Self-host n8n AI Starter Kit on a VPS
n8n wired to a local Ollama model and a Qdrant vector store, ready for private AI workflows.
levelrail-cli templates deploy n8n-ai-starter --name my-n8n-ai-starterSpecification
- Status
- Listed
- Category
- AI
- Services
- db, n8n, ollama, qdrant
- Ports
- 5678
- Volumes
- 4
- Memory
- about 4 GiB
- arm64
- image published
- amd64
- image published
- Settings to fill in
- none
About n8n AI Starter Kit
n8n wired to a local Ollama model and a Qdrant vector store, ready for private AI workflows. Runs 4 containers (db, n8n, ollama, qdrant), with n8n listening on port 5678; data is kept in named volumes.
What it deploys
n8n AI Starter Kit runs as 4 services in a single Compose app, listening on port 5678, with 4 named volume mounts.
| Service | Image | Tag | 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 |
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.
- Listed. It is in the catalog. Back up the data volume before changing an image tag.
- Host ports. It publishes port 5678 directly on the host, so open them in the VPS firewall only if you want that.
Settings and environment
You do not have to fill in anything. 3 secrets are generated at deploy and stored encrypted. Values are never shown here.
| Service | Variable | Value |
|---|---|---|
| db | POSTGRES_DB | Preset by the template |
| db | POSTGRES_PASSWORD | Generated at deploy |
| db | POSTGRES_USER | Preset by the template |
| n8n | DB_POSTGRESDB_DATABASE | Preset by the template |
| n8n | DB_POSTGRESDB_HOST | Preset by the template |
| n8n | DB_POSTGRESDB_PASSWORD | Generated at deploy |
| n8n | DB_POSTGRESDB_USER | Preset by the template |
| n8n | DB_TYPE | Preset by the template |
| n8n | N8N_ENCRYPTION_KEY | Generated at deploy |
| n8n | OLLAMA_HOST | Preset by the template |
Install n8n AI Starter Kit 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 n8n-ai-starter -
Deploy it
This deploys the template compose file as an app. The app name defaults to the template id; --name sets another.
levelrail-cli templates deploy n8n-ai-starter --name my-n8n-ai-starter
Without a domain the app gets an sslip.io address. You can also deploy it from the dashboard: Apps, New app, Browse templates, then n8n AI Starter Kit.
Docs and upstream
More in AI
- n8n MCPA Model Context Protocol server that gives AI assistants searchable n8n node documentation. MIT licensed. The bearer token is generated for you.
- New APIAn LLM gateway and AI asset management system that unifies many model providers.
- MLflowTrack experiments, compare runs, and manage models with a self-hosted MLflow tracking server.
- MindsDBA query layer that connects data sources and AI models so you can ask questions in SQL. MIT licensed. Includes the web editor and the HTTP API.
- MetaMCPAn MCP aggregator and gateway that groups many MCP servers behind one endpoint with auth, namespaces and middleware.
- OllamaA local LLM runtime with an HTTP API. Pull any model yourself once it's running.