Prerequisites

• Docker Desktop (macOS, Windows) or Docker Engine with the Compose plugin (Linux)
• An API key from an AI provider, or a local model server such as Ollama. You add it in the UI, not in config files.

Step 1: Download docker-compose.yml

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

This is the official docker-compose.yml from this repository. It runs two services: surrealdb (the database) and open_notebook (UI, API and background worker).

Step 2: Set your encryption key

Edit docker-compose.yml and change this line:

- OPEN_NOTEBOOK_ENCRYPTION_KEY=change-me-to-a-secret-string

to a long random secret you generate yourself (for example with openssl rand -hex 32; other options). It encrypts the API keys you store; keep it.

Shared network or server? The UI (8502) and API (5055) are published on all network interfaces and there is no password by default. If other devices can reach this machine, change those two port lines to "127.0.0.1:8502:8502" and "127.0.0.1:5055:5055", or add - OPEN_NOTEBOOK_PASSWORD=your-password to the environment: block, before starting.

Step 3: Start services

docker compose up -d

Wait about 30 seconds, then open: http://localhost:8502

Step 4: Connect an AI provider

1. In the sidebar, open Models (under Manage).
2. Find your provider (OpenAI, Anthropic, Google, etc.) and click Add Configuration.
3. Enter a name and your API key (local providers such as Ollama need a Base URL instead), then click Add Configuration.
4. Click Test on the new configuration to check the connection.
5. Click Models, choose a Model Type, tick the models to add and click Add. Add at least one Language model and one Embedding model.
6. Under Default Model Assignments, click Auto-assign Defaults (or pick the models yourself).

Done! Create a notebook, add a source and start chatting. Full walkthrough: Connect a provider.

Need an API key? Get one from: OpenAI · Anthropic · Google · Groq

Anthropic and Groq have no embedding models; pair them with a provider that does (see the matrix).

Want free local AI? See the Local Quick Start (Ollama in Docker).

---

📚 More Installation Options

• Local AI with Ollama - Run models locally without API costs
• Docker Compose guide - Settings, backups, updates, remote access
• From Source (Developers) - For development and contributions
• Complete Installation Guide - All deployment scenarios

---

📖 Need Help?

• 🤖 AI Installation Assistant: CustomGPT to help you install
• 🆘 Troubleshooting: 5-minute troubleshooting guide
• 💬 Community Support: Discord Server
• 🐛 Report Issues: GitHub Issues

---