simple page-read task to confirm everything works.
Use browser-use to open https://web-access.pro and summarize what the page helps users do.
Please use browser-use for this setup check. Open https://web-access.pro, read the page content, and summarize what the site helps users install, verify, and do next. If the page cannot be read, check that Python 3.11+ is active and the .env file has a valid API key.
A working setup should return a short summary of the page. If it fails, double-check your Python version and LLM API key.
Once the setup works, try a small browser research task.
Use browser-use to search for "browser automation Python library 2025" on Google, open the first two results, and return a short summary with source links.
You should get a source-backed summary with clickable links, proving your agent can navigate, read, and report on real web pages.
What you need before installing browser-use.
python --version..env file as OPENAI_API_KEY or ANTHROPIC_API_KEY.browser-use is a Python library that lets AI agents control a real browser. It combines Playwright for browser automation with an LLM (like GPT-4 or Claude) to make smart decisions — open pages, click elements, type text, fill forms, scroll, and extract structured data.
Use uv add browser-use (recommended, requires Python 3.11+) or pip install browser-use. You also need to set up an LLM API key in a .env file. The library uses Playwright under the hood, so browser binaries are installed automatically on first run.
Yes. browser-use requires an LLM to make decisions about what to click, type, and extract. Set your API key (OpenAI, Anthropic, or compatible) in a .env file. Without an API key, the agent cannot reason about page content and actions.
Python 3.11 or higher is required. Check with python --version. We recommend Python 3.12 for the best compatibility with the latest browser-use releases and the uv package manager.
browser-use can open any URL, click buttons and links, type into input fields, fill and submit forms, scroll through pages, extract text and structured data, take screenshots, and handle multi-step workflows across multiple pages — all driven by natural language task descriptions.
No. This is an independent setup and usage guide for browser-use users. The official project is available on GitHub at github.com/browser-use/browser-use.
This is an independent setup and usage guide for browser-use users.
The official project is maintained on GitHub. Review the repository before installing or adapting the library in your own environment.
View Source on GitHub