# NotebookLM Agent

Q&A agent that answers user questions based on NotebookLM notebooks. Leverages NotebookLM's Gemini-powered analysis to provide grounded, citation-backed responses from uploaded sources.

## Use Cases

- Ask questions about documents in a specific notebook
- Get summaries with source citations
- Compare information across multiple sources
- Research assistant workflows

## Prerequisites

```bash
pip install notebooklm-py
playwright install chromium
notebooklm login  # One-time browser auth
```

## Quick Start

```bash
# Set active notebook
notebooklm use <notebook_id>

# Ask questions
notebooklm ask "What are the key findings?"
notebooklm ask "Compare approaches from different sources"

# Get citations with JSON output
notebooklm ask "Summarize the methodology" --json
```

## Versions

| Version | Path | Purpose |
|---------|------|---------|
| Claude Code | `code/` | CLAUDE.md for Claude Code integration |
| Claude Desktop | `desktop/` | SKILL.md for Claude Desktop skills |

## Related Skills

- [51-notebooklm-automation](../51-notebooklm-automation/) - Full automation workflows
- [52-notebooklm-studio](../52-notebooklm-studio/) - Content generation (podcasts, videos)
- [53-notebooklm-research](../53-notebooklm-research/) - Research and source discovery