Diagnostics recipe

Find out what's listening before you debug for an hour

Your local AI setup stops working and you don't know whether the model runner died, the port changed, or something else grabbed the port.

diagnostics local model developer Free tier + a local model

What you get

A diagnostic brief on your desktop telling you what responded and what didn't.

What it does

  1. Probe the local endpoints your AI tools use.
  2. Have a local model turn the raw results into a readable diagnosis.
  3. Save the brief and notify you.

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": "system-diagnostics",
  "description": "Performs system port probe check, checks for active AI servers, and outputs a diagnostic brief.",
  "tasks": [
    {
      "id": "probe_ports",
      "trigger": "manual",
      "action_type": "http_request",
      "target": "http://localhost:8990/vibra/discovery",
      "payload": {
        "method": "GET"
      },
      "next": "ai_diagnose_system"
    },
    {
      "id": "ai_diagnose_system",
      "trigger": "after:probe_ports",
      "action_type": "ai_call",
      "target": "local",
      "payload": {
        "model": "llama3.2:3b",
        "system": "You are a systems engineer. Look at the local discovery JSON payload and summarize active systems and client integrations in plain English.",
        "prompt": "Here is the local system discovery scan data:\n\n{{prev_output}}\n\nCheck if local servers like Ollama or LM Studio are online. Check which IDE integrations are active. Write a 1-page health report in markdown."
      },
      "next": "save_health_report"
    },
    {
      "id": "save_health_report",
      "trigger": "after:ai_diagnose_system",
      "action_type": "file_op",
      "target": "{{desktop_dir}}\\system_diagnostic_brief.md",
      "payload": {
        "operation": "write",
        "content": "# \ud83d\udee0\ufe0f Local AI Environment Diagnostics\n*Generated by Vibe Engine System Scanner*\n\n{{prev_output}}"
      },
      "next": "notify_done"
    },
    {
      "id": "notify_done",
      "trigger": "after:save_health_report",
      "action_type": "notify",
      "target": "stdout",
      "payload": {
        "message": "\u2713 System Diagnostics Brief saved to Desktop: system_diagnostic_brief.md"
      }
    }
  ]
}

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

Why this is different

It's a health check you can read and edit, not a status light in someone else's dashboard.

Questions

Which ports does it check?

The ones listed in the file, which you can extend to any local service.

Does it need internet?

No. Everything it touches is on your own machine.

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