notebookllama
run-llama/notebookllama
NotebookLlaMa is an open-source alternative to Google's NotebookLM, built using LlamaCloud and designed to generate audio-style podcasts or structured interactions from documents.
2k 250MITUpdated 2026-03-02
72
GoodOverview
NotebookLlaMa serves as a fully open-source clone of NotebookLM, leveraging LlamaCloud pipelines, custom extraction agents, and text-to-speech services to ingest documents and transform them into engaging audio outputs. The platform utilizes Streamlit for its frontend interface, Docker containers for backing services like PostgreSQL and Jaeger, and an MCP server for integrations.
Capabilities
- ▸Document extraction and indexing via LlamaCloud
- ▸Audio synthesis and generation using external TTS services like ElevenLabs
- ▸Interactive UI powered by Streamlit
- ▸Model Context Protocol (MCP) server support
Best for
Transforming research papers or documentation into podcast-style audio summaries, Extracting and indexing insights from private documents using LlamaCloud, Building custom document-to-audio knowledge bases
Works with
CursorClaude Code
Evoa Score breakdown= Σ (score × weight)
72Task usefulness20%77 → +15.4
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%85 → +12.8
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%70 → +10.5
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%30 → +3.6
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%90 → +9.0
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%85 → +6.8
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%50 → +2.5
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total72.5 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Requires storing sensitive API keys in a local .env file. Running local Docker containers and third-party tools should be done securely.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.