open-notebook
by lfnovo
Open Notebook is a self-hosted research workspace that lets you gather PDFs, videos, audio and web pages, then search them and chat with an AI about the contents. It is an open-source alternative to Google's Notebook LM, and it can also turn your sources into podcasts.
- Stars
- 40.6k +17 a day
- Licence
- MIT
- Runs on
- A small server
- Setup
- Moderate
- Language
- TypeScript
- Age
- 735 days
What you can do with it
- Add PDFs, videos, audio and web pages to a notebook and chat with an AI that cites those sources
- Search across all your material using full-text and meaning-based search
- Generate podcasts with one to four speakers from your research
Make money with it
A freelancer could offer research digests or podcast-style audio summaries of industry material to clients as a paid service.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Build a private searchable knowledge base from client documents, reports and recordings without sending them to a single vendor's cloud
- Produce research summaries and audio briefings for clients or staff, using cheaper AI providers to keep costs down
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Download the supplied docker-compose.yml, set an encryption key, run "docker compose up -d", then add an AI provider in the web interface.
Follow the official instructions in the project README.
Things to check
- Needs an API key from a paid AI provider unless you run local models such as Ollama
- No password by default, so you must set one or restrict ports if the machine is on a shared network
Checked 27 Oct 2026. Summary drafted by AI from the project's README.
