Self-host Open Notebook on a VPS
An open source, self-hosted alternative to NotebookLM for researching with your own sources, with podcasts and chat. Add model provider keys in the app after install.
levelrail-cli templates install open-notebook --name my-open-notebookSpecification
- Status
- Verified on arm64 with image tag 1.15.0
- Category
- AI
- Services
- open_notebook, surrealdb
- Ports
- 8502, 5055
- Volumes
- 2
- Memory
- about 1.5 GiB
- arm64
- tested
- amd64
- image published
- Settings to fill in
- none
- License
- Permissive license, MIT
About Open Notebook
An open source, self-hosted alternative to NotebookLM for researching with your own sources, with podcasts and chat. Add model provider keys in the app after install.
What it deploys
Open Notebook runs as 2 services in a single Compose app, listening on ports 8502, 5055, with 2 named volume mounts.
| Service | Image | Tag | Ports | Volumes |
|---|---|---|---|---|
| open_notebook | lfnovo/open_notebook | 1.15.0 | 8502, 5055 | notebook_data -> /app/data |
| surrealdb | surrealdb/surrealdb | v2.6.5 | none | surreal_data -> /home/nonroot |
Before you install
- CPU architecture. arm64 listed. Every image lists linux/arm64 in its registry manifest. That is a manifest fact, not proof the app runs on Arm.
- Verified. Verified on arm64 with image tag 1.15.0. Verified means our CI ran this exact image version and it answered on its health path. Evidence
Settings and environment
You do not have to fill in anything. 4 secrets are generated at deploy and stored encrypted. Values are never shown here.
| Service | Variable | Value |
|---|---|---|
| open_notebook | API_URL | Preset by the template |
| open_notebook | OPEN_NOTEBOOK_ENCRYPTION_KEY | Generated at deploy |
| open_notebook | OPEN_NOTEBOOK_PASSWORD | Generated at deploy |
| open_notebook | SURREAL_DATABASE | Preset by the template |
| open_notebook | SURREAL_NAMESPACE | Preset by the template |
| open_notebook | SURREAL_PASSWORD | Generated at deploy |
| open_notebook | SURREAL_URL | Preset by the template |
| open_notebook | SURREAL_USER | Preset by the template |
| surrealdb | SURREAL_PASS | Generated at deploy |
| surrealdb | SURREAL_USER | Preset by the template |
Install Open Notebook on a VPS
-
Install Levelrail on a fresh VPS
Run this as root on a Linux server (amd64 or arm64) with ports 80 and 443 reachable. The installer prints a setup link.
curl -fsSL https://levelrail.com/install.sh | sudo sh -
Sign in
Open the setup link, choose a password, then log the CLI in. The CLI install command is
curl -fsSL https://levelrail.com/install-cli.sh | shif the machine does not have it. See Getting started.levelrail-cli login --device -
Read the template
Shows the entry, including its full compose.yaml.
levelrail-cli templates get open-notebook -
Install it
This template has an install form, so the CLI fills each setting from --env, a generated secret or its default.
levelrail-cli templates install open-notebook --name my-open-notebookTo put a service behind a domain at install, add
--domain SERVICE=HOST:levelrail-cli templates install open-notebook --name my-open-notebook --domain open_notebook=open-notebook.example.com
Without a domain the app gets an sslip.io address. You can also deploy it from the dashboard: Apps, New app, Browse templates, then Open Notebook.
Docs and upstream
More in AI
- Open WebUIA self-hosted chat interface for running local large language models through Ollama.
- OpenClawA self-hosted personal AI agent gateway that connects chat apps and tools to the model provider you choose. Recommended container limit is 2 GiB. Measured use is 0.9 to 1.3 GiB, so a Levelrail VM needs at least 4096 MiB. The gateway trusts the ingress proxy through gateway.trustedProxies, written once to openclaw.json in the data volume.
- Ollama: Qwen 2.5 7BAlibaba's Qwen 2.5 7B model, served locally through Ollama's HTTP API.
- Ollama: Phi-3 MiniMicrosoft's Phi-3 Mini (3.8B), the smallest model in this catalog, good for constrained nodes.
- Ollama: Mistral 7BMistral's 7B instruct model, served locally through Ollama's HTTP API.
- Ollama: Llama 3 8BMeta's Llama 3 8B model, served locally through Ollama's HTTP API.