browser-use/browser-use

What it solves

Browser Use allows AI agents to navigate and interact with the web exactly like a human would. It solves the difficulty of automating complex web tasks—such as booking appointments, handling CAPTCHAs, or extracting data from dynamic sites—by giving LLMs a way to control a web browser.

How it works

It provides a framework that connects a Large Language Model (LLM) to a browser instance. The agent receives a task in plain language, analyzes the page, and executes actions to achieve the goal. It can be used as a Python library for custom application development, a CLI to give existing agents (like Claude Code or Cursor) browser access, or via a fully hosted cloud API that manages both the agent and the browser infrastructure.

Who it’s for

This tool is designed for developers building AI agents, automation engineers looking to replace brittle scrapers with LLM-driven navigation, and users who want to integrate browser control into their existing AI workflows.

Highlights

• Flexible Deployment: Available as an open-source Python library, a CLI tool, or a managed cloud service.
• Model Agnostic: Supports various models including OpenAI, Anthropic, Google, and a specialized automation model called BU2.
• Extensible: Allows developers to register custom tools (Python functions) that the agent can call during its browser session.
• Stealth Capabilities: Offers cloud browsers with residential proxies and stealth features to reduce bot detection and solve CAPTCHAs.