Open Notebook: Self-hosted NotebookLM alternative
Open source implementation of Google's NotebookLM that runs locally with document processing and podcast generation.
Learn more about Open Notebook
Open Notebook is a self-hosted alternative to Google's NotebookLM built with Python backend and Next.js frontend. The system uses SurrealDB for data storage and LangChain for AI integrations, supporting over 16 different AI providers including OpenAI, Anthropic, and local models through Ollama. It processes multi-modal content including PDFs, videos, audio files, and web pages using vector embeddings and full-text search. The application includes REST API access and can be deployed via Docker containers or installed from source code.
Multi-provider AI
Integrates with 16+ AI providers through a unified interface, allowing users to switch between OpenAI, Anthropic, Google, local Ollama models, and others. Supports different providers for LLM, embedding, speech-to-text, and text-to-speech functions.
Self-hosted deployment
Runs entirely on user infrastructure with Docker Compose or source installation. All data processing and AI interactions occur within the user's environment, maintaining complete control over sensitive research materials.
Advanced podcast generation
Generates multi-speaker podcasts with 1-4 configurable speaker profiles and custom script control. Includes professional audio processing capabilities beyond the standard two-speaker format of similar tools.
Hotfix for llama.cpp connection error and LangChain connection issues.
- –Connection error with llama.cpp and OpenAI-compatible providers
- –Bump Esperanto to 2.17.2 which fixes LangChain connection errors caused by garbage collection
Adds internationalization support with Chinese translations and frontend test infrastructure.
- –Internationalization (i18n) support with Chinese (Simplified and Traditional) translations
- –Frontend test infrastructure with Vitest
- –Language toggle component for switching UI language
- –Date localization using date-fns locales
- –Error message translation system
Upgrades to Next.js 16 with offline deployment support and enables large file uploads up to 100MB.
- –Upgraded Next.js from 15.4.10 to 16.1.1
- –Enables proxyClientMaxBodySize configuration for large file uploads
- –Upgraded React from 19.1.0 to 19.2.3
- –Renamed middleware.ts → proxy.ts (required by Next.js 16)
- –Users can now upload files larger than 10MB (up to 100MB)
See how people are using Open Notebook
Top in AI & ML
Related Repositories
Discover similar tools and frameworks used by developers
Megatron-LM
Library for training large transformer models with distributed computing and GPU-optimized building blocks.
Open Lovable
AI tool that generates React applications from website clones or user descriptions.
Paperless-ngx
Self-hosted OCR document archive with ML classification.
Tesseract
LSTM-based OCR engine supporting 100+ languages.
Chart-GPT
AI tool that generates charts from natural language text descriptions.
Related Reading
Guides and comparisons from the Greptile content library
Choosing the Right Code Review Tool: Better Alternatives to Graphite AI
A breakdown of the best alternatives to Graphite for code reviews. Compare AI tools like Trag, open-source solutions like Gerrit, and database-focused platforms like Visual Expert.
What is agentic coding? Benefits, risks, and best tools to consider
What engineering leaders need to know about agentic coding: how it differs from AI coding and vibe coding, how it works, the benefits and risks, and the tools worth evaluating.
Top AI Code Review Tools for Small Dev Teams 2026
Affordable, lightweight AI code review tools that help small teams catch bugs faster. Practical comparisons of accuracy, ease of use, and value for teams without enterprise budgets.
Best CodeRabbit Alternatives for Smarter AI Code Reviews in 2026
7 powerful CodeRabbit alternatives ranked by real dev teams. Feature comparison, pricing analysis, and honest reviews to find your perfect AI code reviewer.