Open Notebook
Open Notebook is an MIT-licensed, self-hosted research and note-taking app with AI chat, search and multi-speaker podcasts, positioned against Google's Notebook LM.
- GitHub stars
- 42k
- Last commit
- 4 days ago
- Latest release
- v1.15.1
- Licence
- MIT
- Self-hosted
- Yes

Open Notebook is an open source, privacy-focused alternative to Google's Notebook LM. You gather PDFs, videos, audio and web pages into notebooks, search them with full-text and vector search, chat with AI that draws on your research, and generate podcasts. The homepage describes it as a note-taking and research platform with AI-powered notes and privacy controls.
Model choice is a central point. The README lists more than 20 providers, including OpenAI, Anthropic, Google, Mistral and Ollama, plus any OpenAI-compatible server such as LM Studio or vLLM. Podcasts can use one to four speakers with custom profiles, answers cite the sources and notes used, and a full REST API is available. The interface comes in many languages.
Setup uses Docker Compose with two services: a SurrealDB database and one app container holding the UI, API and background worker. You set an encryption key for stored API keys, start the services and open the UI on port 8502, then connect an AI provider. The stack is built with Python, Next.js, React, SurrealDB and LangChain.
Key features
- Choice of 20+ AI providers including local models
- Handles PDFs, videos, audio and web pages
- Multi-speaker podcast generation
- Full-text and vector search
- Chat that uses your research as context
- Answers cite the sources used
- Full REST API
- Interface available in many languages





















