lfnovo/open-notebook

What it solves

Open Notebook is a privacy-focused, open-source alternative to Google's Notebook LM. It allows users to organize research materials and interact with them using AI without relying on a single cloud provider or sacrificing data sovereignty.

How it works

Users can upload multi-modal content—including PDFs, videos, audio, and web pages—into organized notebooks. The system uses a combination of full-text and vector search to provide context-aware AI chat and note-taking. It is designed to be self-hosted (via Docker) and supports over 18 AI providers, including local options like Ollama and LM Studio, ensuring that data can remain entirely local.

Who it’s for

It is designed for researchers, students, and anyone who needs a secure, customizable environment to manage large amounts of information and generate insights from their own private datasets.

Highlights

• Multi-Model Flexibility: Support for 18+ providers (OpenAI, Anthropic, Google, Ollama, etc.) for LLMs, embeddings, and speech services.
• Podcast Generation: Ability to create professional multi-speaker podcasts based on research materials with custom profiles.
• Data Sovereignty: Fully self-hosted and privacy-first, avoiding vendor lock-in.
• Universal Content Support: Handles a wide variety of formats including PDFs, Office docs, and web pages.
• Developer Friendly: Includes a comprehensive REST API for automation and integration.