Agent Skills

steel-browser

🔥 The easiest way to run AI Agents from your terminal. Scale your agents with Steel.

Installation
CLI
npx skills add https://github.com/steel-dev/cli --skill steel-browser

Installieren Sie diesen Skill über die CLI und beginnen Sie mit der Verwendung des SKILL.md-Workflows in Ihrem Arbeitsbereich.

Zuletzt aktualisiert am 6/18/2026

Steel CLI

Browser infrastructure for AI agents, from your terminal.

npm
License
Discord

The Steel CLI gives any AI agent (Claude, Cursor, Browser Use, or your own) a production-grade cloud browser: markdown-first scraping, long-running sessions, stealth, residential proxies, automatic CAPTCHA handling, and credential injection. One binary, cloud or self-hosted.

# Install, then interactively log in and install agent skills
curl -fsS https://setup.steel.dev | sh

# Scrape a page (agent-ready markdown)
steel scrape https://example.com

Steel CLI demo

Why Steel CLI

  • Agent-native. Markdown-first output, steel describe for machine-readable command introspection, shell completions, and ready-to-install skills for Claude Code, Cursor, OpenCode, and Codex.
  • Long-running sessions. 24-hour browser sessions, reusable named profiles, persistent auth context. Built for agents that actually live: deep research, async workflows, overnight jobs.
  • Framework-agnostic. First-class support for Claude Computer Use, OpenAI Computer Use, Gemini Computer Use, Browser Use, Playwright, Puppeteer, Selenium, Stagehand, CrewAI, Magnitude, Notte, Agno, and AgentKit.
  • Cloud or self-hosted. Fully open source. Use managed infrastructure at steel.dev, or run the Steel Browser stack yourself with steel dev or Docker.
  • Pro browser features. Managed residential proxies, stealth mode, automatic CAPTCHA solving, stored credential injection. Everything a real-world agent needs.
  • 📖 Docs: guides, recipes, API reference
  • 🧪 Cookbook: runnable examples across Python, Node, and every supported framework
  • 💬 Discord: community, feedback, roadmap
  • 🐙 GitHub: source, issues, releases

Install

curl -fsS https://setup.steel.dev | sh

The installer drops a single binary into ~/.steel/bin, updates your shell's PATH, and auto-generates shell completions for bash, zsh, and fish.

Alternatives:

  • Download from GitHub Releases
  • cargo install steel-cli
  • npm i -g @steel-dev/cli (thin wrapper around the native binary)

After install, either restart your shell or run export PATH="$HOME/.steel/bin:$PATH".

Shell Completions

Shell completions are installed automatically by install.sh. To regenerate or install manually:

# Bash (user-local)
steel completion bash > ~/.local/share/bash-completion/completions/steel

# Zsh (ensure a writable dir is in $fpath, then reload)
steel completion zsh > "${fpath[1]}/_steel"

# Fish
steel completion fish > ~/.config/fish/completions/steel.fish

# PowerShell (append to $PROFILE)
steel completion powershell | Out-String | Invoke-Expression

Supported shells: bash, zsh, fish, powershell, elvish.

Command Overview

Group Commands
Onboarding init, forge
Browser lifecycle browser start, browser stop, browser sessions, browser live
Browser passthrough steel browser <inherited-command>
Browser profiles profile import, profile sync, profile list, profile delete
API tools scrape, screenshot, pdf
Local runtime dev install, dev start, dev stop
Credentials credentials list, credentials create, credentials update, credentials delete
Account and utility login, logout, config, doctor, cache, update, completion

Full flags and schemas: CLI reference.

Agent-Browser Integration

steel browser is directly backed by the vendored agent-browser runtime. Steel-owned lifecycle commands:

  • steel browser start
  • steel browser stop
  • steel browser sessions
  • steel browser live

All other steel browser <command> calls inherit upstream runtime behavior and route through Steel. Migration from upstream agent-browser is typically command-prefix only:

  • before: agent-browser <command> ...
  • after: steel browser <command> ...

See the migration guide, compatibility matrix, and synced command catalog for details.

Endpoint Resolution

For browser lifecycle, browser passthrough bootstrap, and top-level API tools (scrape, screenshot, pdf), endpoint selection is deterministic.

Self-hosted precedence (highest to lowest):

  1. --api-url <url>
  2. STEEL_BROWSER_API_URL
  3. STEEL_LOCAL_API_URL
  4. browser.apiUrl in ~/.config/steel/config.json
  5. http://localhost:3000/v1

Cloud precedence:

  1. STEEL_API_URL
  2. https://api.steel.dev/v1

Attach-flag override rule:

  • If --cdp or --auto-connect is provided, Steel bootstrap injection is skipped and passthrough args are forwarded unchanged.

Output and Runtime Notes

  • steel scrape defaults to markdown-first output for token efficiency; use --raw for the full JSON payload.
  • steel browser start and steel browser sessions emit display-safe connect URLs with sensitive query values redacted.
  • Browser command paths bypass auto-update checks for lower interactive latency.
  • Piped output auto-switches to JSON for machine-readable workflows. Use --json to force it, or STEEL_FORCE_TTY=1 to disable.

Documentation Map

Primary docs:

Reference docs:

Agent skill:

Migrating from the Node CLI

The Steel CLI is now a single native Rust binary. If you previously installed it via npm i -g @steel-dev/cli, the install.sh script auto-detects and removes the old Node-based install. You can also do it manually:

npm update -g @steel-dev/cli    # auto-installs native binary
npm uninstall -g @steel-dev/cli # optional cleanup
export PATH="$HOME/.steel/bin:$PATH"

Licensed under MIT.