# Notebooklm CLI > Help users operate the NotebookLM CLI (`nlm`) to manage notebooks, add/sync sources, run research, query sources, and generate artifacts (audio overviews, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables). Use when the user mentions NotebookLM, `nlm`, notebooks/sources/podcasts from the command line, or asks to create/query/research notebooks programmatically. - Skill: `mukundmurali-mm/notebooklm-cli` (Agent Skill) - Install (CLI): `npx skillmds@latest add mukundmurali-mm/notebooklm-cli` - Raw SKILL.md: https://api.skillmd.com/api/skills/mukundmurali-mm/notebooklm-cli/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Docs & Writing - Author: mukundmurali-mm (https://skillmd.com/u/mukundmurali-mm) - Updated: 2026-09-22 - Page: https://skillmd.com/skills/mukundmurali-mm/notebooklm-cli --- # NotebookLM CLI (`nlm`) Drive Google NotebookLM from the terminal via the `nlm` binary (https://github.com/jacob-bd/notebooklm-cli). ## Default workflow 1. If the command is known, run it directly (e.g. `nlm notebook list`). 2. **Resolve IDs first.** Most commands need a notebook ID. Run `nlm notebook list` (or `nlm notebook list --json` to parse) to get IDs, or use an alias (see Aliases). 3. **When unsure of flags, check the live interface** — run `nlm --ai` (emits AI-friendly docs) or `nlm --help`. The version installed may differ from this cheat-sheet; trust `--help`. 4. **Generation and destructive commands need `--confirm` / `-y`.** Never add `--confirm` to a delete, sync, or generation command unless the user clearly asked for that action. ## Prerequisites - Requires the `nlm` binary, Python 3.10+, and Google Chrome (auth uses Chrome DevTools Protocol). - Install: `pipx install notebooklm-cli` (recommended) — or `pip install notebooklm-cli` / `uv tool install notebooklm-cli`. - If `nlm` is missing, suggest the install command; do not install without the user's ok. ## Authentication ```bash nlm login # Authenticate via Chrome nlm login --profile # Log in to a specific account nlm login --check # Check credentials nlm auth status # Verify the current session is valid nlm auth list # List stored profiles nlm auth delete --confirm # Remove a profile ``` Most commands accept `--profile ` to target a specific account. ## Notebooks ```bash nlm notebook list # List all notebooks (use --json to parse) nlm notebook create "Title" # Create a notebook nlm notebook get # Notebook details nlm notebook describe # AI-generated summary nlm notebook query "question" # Ask a question against the notebook's sources nlm notebook delete --confirm # Delete (destructive) ``` ## Sources ```bash nlm source list # List sources nlm source list --drive # Show Drive sources w/ freshness nlm source list --drive -S # Faster (skip freshness check) nlm source add --url "URL" # Add a URL or YouTube video nlm source add --text "content" --title "..." # Add pasted text nlm source add --drive # Add a Google Drive document nlm source describe # AI summary of a source nlm source content # Retrieve raw text nlm source stale # List outdated Drive sources nlm source sync --confirm # Sync Drive sources (re-ingest) ``` ## Research (discovery) ```bash nlm research start "query" --notebook-id # Web search (~30s) nlm research start "query" --notebook-id --mode deep # Deep research (~5min) nlm research start "query" --notebook-id --source drive # Search Google Drive nlm research status # Check progress nlm research import # Import results as sources ``` Research is async: `start` returns a task, poll `status`, then `import` when complete. ## Content generation All of these need `--confirm` (or `-y`) and may take a while: ```bash nlm audio create --confirm # Podcast / audio overview nlm report create --confirm # Briefing document nlm quiz create --confirm # Quiz questions nlm flashcards create --confirm # Flashcards nlm mindmap create --confirm # Mind map nlm slides create --confirm # Slide deck nlm infographic create --confirm # Infographic nlm video create --confirm # Video overview nlm data-table create "description" --confirm # Extract a data table ``` ## Studio (artifact management) ```bash nlm studio status # List generated artifacts nlm studio delete --confirm # Delete an artifact ``` ## Chat (interactive REPL) ```bash nlm chat start # Launch an interactive chat session nlm chat configure # Set chat goal/style ``` REPL commands inside a session: `/sources`, `/clear`, `/help`, `/exit`. ## Aliases UUIDs are unwieldy — alias them to readable names, then use the name anywhere an ID is expected. ```bash nlm alias set # Create a shortcut nlm alias list # Show all aliases nlm alias get # Resolve an alias to its UUID nlm alias delete # Remove an alias ``` ## Config & output formats ```bash nlm config show # Display settings nlm config get # Read a setting nlm config set # Update a setting # Output flags (on list-style commands): nlm notebook list --json # JSON (use when parsing programmatically) nlm notebook list --quiet # IDs only nlm notebook list --title # "ID: Title" nlm notebook list --full # All columns ``` ## Utilities ```bash nlm --ai # Output AI-friendly documentation (run this when unsure) nlm --install-completion # Enable shell tab completion nlm --show-completion # Print the completion script ``` ## Notes - Prefer `--json` output when you need to extract IDs or fields for follow-up commands. - Surface the notebook/source/artifact IDs back to the user so they can reference them later. - Generation jobs are not instant — set expectations (audio/deep research can take minutes).