Skip to content
New this week26 prompts for Sora, Veo and Runway video workflows.
Explore video prompts→
AIPrompt123Prompt library

Search AIPrompt123

Search prompts, categories, platforms and repositories

AgentsPythonMIT

browser-use/browser-use

Browser-use connects a language model to a real browser so an agent can navigate, click, type and extract information. It is powerful for repetitive web tasks and testing. Production use requires careful scoping, domain allowlists and confirmation for anything that submits data or spends money.

72.0k stars8.7k forks290 contributors320 open issuesUpdated

What it does

  • Controls a browser through an LLM-driven agent loop.
  • Extracts page structure and interacts with elements.
  • Supports local and cloud browser sessions.

Key features

  • Python API with multiple model backends.
  • Vision and DOM-based element selection.
  • Custom actions and sensitive-data handling.
  • Replay and debug tooling.

How to install it

Commands are copied from the project documentation at the time of review. Check the repository for the current version.

Python
pip install browser-use
playwright install

Alternatives to consider

browser-use is a strong default for agents, but the right choice depends on your stack, licence constraints and how much control you need. These are the projects we compare most often.

PlaywrightStagehandOpenHands

Prompts that pair with it

All prompts →
Verified Knowledge · FAQ

browser-use FAQ

Adoption questions we hear most often about this project.

Related repositories

Agents · TypeScript

An early autonomous agent platform that now offers a visual builder for AI workflows.

171.0k45.2kMIT (platform: Polyform Shield)

Agents · Python

An open platform for AI software agents that can modify code, run commands and browse.

64.0k7.7kMIT

Agents · Python

A programming framework for multi-agent conversations and event-driven agent systems.

51.0k7.6kMIT