Steel Browser

Active
GitHub TypeScript Apache-2.0

Description

Steel Browser is an open-source browser sandbox purpose-built for AI agents and applications. It provides a full browser API with session management, proxy integration, and built-in anti-detection, enabling web automation without infrastructure headaches.

Key Features

  • Full Browser Control — Puppeteer and CDP-based complete control over Chrome instances with Puppeteer, Playwright, or Selenium support
  • Session Management — maintains browser state, cookies, and local storage across requests for persistent browsing
  • Anti-Detection — built-in stealth plugins and fingerprint management to avoid bot detection
  • Proxy Support — built-in proxy chain management for IP rotation and geographic routing
  • Browser Tools API — quick conversion of pages to markdown, readability text, screenshots, or PDFs
  • Extension Support — load custom Chrome extensions for enhanced browser functionality

Use Cases

💡 Build AI web agents that browse, interact with, and extract data from websites
💡 Automate web scraping tasks with session persistence and anti-detection
💡 Create browser automation tools with proxy rotation for large-scale data collection
💡 Develop QA testing pipelines with full browser state management
💡 Power Lovable-style app builders with live web browsing capabilities

Quick Start

Run with Docker: docker run -p 3000:3000 -p 9223:9223 ghcr.io/steel-dev/steel-browser. Access the API at localhost:3000 and UI at localhost:3000/ui. Or deploy to Railway/Render with one-click buttons. SDKs available for Python and Node.js.

Related Projects

Related Articles