Logo
Deploy Now

Categories

Self-Hosted Web Scraping AI Agents Browser Automation API Platform Headless Browser DevTools

Stars

7,524

Forks

968

Watchers

20

Developer links

Last Updated: 08-22-2026 03:19 PM (UTC)

Steel Browser

With over 7,400 GitHub stars and benchmarked at 0.89 seconds average session lifecycle — 1.7x to 9x faster than competing browser automation platforms — Steel Browser delivers production-grade headless Chrome infrastructure purpose-built for AI agents that need to interact with the modern web. The TypeScript-based server exposes a REST API providing on-demand browser sessions with full CDP (Chrome DevTools Protocol) access, allowing connections from Puppeteer, Playwright, or Selenium through standard WebSocket endpoints without framework lock-in. Each session maintains persistent state including cookies, localStorage, IndexedDB, and authentication credentials across requests, enabling stateful multi-step agent workflows that survive session restarts. Built-in anti-detection includes stealth plugins, browser fingerprint randomization, and configurable user-agent rotation, while the proxy chain manager handles IP rotation through residential, datacenter, or custom proxy pools. CAPTCHA solving integrates natively so agents encounter fewer blocking interrupts during autonomous navigation. The Session Viewer provides real-time WebRTC-streamed visual debugging of live sessions and playback of recorded sessions with full network request logging. Browser Tools APIs convert any page to clean Markdown, readability-optimized text, PDF documents, or high-resolution screenshots with a single API call. The MCP Server integration exposes Steel sessions as tools accessible to Claude, Cursor, and other Model Context Protocol-compatible AI agents. Deploy via Docker with a single container or use Docker Compose for production configurations with automatic resource cleanup and session lifecycle management. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Steel Browser
Steel Browser
Steel Browser
Steel Browser

Benefits

  • Purpose-Built for AI Agent Browsing
  • Sessions maintain persistent authentication, cookies, and localStorage across requests, enabling stateful multi-step agent workflows that survive restarts and handle modern SPAs.
  • Framework-Agnostic Browser Control
  • Standard WebSocket CDP endpoints accept connections from Puppeteer, Playwright, or Selenium with Node and Python SDKs providing fully typed API access.
  • Production Anti-Detection Infrastructure
  • Stealth plugins, fingerprint randomization, proxy rotation through residential IP pools, and native CAPTCHA solving automatically minimize blocking during autonomous web navigation.
  • Real-Time Session Debugging
  • WebRTC-streamed Session Viewer shows live browser state with full network request logging, recorded session playback, and automatic screenshot capture for audit trails.

Features

  • Headless Chrome Sessions API
  • REST API creates on-demand browser sessions with full CDP access, configurable timeouts up to 24 hours, and automatic resource cleanup on expiration.
  • Persistent Session State
  • Cookies, localStorage, IndexedDB, and authentication credentials persist across requests using browser profiles that survive session restarts.
  • Anti-Bot Stealth Suite
  • Stealth plugins, fingerprint randomization, user-agent rotation, and proxy chain management with residential IP pools defeat bot detection systems.
  • Page Content Extraction
  • Single API calls convert pages to clean Markdown, readability-optimized text, PDF documents, or high-resolution screenshots without additional tooling.
  • MCP Server Integration
  • Steel MCP Server exposes browser sessions as tools for Claude, Cursor, and other AI agents supporting the Model Context Protocol standard.