Originally published on andrew.ooo — visit the original for any updates, code snippets that aged out, or follow-up posts.
TL;DR
Open Notebook (by Luis Novo / lfnovo) is the open-source answer to Google's NotebookLM — and it's having a moment. This week it cleared 28,152 stars on GitHub (+3,891 in seven days) and currently sits in the top-15 weekly Python trending. Drop in PDFs, YouTube videos, web pages, audio, or office docs; chat with them, search them, generate multi-speaker podcasts from them — all on your own box, with whichever AI provider you want.
18+ AI providers out of the box (OpenAI, Anthropic, Google, Mistral, Groq, xAI, DeepSeek, Ollama, LM Studio, OpenRouter, Voyage, ElevenLabs, Deepgram, Azure, Vertex, MiniMax, DashScope/Qwen, and any OpenAI-compatible endpoint).
Multi-speaker podcasts (1–4 voices) with custom Episode Profiles — vs NotebookLM's locked 2-host deep-dive format.
