Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

browser-use

browser-use• Pinned

browser-use: An open-source Python library for AI browser agents that operate real browsers through a persistent Python REPL and raw Chrome DevTools Protocol.

What problem it solves

AI agents need a reliable way to perform browser tasks such as finding availability, selecting options, handling CAPTCHAs, and completing forms. Developers also need flexibility to run the agent locally or through hosted infrastructure while choosing their model, browser mode, tools, and output format.

Key features

  • Persistent Python agent runtime — The model writes Python in a persistent REPL, receives browser output, and completes tasks through a compact agent loop built on Pydantic AI.

    Source: README

  • Local and cloud browser options — Agents can drive a fresh local Chromium, attach to an open Chrome, or use a Browser Use Cloud browser.

    Source: README

  • Model choice and structured output — Users can select gateway models, built-in Anthropic and Google integrations, compatible model strings, or their own OpenAI-compatible endpoint. Agents can return data matching a supplied schema.

    Source: README

  • Browser controls for sensitive tasks — The library provides domain restrictions, secret handling, uploads, downloads, follow-up tasks, and custom tools for application-specific workflows.

    Source: README

  • CLI and hosted-agent access — The project provides a CLI that gives existing agents browser access and a fully hosted path for submitting tasks through an API.

    Source: README

Quick start

Copied verbatim from the project's README.

uv init --python 3.12 my-agent && cd my-agent
uv add 'browser-use==1.0.2'
export BROWSER_USE_API_KEY=bu_...    # get one at https://cloud.browser-use.com/new-api-key
python3 -m venv .venv && source .venv/bin/activate
pip install 'browser-use==1.0.2'
export BROWSER_USE_API_KEY=bu_...
from browser_use import Agent

result = Agent('Find the number of stars of the browser-use repo').run_sync()
print(result.final_result())

Who it may suit

This may suit Python developers building AI agents that interact with websites, as well as existing coding agents that need browser access through the CLI.

Topics to discuss

  • Which local and hosted browser workflows should receive more examples?

  • How should domain restrictions and secret handling be documented for production use?

  • Which custom tools and structured-output patterns would help most community projects?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/browser-use/browser-use#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/browser-use/browser-use

Comments

…