Self-host n8n AI Starter Kit with Levelrail
n8n wired to a local Ollama model and a Qdrant vector store, ready for private AI workflows.
- Authorn8n-io
- LicenceLicenseRef-n8n-SUL
- Memory4 GiB
- Archarm64
- Services4
How to self-host n8n AI Starter Kit
-
Pull the images
4 images are pulled on your server.
Show images
postgres:16-alpinen8nio/n8n:1.62.1ollama/ollama:0.34.4qdrant/qdrant:v1.12.4
-
Create the app
4 services start in a single Compose app, with 4 named volume mounts for your data, on port 5678.
-
Fill in the secrets
3 secrets are generated and stored encrypted, 7 settings are preset, you do not have to fill in anything.
-
Open it
Without a domain the app gets an sslip.io address; add --domain SERVICE=HOST to use your own.
n8n AI Starter Kit requirements
- Memory
- About 4 GiB
- Architectures
- amd64 image published, arm64 image published
- Ports
- 5678
- Domain
- Optional, an sslip.io address is used without one
- Settings
- none to fill in
- License
- LicenseRef-n8n-SUL, source available
- Listed. It is in the catalog but not verified. Back up the data volume before changing an image tag.
- Host ports. It publishes port 5678 on the host, so open them in the VPS firewall only if you want that.
Install Levelrail first
On a server with Levelrail running, run the command above, or open the dashboard: Apps, New app, Browse templates, then n8n AI Starter Kit. New to Levelrail? Install it on a fresh VPS first.
docker pull ghcr.io/glincker/levelrail:latest Then levelrail-cli login --device. See Getting started and the n8n AI Starter Kit docs page.
Deploy n8n AI Starter Kit your way
Every format below deploys the same pinned images. Pick the one that fits how you work.
Deploy n8n AI Starter Kit from the CLI
levelrail-cli templates deploy n8n-ai-starter --name my-n8n-ai-starter Deploy n8n AI Starter Kit with the API
curl -X POST -H "Authorization: Bearer $TOKEN" \
https://levelrail.example.com/api/v1/service-templates/n8n-ai-starter/deploy n8n AI Starter Kit configuration
n8n AI Starter Kit services
| Service | Image | Ports | Volumes |
|---|---|---|---|
| db | postgres:16-alpine | none | n8n_ai_db_data -> /var/lib/postgresql/data |
| n8n | n8nio/n8n:1.62.1 | 5678 | n8n_ai_data -> /home/node/.n8n |
| ollama | ollama/ollama:0.34.4 | none | n8n_ai_ollama -> /root/.ollama |
| qdrant | qdrant/qdrant:v1.12.4 | none | n8n_ai_qdrant -> /qdrant/storage |
n8n AI Starter Kit environment variables
| Variable | Service | Value |
|---|---|---|
| POSTGRES_DB | db | Preset by the template |
| POSTGRES_PASSWORD | db | Generated at deploy |
| POSTGRES_USER | db | Preset by the template |
| DB_POSTGRESDB_DATABASE | n8n | Preset by the template |
| DB_POSTGRESDB_HOST | n8n | Preset by the template |
| DB_POSTGRESDB_PASSWORD | n8n | Generated at deploy |
| DB_POSTGRESDB_USER | n8n | Preset by the template |
| DB_TYPE | n8n | Preset by the template |
Show all 10 variables
- N8N_ENCRYPTION_KEYn8nGenerated at deploy
- OLLAMA_HOSTn8nPreset by the template
Ports and volumes
- Ports
- 5678
- Volumes
- 4 named mounts: n8n_ai_db_data -> /var/lib/postgresql/data, n8n_ai_data -> /home/node/.n8n, n8n_ai_ollama -> /root/.ollama, n8n_ai_qdrant -> /qdrant/storage
n8n AI Starter Kit FAQ
How much memory does n8n AI Starter Kit need?
The catalog lists about 4 GiB of memory for n8n AI Starter Kit across its 4 services.
Does n8n AI Starter Kit run on arm64?
For n8n AI Starter Kit, an arm64 image is published; amd64 is image published.
What licence is n8n AI Starter Kit under?
n8n AI Starter Kit is licensed under LicenseRef-n8n-SUL, which is source-available, so read the terms before commercial use.
Does n8n AI Starter Kit need configuration before it starts?
No. The template fills in its own defaults and generates secrets at deploy time.
Which database does n8n AI Starter Kit bundle?
The template includes Postgres, running as its own service.
Which ports does n8n AI Starter Kit use?
n8n AI Starter Kit listens on port 5678 inside the stack.
Where does n8n AI Starter Kit keep its data?
In named volumes: n8n_ai_db_data mounted at /var/lib/postgresql/data, n8n_ai_data mounted at /home/node/.n8n, n8n_ai_ollama mounted at /root/.ollama and n8n_ai_qdrant mounted at /qdrant/storage.
Can I deploy n8n AI Starter Kit on Dokploy or Dokku?
The services and pinned images on this page can be run on any Docker host. The public Dokploy templates list we compared does not have an entry with the same id for n8n AI Starter Kit, so on Dokploy you would use a Docker Compose application with the file from this page. Dokku deploys container images with its own commands, so the pinned image postgres:16-alpine, n8nio/n8n:1.62.1, ollama/ollama:0.34.4, qdrant/qdrant:v1.12.4 is what you deploy there.