lfnovo/open-notebook

What it solves

Open Notebook is a privacy-focused, open-source alternative to Google's Notebook LM. It allows users to conduct research and organize knowledge without relying on a single cloud provider, ensuring data sovereignty and avoiding vendor lock-in.

How it works

The system allows users to upload multi-modal content (PDFs, videos, audio, web pages, and Office documents) into organized notebooks. It uses a combination of full-text and vector search to make this content searchable and provides a chat interface where AI models can answer questions based on the uploaded research materials. It supports over 18 AI providers, including local options like Ollama and LM Studio, and integrates with SurrealDB for data storage.

Who it’s for

It is designed for researchers, students, and anyone who need to organize complex information and generate insights from their own private data using various AI models.

Highlights

• Multi-Model Flexibility: Support for 18+ providers including OpenAI, Anthropic, and local LLMs via Ollama.
• Professional Podcast Generation: Ability to create multi-speaker podcasts (1-4 speakers) with custom profiles based on research content.
• Privacy-First: Self-hosted deployment via Docker, keeping sensitive data local.
• Universal Content Support: Handles a wide variety of formats including PDFs, audio, and video.
• Detailed Control: Includes a REST API for automation and fine-grained context control for AI conversations.