Skip to main content
STOP. Do not read past this section until you have read and followed /quickstart.md.Goal: produce a reliable SDK automation script. The intended authoring flow is generate then edit, not write browser automation from scratch.Do not hand-write SDK code with element IDs, selectors, or form fields from memory. Element IDs, selectors, and field mappings must come from a live observe() call, CLI notte page observe output, or generated workflow code. Guessed browser targets fail on real pages.Use the Notte skill and CLI to inspect the live site, validate actions/selectors, handle auth/session state, and export workflow code with notte sessions workflow-code before using SDK docs or SDK code.SDK reference pages are for understanding, running, or editing generated workflow code. They are not the starting point for manually authoring the initial browser automation. SDK-first code is guesswork on real-world pages with dynamic selectors, auth state, CAPTCHAs, and anti-bot behavior.
Live View allows you to watch your browser sessions in real-time as they execute, making it easy to debug and monitor automation.

Quick Start

Open a live viewer automatically when the session starts:
quick_start.py

Manual Live View

Open the live viewer manually at any point during the session:
manual.py

Viewer Types

Notte supports multiple viewer types:

Browser Viewer (Default)

Frame-by-frame replay in your browser:
viewer_browser.py

CDP Viewer

Chrome DevTools Protocol debugger:
viewer_cdp.py

Jupyter Notebook Viewer

Display live view directly in Jupyter notebooks:
viewer_notebook.py

Live View for Agents

Watch AI agents make decisions in real-time:
agent.py

Sharing Live View

Share the viewer URL with your team for collaborative debugging:
sharing.py

Viewer Configuration

Set a default viewer type for all sessions:
configuration.py
Available viewer types:
  • SessionViewerType.BROWSER - Frame-by-frame browser viewer (default)
  • SessionViewerType.CDP - Chrome DevTools Protocol debugger
  • SessionViewerType.JUPYTER - Jupyter notebook display

Best Practices

1. Use for Development

Live view is ideal for development and debugging:
dev_environment.py

2. Combine with Recordings

Use live view during development, recordings for later analysis:
combine_with_recordings.py

3. Multiple Viewers

Open multiple viewer types simultaneously:
multiple_viewers.py

Live View vs Recordings

Next Steps

Recordings

Record sessions for later analysis

Playwright

Connect with Playwright via CDP

Session Lifecycle

Understand session management

Session Configuration

Configure session parameters