Pi Agent

Use Pi with the pi-steel extension to drive real browser sessions, scrape rendered pages, extract structured data, and run computer actions from the terminal.

This integration is part of Steel's experiments effort. Defaults can change without notice, and stability is not guaranteed.

Overview

The Pi integration uses Steel as a native Pi extension through the @steel-experiments/pi-steel package. This lets Pi:

  • Start and control Steel browser sessions from the Pi session
  • Scrape fully rendered pages and perform computer-use actions
  • Extract structured data with a JSON schema instead of parsing markdown
  • Capture screenshots and PDFs as Pi artifacts
  • Fill and submit forms, and reuse sessions across prompts

Pi is a minimal, extension-first coding agent. It ships with no built-in browser, so capabilities arrive through pi install. Steel plugs into that socket and hands Pi a real cloud browser without any Playwright or headless Chromium setup on your side.

Requirements

  • Node.js: Version 18 or higher
  • Pi: Installed locally
  • Steel API Key: Active Steel account

Setup

Step 1: Install the extension

Terminal
pi install npm:@steel-experiments/pi-steel

Pi picks up the extension on the next run and the Steel browser tools become available automatically.

Step 2: Authenticate

Set STEEL_API_KEY in your environment.

Grab a free API key at app.steel.dev if you do not have one yet.

Available tools

Once the extension is installed, Pi has access to a full browser toolset:

  • steel_navigate and steel_scrape for fetching pages as text, markdown, or HTML
  • steel_extract for structured data from a JSON schema
  • steel_fill_form for submitting forms
  • Playwright-backed computer actions (click, scroll, type) for pages that scraping cannot reach
  • Screenshot and PDF capture, returned as Pi artifacts
  • steel_pin_session to keep a browser alive across prompts, or STEEL_SESSION_MODE=session for persistent mode

CAPTCHA handling is built in, so most bot-protected pages work without extra configuration.

Example workflow

Pi works well on research tasks that span multiple pages and require both scraping and interaction. A prompt like:

Visit apple.com and compare all recent MacBook models.

Pi will navigate the Mac lineup, follow links into each model page, and fall back to computer actions and screenshots when sticky navigation or viewport-dependent sections block plain scraping.

For bot-protected docs:

Visit OpenAI docs and tell us how we can use the latest model.

Steel handles the bot-protection layer so Pi sees a normal webpage, reads the current API reference, and returns an up-to-date code example rather than a stale one from training data.

Structured extraction

When you would otherwise parse markdown for prices, specs, or listings, steel_extract with a JSON schema is usually the better call. Pi gets typed output directly, which is easier to reason about across multi-step workflows.

Constraints

  • Command approvals depend on your Pi settings. Extension tools may require approval depending on your configuration.
  • First runs are usually the roughest. Dynamic web apps often need a few retries before the workflow is stable.
  • Authenticated sites work best with prepared Steel auth state. Reusing profiles or auth context is generally more reliable than repeated interactive logins.

Additional Resources

Contents

OverviewRequirementsSetupStep 1: Install the extensionStep 2: AuthenticateAvailable toolsExample workflowStructured extractionConstraintsAdditional Resources