APIActive

Steel Browser API

Steel Browser API: Full docs index: https://docs.steel.dev/llms.txt Steel Documentation Steel is the open-source browser API for AI agents — managed cloud browsers with stealth, residential proxies, CAPTCHA solving, persistent profiles, session replays, and agent observability.

Open source page

Field note

What it does

Full docs index: https://docs.steel.dev/llms.txt Steel Documentation Steel is the open-source browser API for AI agents — managed cloud browsers with stealth, residential proxies, CAPTCHA solving, persistent profiles, session replays, and agent observability. Use Steel to launch cloud browsers, scrape content, and automate web tasks. Quick Reference - Install: npm install steel-sdk (Node.js) or pip install steel-sdk (Python) - CLI: curl -sSf https://setup.steel.dev | sh - Auth header: steel-api-key: <your-key - Auth env var: STEEL API KEY - API base URL: https://api.steel.dev - WebSocket: wss://connect.steel.dev?apiKey=<key &sessionId=<id - API reference: https://steel.apidocumentation.com/api-reference - Brand design language (DESIGN.md): https://docs.steel.dev/DESIGN.md Agent Instructions - For the simplest one-liner scrape, use the CLI: - For simple scraping without a browser session, use the REST scrape endpoint: - For browser automation, connect Puppeteer or Playwright via WebSocket: - Python SDK: - client.scrape() returns a ScrapeResponse with: - result.content.html — full HTML string - result.content.markdown — markdown version - result.content.cleaned html — cleaned HTML - result.content.readability — readability text - result.metadata.status code — HTTP status (int) - result.metadata.title — page title - result.links — list of extracted links - Always release sessions when done: client.sessions.release(sessionId) - Do NOT use session.websocketUrl directly — construct the WSS URL as shown above - The Node SDK constructor param is steelAPIKey (not apiKey) - The Python SDK constructor param is steel api key (not api key) - The Python package installs as pip install steel-sdk but imports as from steel import Steel - sessions.create() accepts an optional sessionId (Node) / session id (Python) UUID when you need the ID before the session exists; omit it and Steel generates one - The Python sessions.create() session timeout param is api timeout (not timeout, which is the HTTP request timeout) - Any docs page is available as markdown by appending .md to its URL, for example https://docs.steel.dev/overview/steel-cli.md; AI user agents (Claude, Cursor, GPT) receive markdown automatically at the canonical URL - /llms-full.txt concatenates every page into one file (large, roughly 230k tokens); prefer fetching the individual .md pages you need over reading the whole bundle

Capabilities

Available capabilities

Tags

Tags

No tags filed yet.

Ways to use it

Ways to use it

No integrations filed yet.

Product features

Product features

Agent Instructions

Quick Reference

Steel Documentation