Skip to content
Browserbase
    • Primitives
      • BrowsersCloud browsers for your agent to use the web
      • AgentsScale fully managed browser agents with simple prompts
      • SearchFind relevant websites from a single query
      • FetchRetrieve web data as agent-ready HTML, JSON, or markdown
      • RuntimeScalable, sandboxed environments for agent deployments
      • IdentityAuthenticate your agent to navigate the web like a human
      • ModelsUse any model with a single API key
      • ObservabilityUnified debugging your agent across replays, logs, and prompts
    • Open Source
      • Browse CLIGive your agent browsing skills with a single command
      • StagehandThe most popular AI browser automation framework
    • Use Cases
      • Browser Agents
      • Automated Testing
      • Workflow Automation
      • Web Data Extraction
      All use cases
    • Industries
      • AI & Agent Platforms
      • Healthcare
      • Fintech
      • GTM
      • Legal
    • Resources
      • Blog
      • Customers
      • Enterprise
      • Templates
  • Pricing
  • Docs
  • Log in
Log in
Sign up
Get a demo

Quickstart: Puppeteer

Run Puppeteer against a cloud browser. No AI, no infrastructure, no local browser required.

Quickstart: Puppeteer demo

Works with

TypeScriptTypeScriptPuppeteerPuppeteer

Built by

Browserbase

Support

support@browserbase.com

Resources

Browserbase docsStagehand websiteStagehand docs
Copy prompt to run with your AI agent
npx create-browser-app --template quickstart-puppeteer

Send this template to your email, or view it on your desktop for the source code.

Get started with Puppeteer and Browserbase

Connect Puppeteer to a cloud browser on Browserbase and automate anything. No local Chrome install, no infrastructure to manage, no headless quirks. Open a WebSocket connection and use the same Puppeteer API you already know to navigate pages, interact with elements, and extract data. Perfect for scraping, testing, and workflow automation at scale.

Steps

  1. Spin up a Browserbase cloud session and connect Puppeteer over WebSocket
  2. Navigate to any page and verify it loaded successfully
  3. Interact with on-page elements using standard Puppeteer selectors and clicks
  4. Move between pages and confirm each navigation
  5. Extract the content you need, whether that's headings, copy, or structured data

Most Popular Templates

AI browser agent: Microsoft Fara-7B

Execute autonomous web tasks using Microsoft's Fara-7B computer use model

AI browser agent: Microsoft Fara-7B

Scrape with geolocation proxies

Route browser automation traffic through specific geolocations to access region-specific content

Scrape with geolocation proxies

Extract trending keywords from Google Trends

Extract trending search keywords from Google Trends for any country with structured JSON output for SEO and market research.

Extract trending keywords from Google Trends
Browserbase

Primitives

  • Browsers
  • Web APIs
  • Runtime
  • Identity
  • Model Gateway
  • Observability
  • Stagehand
  • MCP

Industries

  • AI
  • Healthcare
  • GTM
  • Tax
  • Legal

Developers

  • Docs
  • Templates
  • APIs & SDKs
  • Changelog
  • Status
  • Github

Company

  • Careers
  • Customers
  • Partner with Us
  • Trust & Security

Community

TwitterLinkedinYoutube
  • Privacy Policy
  • Terms of Service

Community

TwitterLinkedinYoutube
  • Privacy Policy
  • Terms of Service