# notebooklm-py — NotebookLM CLI + Python API Skill

> notebooklm-py provides a CLI + Python API for NotebookLM with agent hooks; verified 13,142★ and uses Playwright Chromium for browser login.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

```bash
pipx install "notebooklm-py[browser]"  # or pip install in a venv
playwright install chromium  # ~170MB download (README note)
notebooklm login  # opens browser for Google OAuth
notebooklm create "My Research"
notebooklm source add "https://en.wikipedia.org/wiki/Artificial_intelligence"
notebooklm ask "What are the key themes?"
```

## Intro

notebooklm-py provides a CLI + Python API for NotebookLM with agent hooks; verified 13,142★ and uses Playwright Chromium for browser login.

**Best for:** Researchers and builders automating NotebookLM ingestion, chat, and artifact downloads from scripts

**Works with:** Python 3.10+ (per README), Playwright Chromium for login, and NotebookLM web accounts

**Setup time:** 12-25 minutes

### Key facts (verified)

- GitHub: 13142 stars · 1826 forks · pushed 2026-05-13.
- License: MIT · owner avatar + repo URL verified via GitHub API.
- README-backed entrypoint: `notebooklm login`.

## Main

- Treat auth as a first-class step: run `notebooklm auth check --test` after login, and keep a known-good storage state for CI/headless usage.

- Start with a small notebook + 1–2 sources, then add `generate` / `download` flows only after you can reliably `ask` with citations.

- Because this is an unofficial wrapper over undocumented APIs, pin versions in automation and expect breakage; keep troubleshooting links near your runbooks.

### Source-backed notes

- README explicitly warns it is unofficial and uses undocumented Google APIs that may break without notice.
- README shows CLI flows: create/use notebooks, add sources, ask questions, generate artifacts, and download outputs (MP3/MP4/PDF/PNG/CSV/JSON/Markdown).
- README notes a browser-based login via Playwright Chromium and includes a size/time hint for the Chromium install (~170MB; ~30–90s).

### FAQ

- **Is this affiliated with Google?**: No — README says it’s unofficial and not affiliated with Google.
- **Can I use it headless?**: Yes — README documents cookie/storage-state based auth paths, but you should validate with `auth check`.
- **What breaks most often?**: Auth and internal endpoints; pin versions and keep troubleshooting docs handy.

## Source & Thanks

> Source: https://github.com/teng-lin/notebooklm-py
> License: MIT
> GitHub stars: 13142 · forks: 1826

---

<!-- ZH -->

## Quick Use

```bash
pipx install "notebooklm-py[browser]"  # or pip install in a venv
playwright install chromium  # ~170MB download (README note)
notebooklm login  # opens browser for Google OAuth
notebooklm create "My Research"
notebooklm source add "https://en.wikipedia.org/wiki/Artificial_intelligence"
notebooklm ask "What are the key themes?"
```

## Intro

notebooklm-py 为 Google NotebookLM 提供 CLI 与 Python API，并支持 Claude Code/Codex 等 agent 集成；已验证 13,142★，登录流程基于 Playwright。

**Best for:** 希望用脚本自动化 NotebookLM 导入、问答与产物下载的研究/开发者

**Works with:** Python 3.10+（README 标注）、Playwright Chromium 登录，以及 NotebookLM 账号

**Setup time:** 12-25 minutes

### Key facts (verified)

- GitHub：13142 stars · 1826 forks；最近更新 2026-05-13。
- 许可证：MIT；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中可对照的入口命令：`notebooklm login`。

## Main

- 把认证当作第一步：登录后跑 `notebooklm auth check --test`，并保存稳定的 storage state 以支持 CI/无头环境。

- 先用小 notebook + 1–2 个 source 验证稳定性；能稳定 `ask` 后再接入 `generate` / `download` 流程。

- 由于它是对未公开接口的非官方封装，自动化里要固定版本并预期变更；把 troubleshooting 链接写进 runbook。

### Source-backed notes

- README 明确提示该项目为非官方，并依赖未公开的 Google 内部接口，可能随时变更导致失效。
- README 展示 CLI 流程：创建/切换 notebook、添加 source、提问、生成产物与下载输出（MP3/MP4/PDF/PNG/CSV/JSON/Markdown）。
- README 的登录流程基于 Playwright Chromium，并给出体积/耗时提示（约 170MB；约 30–90 秒）。

### FAQ

- **这是 Google 官方项目吗？**：不是。README 标注为非官方且不隶属 Google。
- **能在无头环境用吗？**：可以。README 提到基于 cookie/storage-state 的方式，但建议用 `auth check` 做验证。
- **最常见的故障点是什么？**：认证与内部接口变更；建议固定版本并保留 troubleshooting 路径。

## Source & Thanks

> Source: https://github.com/teng-lin/notebooklm-py
> License: MIT
> GitHub stars: 13142 · forks: 1826


---
Source: https://tokrepo.com/en/workflows/notebooklm-py-notebooklm-cli-python-api-skill
Author: Skill Factory