notebooklm-py
Unofficial Python library for automating Google NotebookLM
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Google authentication (NotebookLM/Gemini account).
- Uses undocumented Google APIs that may change without notice; rate limits apply.
- Low friction: pure Python wheel with only four runtime dependencies (click, filelock, httpx, rich).
License · maintenance · safety
MIT (permissive) — 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.
last release 2026-08-14 (0 days) · last repo commit 2026-08-14 · 18,706 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 187,418 downloads/mo, #9,966 on PyPI
Alternatives
Verify before relying
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()- 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
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 on this page. Verify before relying on it.
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
notebooklm-py on PyPI
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.
Requires Google authentication (NotebookLM/Gemini account). Uses undocumented Google APIs that may change without notice; rate limits apply.
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()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 the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 4 packagesclickfilelockhttpxrich |
| Maintenance | Actively maintained 0 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 187,418 / month, #9,966 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Software Development :: Libraries :: Python Modules |
Evidence: notebooklm_py-0.8.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “notebooklm python api”
- notebooklm-pyProgrammatic access to Google Gemini Notebook for automating…
- notebooklm-mcp-cliProvides CLI and MCP server access to Google Gemini Notebook…
- xdkA Python SDK for interacting with the X API, providing typed client…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also notebooklm-mcp-cli · google-agents-cli · google-genai · jupyter-ai-magics · vertexai · google-cloud-aiplatform · vlmrun · google-antigravity · claude-tap · boost-skill-cli