---
id: notebooklm-py
version: "0.8.1"
license: MIT
license_treatment: permissive
maintenance: active
---

# notebooklm-py — Unofficial Python library for automating Google NotebookLM

License: permissive · Maintenance: active · Downloads: 187.4K/mo

## What it is and what it does

notebooklm-py is an unofficial Python client for Google Gemini Notebook (rebranded from NotebookLM in July 2026). It exposes programmatic access to the service's core capabilities—document ingestion, grounded question-answering, and artifact generation—including features not available in the web UI. The library drives the same underlying Google service and works unchanged after the rebrand.

The package is designed for automation workflows: bulk-importing sources (URLs, PDFs, YouTube, Google Drive), running research queries with auto-import, generating media (podcasts, videos, slide decks, quizzes, flashcards, mind maps), and downloading artifacts locally in multiple formats. It integrates with AI agents via a skill interface and an MCP server, and supports CLI usage for unattended, headless, or scheduled tasks. The library treats NotebookLM as a grounded synthesis and memory layer—offloading expensive analysis to Gemini while an agent orchestrates the final mile.

Use it for:

- Offload expensive document analysis to Gemini, letting your agent spend tokens only on final polish rather than reading large source sets.
- Build persistent cross-session memory by appending session decisions as notes and querying them at the start of the next session.
- Generate multiple content formats (podcast, video, slides, quiz, flashcards) from a single source set and export programmatically.
- Create a grounded knowledge base by loading product docs and FAQs, then querying for cited answers instead of hallucinated ones.
- Integrate into AI agents as a skill to provide source-grounded answers from your internal docs or architecture RFCs.
- Automate incident response by spinning up a notebook of relevant docs on alert and generating a diagnostic briefing.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Programmatic access to Google Gemini Notebook for automating research, content generation, and artifact export via Python, CLI, and AI agent integration.

Yes, with conditions. The package is actively maintained, has low install friction, and offers genuine value for research automation, content generation, and agent integration workflows. However, it relies on undocumented Google APIs that can break without notice, carries no official support, and is best suited for prototypes, research, and personal projects rather than production systems. Verify rate limits and API stability for your use case before committing to heavy-usage workflows.

## Install

pip install notebooklm-py
uv add notebooklm-py
poetry add notebooklm-py

## Installing notebooklm-py

Before you install: Low friction: pure Python wheel with only four runtime dependencies (click, filelock, httpx, rich). Active maintenance with a recent release (0.8.1 on 2026-08-14) and substantial community adoption (18706 GitHub stars). Supports Python 3.10 through 3.14.

License in practice: MIT license permits commercial and private use with minimal restrictions. You may use, modify, and distribute this package freely as long as you include the license notice.

Quickstart:

pip install notebooklm-py

import notebooklm_py

# Create a notebook and add sources
notebook = notebooklm_py.create_notebook("My Research")
notebook.add_source("https://example.com/doc.pdf")

# Query and generate artifacts
answer = notebook.ask("What are the key findings?")
notebook.generate_audio_overview()

Requires Google authentication (NotebookLM/Gemini account). Uses undocumented Google APIs that may change without notice; rate limits apply.

Verify before relying:

- Specific rate limits and throttling thresholds for heavy usage
- Stability guarantees or SLA for undocumented API endpoints
- Whether all web UI features are accessible via the Python API

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 187.4K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

notebooklm python api, gemini notebook automation, ai research automation, content generation from documents, grounded knowledge base query, podcast generation from sources, bulk document processing, ai-automation, research-tools, agent-integration

[View on SkillFed](https://skillfed.io/packages/notebooklm-py) · [View on PyPI](https://pypi.org/project/notebooklm-py/)