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

Strengths & Limitations

✅ Strengths

• Actively maintained, recent updates
• High community interest (7.6k stars)
• Permissive open-source license (Apache-2.0)
• Responsive to issues, low backlog

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.

Visit GitHub Visit Website

Related Projects

AIPex

1.2k · TypeScript

Active A

AI browser automation assistant as a Chrome extension, privacy-first with MCP support, alternative to Claude Chrome and Manus Browser Operator

browser-automationchrome-extensionmcp +2

· Zero-migration browser automation — runs in your existing Chrome/Edge browser, no new app to install
· Privacy-first BYOK model — your data never leaves your machine, bring your own API key
· MCP protocol support — 30+ browser automation tools accessible via Model Context Protocol

View on GitHub

MCP Playwright

5.6k · TypeScript

Stale B

Playwright Model Context Protocol server for automating browsers and APIs in Claude Desktop, Cline, Cursor IDE and other AI coding tools

mcpplaywrightbrowser-automation +2

· MCP server enabling LLMs to interact with real browser environments via Playwright for web automation, scraping, and testing
· 143 real device presets for accurate emulation including iPhone, iPad, Pixel, Galaxy and desktop browsers
· Automatic browser binary installation — Chromium, Firefox, and WebKit downloaded on first use with no manual setup

View full details → View on GitHub

HyperAgent

1.6k · TypeScript

Stale C

HyperAgent is a Playwright-based AI browser automation framework offering high-level APIs like page.ai(), page.perform(), and page.extract(). It features built-in MCP client support and action caching, enabling AI agents to browse, interact, and extract data using natural language.

browser-automationplaywrightai-agent +3

· Natural language AI commands drive browser automation, replacing brittle scripts
· Three-tier API system: page.ai(), page.perform(), page.extract() for simple to complex scenarios
· Built-in MCP client connects to tools like Composio for full workflow orchestration

View on GitHub

Camofox Browser

9.0k · JavaScript

Active A

Camofox Browser is a headless browser automation server powered by Camoufox, a Firefox fork with C++-level fingerprint spoofing. It bypasses Google, Cloudflare, and most bot detection, providing token-efficient accessibility snapshots and stable element references for AI agents.

anti-detectionbrowser-automationcamoufox +3

· C++ level fingerprint spoofing bypassing bot detection
· Stable element references (e1, e2, e3) for reliable interaction
· Token-efficient accessibility snapshots (~90% smaller than HTML)

View full details → View on GitHub

Web Scraping反爬Browser Fingerprint

Anti-Bot and Browser Fingerprinting: Modern Web Scraping Strategies

A systematic deep dive into modern web scraping anti-bot defenses: HTTP layer (curl_cffi for TLS fingerprint), browser layer (Playwright plus stealth), behavior layer (human behavior simulation), covering Cloudflare bypass, proxy IP rotation, Scrapling selector self-healing, and legal compliance boundaries.

Browser AgentWeb 自动化Playwright

Browser Agents in Practice: Architecture and Pitfalls of AI-Controlled Browsers

Breaking down three abstraction layers for browser automation—from raw Playwright to structured extraction—with production patterns, runnable code, and common pitfalls.