notebooklm
NotebookLM
NotebookLM = external RAG engine that offloads reading from your context window. Uses the notebooklm-mcp-cli MCP server (PyPI, v0.6.1+) to create notebooks, manage sources, generate content, label sources thematically, and query with grounded AI responses. Supports batch operations across notebooks, pipelines, and multilingual content generation.
Disclaimer: Uses internal undocumented Google APIs via browser authentication. Sessions last ~20 minutes. API may change without notice.
What's New (April 2026 — v0.6.1)
- Source labels (NEW in v0.6.0) — Organize sources into thematic categories. New
labelMCP tool +nlm labelCLI:auto(AI generates from sources, requires 5+),list,create,rename,delete,assign,unassign. Surfaces in NotebookLM web UI's source filter. - Label reorganize (NEW in v0.6.1) —
nlm label reorganize(orlabelMCP withaction="reorganize") forces AI re-categorization when labels already exist. Two modes: all-sources (replace, requires--confirm) or unlabeled-only (preserve existing). - Video formats — 3 formats (explainer, brief, cinematic) + 9 visual styles
- Audio length —
audio_lengthparam: short, default, long - PPTX export —
download_artifact(slide_deck_format="pptx")alongside PDF - Bulk source ops —
source_add(urls=[...]),source_delete(source_ids=[...]),source_add(wait=True) - Studio artifact rename —
studio_status(action="rename", artifact_id="...", new_title="...") - Slide/report/quiz params —
slide_format,report_format,difficulty+question_count - Infographic options —
orientation,detail_level, 11infographic_styleoptions - Audio sources — Upload m4a, wav, mp3, aac, ogg, opus
- Async large queries —
notebook_query_start/notebook_query_statusfor 50+ source notebooks
More from yonatangross/orchestkit
responsive-patterns
Responsive design with Container Queries, fluid typography, cqi/cqb units, subgrid, intrinsic layouts, foldable devices, and mobile-first patterns for React applications. Use when building responsive layouts or container queries.
492ui-components
UI component library patterns for shadcn/ui and Radix Primitives. Use when building accessible component libraries, customizing shadcn components, using Radix unstyled primitives, or creating design system foundations.
477devops-deployment
Use when setting up CI/CD pipelines, containerizing applications, deploying to Kubernetes, or writing infrastructure as code. DevOps & Deployment covers GitHub Actions, Docker, Helm, and Terraform patterns.
453rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
374architecture-decision-record
Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Use when writing ADRs, recording decisions, or evaluating options.
369domain-driven-design
DDD tactical patterns for complex business modeling including entities, value objects, aggregates, domain services, repositories, specifications, and bounded contexts. Python dataclass implementations with TypeScript alternatives. Use when building rich domain models, enforcing invariants, or separating domain logic from infrastructure.
356