Open source, privacy-focused alternative to NotebookLM with local deployment and multi-model AI support
- Stars30.8k
- Forks3.5k
- Open Issues149
MIT
- TypeScript
- Python
- Jinja

About Open Notebook
Open Notebook is a privacy-focused, open source alternative to Google's NotebookLM. It keeps your research under your control while letting you organize multiple notebooks and pick the AI models you want, instead of being locked to a single provider.
Feed it PDFs, videos, audio, web pages, and Office docs, then use full-text and vector search to find anything across them. Chat with your research for context-aware answers, generate multi-speaker podcasts with custom episode profiles, and apply content transformations to summarize and extract insights. It works with 18+ AI providers and runs fully local through Ollama, with proper source citations on every answer.
A full REST API opens up automation, and optional password protection secures public deployments. Open Notebook is MIT licensed, ships in multiple UI languages, and installs with Docker Compose.
Key features
- Multi-notebook organization for research projects
- PDF, video, audio, web page, and Office doc support
- Full-text and vector search across content
- Chat with research context and AI-assisted notes
- Multi-speaker podcast generation with episode profiles
Details
- First released
- 2024
- Platforms
- Web · Docker
- Deployment
- self-hostable · docker
- AI providers
- 18+ providers incl. OpenAI and Ollama
- Storage
- SurrealDB
- License
- MIT