Loading page
Loading page

Automation · Zapier alternative
n8n with a worker, an external task runner, Redis, PostgreSQL and a local Ollama server, so your AI workflows can run on local models.
This is a full n8n stack for AI workflows. It runs the n8n main instance, a worker that executes workflows from a Redis queue, and an external task runner for Code nodes. PostgreSQL stores the data. An Ollama server runs alongside, so n8n's AI agent and chat model nodes can call models on your own server.
n8n itself lets you build workflows on a visual canvas, with JavaScript or Python when you need it. It connects to more than 1,500 apps and can switch between model providers.
It suits teams who want AI automation but cannot send their data to a cloud model. It also fits developers who want to try local models in real workflows, with room to grow.
Cloud AI calls cost money per token, and your data passes through the provider. With Ollama next to n8n, prompts and documents stay inside your service, and there is no per-token bill.
The trade-off is hardware. Language models need a lot of memory, and they run slowly without a GPU. This template uses latest and nightly image tags, so updates can bring changes without warning. Pin versions if you need stability. You look after updates and backups of the database yourself.
Containers: n8nio/n8n:latest, docker.n8n.io/n8nio/n8n:latest, n8nio/runners:nightly, ollama/ollama:latest, redis:7-alpine, postgres:17-alpine
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose n8n + Worker + Runner with Redis/Postgres and Ollama, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the n8n + Worker + Runner with Redis/Postgres and Ollama setup screen.