BrowserBook

Introduction

Next →

Welcome to BrowserBook

BrowserBook is a developer-first IDE for building reliable web automations. Whether you need to extract data from complex websites, automate repetitive tasks, or give your AI agents browser access, BrowserBook provides the tools to build robust automations fast.

With BrowserBook you can:

  • Write automation logic in a Jupyter-style notebook with AI assistance.
  • Execute against an inline browser running locally on your machine.
  • Deploy notebooks to run via API in secure, cloud-hosted browsers.
  • Integrate seamlessly with your agents and automation workflows.

Common use cases:

  • AI Agents: Provide reliable browser access for your agents to complete end-to-end workflows
  • Healthcare: Automate EHR interactions, billing, coding, and insurance follow-up in a HIPAA-compliant environment
  • Finance & Ops: Streamline back-office tasks like downloading invoices and reconciling reports
  • Web Scraping: Extract hard-to-reach data from dynamic websites with authentication and complex interactions
  • UI Testing: Write, update, and maintain test scripts with real-time debugging tools

Quickstart

  1. 1
    BrowserBook
    BrowserBook is currently available for macOS.
  2. 2
    Create an account
    Sign up using your email, or use GitHub/Google SSO.
  3. 3
    Create a new notebook
    From the sidebar or notebooks list, click New Notebook.
  4. 4
    Write your first automation

    The notebook starts with an input field where you can describe what you want to automate. Type instructions in natural language and press Enter.

    You can also manually add cells by clicking + Code or + Markdown at the top of the interface. In code cells, you write Playwright scripts to automate the inline browser. For example:

    await page.goto("https://example.com")
const title = await page.title()
console.log(title)
  5. 5
    Run the notebook
    Click Run All or press Cmd+Shift+E to execute all cells. To run just the currently selected cell, press Cmd+E. Your automation executes against an inline browser session running locally on your machine.
  6. 6
    View results
    Outputs appear inline below each cell. You can also download artifacts (JSON files) generated from the automation directly from the notebook or execution history (when run via API).
  7. 7