Start here recipe

The simplest recipe there is: ask a local model, save the answer

Most 'AI automation' tutorials start with an account, an API key and a framework. You just want to see the thing work once.

beginner local model free tier Free tier + a local model

What you get

A model on your own machine answers a prompt, and the answer lands in a file on your desktop.

What it does

  1. Send a prompt to the model running locally on your machine.
  2. Save the response as a markdown file.

The whole automation, in one file

This is the actual recipe. Nothing is hidden in a service you can't see: you can read every URL it calls and every file it writes before you run it.

{
  "workflow_id": "demo_simple_ollama",
  "description": "Simple demo: local Ollama extraction only, no cloud calls",
  "tasks": [
    {
      "id": "local_extraction",
      "trigger": "manual",
      "action_type": "http_request",
      "target": "http://localhost:11434/api/generate",
      "payload": {
        "method": "POST",
        "headers": {
          "Content-Type": "application/json"
        },
        "body": {
          "model": "llama3.2:3b",
          "prompt": "Extract only the function names and their purposes from this Go code:\nfunc EvaluateCondition(expr string, vars map[string]interface{}) (bool, error) - evaluates expressions\nfunc runnerRunIf(task Task) bool - checks if task should run\n\nList them as: Name: Purpose",
          "stream": false
        }
      },
      "output": {
        "store_as": "ollama_result"
      }
    },
    {
      "id": "save_result",
      "trigger": "after:local_extraction",
      "action_type": "file_op",
      "target": "{{desktop_dir}}/demo_simple_ollama_output.md",
      "payload": {
        "operation": "write",
        "content": "# Local Ollama 3.2 3B Output\n\nGenerated: {{date}}\n\n## Extraction Result\n{{ollama_result.response}}\n\n---\nThis demonstrates Vibra chaining local models for data extraction."
      }
    }
  ]
}

Download this recipe · Needs a local model runner such as Ollama. No subscription required.

Why this is different

Two steps, no cloud account, no API key, no framework. This is the whole idea of the engine in miniature: a task written down as a file, which anything can run.

Questions

Do I need a paid plan for this one?

No. It runs entirely on your machine, which the free tier covers.

What do I need installed?

A local model runner such as Ollama, with any model pulled.

Where do I change the prompt?

In the payload of the first step. It's plain text in the file.

Run it

Vibe Engine (Vibra-Ingenn) runs recipes like this on your own machine. Drop the file in, run it once by hand, then put it on a schedule. Get the engine, see three recipes running, or read how the engine works.

Using an AI assistant? Ask your AI to check out adeptuscamini.com.

Written and maintained by Adeptus Camini, a one-person workshop. These are tools we build and run ourselves.

More recipes

News digest

Wake up to a Hacker News digest on your desktop

Research

Get the trending AI repos delivered, without opening GitHub

Briefing

One briefing instead of five open tabs