Open Notebook is an open-source, privacy-focused alternative to Notebook LM, designed for researchers and power users to manage research, generate AI-assisted notes, and interact with content on their own terms. It offers flexibility and control over data privacy, aiming to democratize AI-assisted knowledge acquisition.

How It Works

The project leverages a multi-column interface (Sources, Notes, Chat) for streamlined research workflows. It supports fine-grained context management, allowing users to control what data is shared with AI models, from no context to full content. Jinja-based prompts enable customizable AI interactions, and integrated full-text and vector search facilitates efficient information retrieval.

Quick Start & Requirements

• Installation: Clone the repository, copy .env.example to .env and docker.env to .env, and set API keys.
• Running:
  • For local development: uv sync, docker compose --profile db_only up, uv run streamlit run app_home.py
  • For Docker: docker compose --profile multi up
• Prerequisites: Python, Docker, API keys for supported AI models (OpenAI, Anthropic, Gemini, Vertex AI, Open Router, Ollama, Groq, X.AI).

Highlighted Details

• Broad Content Integration: Supports links, PDFs, EPUB, Office files, TXT, Markdown, YouTube videos, audio, and video files.
• Multi-Model Support: Integrates with OpenAI, Anthropic, Gemini, Vertex AI, Open Router, Ollama, Groq, and X.AI.
• Podcast Generator: Automatically converts notes into customizable podcasts with options for speakers, structure, and voices.
• AI-Powered Notes & Transformations: AI assists in note generation and custom content transformations for extracting insights.

Maintenance & Community

The project is under active development with frequent improvements. Users are encouraged to provide feedback via GitHub Issues, Discussions, and Pull Requests. A Discord server is available for support and community interaction.

Licensing & Compatibility

MIT licensed, allowing for commercial use and integration with closed-source projects.

Limitations & Caveats

The project is in active development, and APIs may change. The front-end is currently built with Streamlit, with plans to move to a more robust UI framework.