Skip to content
AI.info

tools

browser-use

Open-source browser agent framework for automating websites through Python, TypeScript, a CLI, or Browser Use Cloud.

browser-use

Browser Use lets developers build agents that navigate websites, click and type, extract data, handle files, solve CAPTCHAs, and complete multi-step browser tasks. It can run locally with a chosen model or use Browser Use Cloud for hosted browsers and agents.

The project is aimed at developers, automation teams, researchers, and coding agents. The open-source library is MIT-licensed; cloud usage is pay-as-you-go, with browser time, traffic, proxies, and model usage charged separately.

Features

  • Automate websites with an open-source Python and TypeScript agent
  • Run browser tasks through the Browser Use CLI
  • Connect agents to local or cloud browsers
  • Use hosted browser agents through an API
  • Extract data and complete multi-step web workflows
  • Support stealth browsers, CAPTCHA solving, and residential proxies
  • Handle files, profiles, recordings, and structured output
  • MIT license

Use cases

  • Automate website navigation, form filling, and booking
  • Extract structured data from websites and return files
  • Run browser tasks from Claude Code, Codex, Cursor, or other agents
  • Build recurring browser workflows with the Python library
  • Use hosted stealth browsers for automation at scale

Pros

    Cons

      Latest updates

      • 0.13.14: Python agent and integration updates (0.13.14)

        Adds OpenAI browser tools and a shared Bash helper; improves browser observations, forms, file access, recovery, and Cloud SDK V4 imports.

      • 0.13.13: OpenAI browser tools and Cloud fixes (0.13.13)

        Added an OpenAI browser-tool driver with 18 default tools and six optional actions; fixed Cloud tab URL and scaled-display alignment issues.

      • 0.13.12: OpenAI browser tools (0.13.12)

        Added OpenAI browser tools backed by Browser Use Actor, supporting local browsers, Browser Use Cloud, and connected BrowserSessions.

      • 0.13.11 (0.13.11)

        Added Browser Use toolsets for Claude and tiny binary image creation with filesystem.write_file.

      • 0.13.10 (0.13.10)

        Upgraded dependencies, migrated to MCP Python SDK 2.1.1, and report unknown MCP tool calls as application errors.

      Capabilities

      • Command line — “Path 2: CLI : Automate your own browser tasks.” source
      • Choice of models — “Run the Browser Use agent locally from Python, with your choice of model and a local or cloud browser:” source
      • Self-hosted — “You can also host the Python library and browsers on your own infrastructure.” source
      • No code retained — “Zero data retention” source
      • API — “Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.” source
      • Official SDKs — “Cloud SDK Integrate Browser Use Cloud into your application.” source
      • Runs models for you — “Use our model with your own agent. Prices per 1M tokens.” source
      • Builds agents and workflows — “Fully Hosted Cloud : Send tasks through the API and let Browser Use run the agent, browser, and infrastructure.” source

      Get it

      Pricing

      Prices checked
      2026-10-24

      Pay as you go

      • $0.02 / hour
      • Model + 20 %
      • No subscription
      • Credits never expire
      • Browser agents: model + 20 %
      • Web agents, plus browser time and traffic
      Official website