Skip to content
Get packs

Open Notebook

Self-hosted, privacy-focused open-source alternative to Google's NotebookLM for research notes and AI chat.

GitHub Download v1.15.0
Stars
41.3k
Forks
4.8k
Licence
MIT
Language
TypeScript
Last update
4 days ago
Type
App

What it is

Open Notebook is a self-hosted app for organizing research material such as PDFs, videos, audio, and web pages into notebooks, then searching and chatting with an AI about that content. It is an open-source take on Google's NotebookLM. You connect your own AI provider, such as OpenAI, Anthropic, Google, or a local model through Ollama, so you control where your data and API calls go.

  • Collect PDFs, web pages, and other sources into a notebook and chat with them
  • Search across all your stored content using full-text and vector search
  • Generate multi-speaker podcasts from your research material
  • Connect a local model through Ollama so AI usage stays on your machine
  • Automate workflows through the REST API

Great for

  • People who want NotebookLM-style research tools without sending their material only to Google
  • Users who want to choose or switch between several AI providers
  • People comfortable running Docker on a personal computer or home server
  • Anyone who wants to run AI models locally with Ollama

Not ideal for

  • People who want a zero-setup hosted service, since the README describes running it yourself with Docker Compose
  • Users who are not comfortable managing an API key or a local model server
  • Anyone exposing the app to a shared network without changing the default port settings and adding a password, since the README says there is no password by default
Step-by-step guide: how to use Open NotebookInstall, first run, examples, tips and FAQs
NotebookLM vs Open NotebookAnythingLLM vs Open Notebook

How to get it

  1. 1

    Run with Docker

    You'll need: Docker Desktop or Docker Engine with the Compose plugin · An API key from an AI provider, or a local model server such as Ollama

    Create a folder and download docker-compose.yml

    mkdir open-notebook && cd open-notebook

    Download the official compose file

    curl -o docker-compose.yml https://raw.githubusercontent.com/lfnovo/open-notebook/main/docker-compose.yml

    Start the services

    docker compose up -d
  2. 2

    Run it

    • Edit docker-compose.yml and replace the encryption key placeholder with your own long random secret
    • Run docker compose up -d and wait about 30 seconds
    • Open http://localhost:8502 in your browser
    • In the sidebar, open Models under Manage, add a provider configuration with your API key or Base URL, and test it
    • Add a Language model and an Embedding model, then click Auto-assign Defaults
  3. 3

    Get the most out of it

    • Use a local Ollama model through the Local Quick Start guide if you want to avoid API costs
    • Restrict the UI and API ports to 127.0.0.1 or set OPEN_NOTEBOOK_PASSWORD if other devices can reach your machine
    • Use the REST API to automate tasks, as the README highlights API access
    • Use the Docker Compose guide for settings, backups, and updates

Downloads

Source code (.zip)main branch · straight from GitHubRelease v1.15.0Release notes and sourceOfficial website & docswww.open-notebook.ai

Strengths

  • Self-hosted, so your research stays on hardware you control
  • Supports many AI providers and any OpenAI-compatible server, per the README
  • MIT licensed, so the code can be inspected, modified, and reused

Trade-offs

  • Requires Docker and a separately obtained AI provider key or local model server
  • The README's default setup has no password and publishes ports on all network interfaces unless changed
  • Quality and cost depend on the AI provider you choose, which the README does not evaluate

How it compares

ProjectStarsTypeLevelUpdatedBest for
open-notebook (this)41.3kAppintermediate4 days agoPeople who want NotebookLM-style research tools without sending their material only to Google
anything-llm67.8kAppbeginner6 days agoPeople who want a private ChatGPT-style assistant over their own PDFs and text files
openclaw394kAppintermediate4 days agoPeople who want an AI assistant that runs on their own machine rather than a hosted service
leon17.6kAppintermediate4 days agoDevelopers who want to inspect or extend an open-source assistant
memos64.2kAppintermediate4 days agoPeople who want a private, self-hosted journal or quick-notes timeline
RuView102kOtheradvanced4 days agoHobbyists who want presence detection in a room without cameras

Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.