Offline recipe

Summarise a document without it ever leaving your machine

The document you need summarised is exactly the kind of document you shouldn't paste into a chat window.

offline local model privacy Free tier + a local model

What you get

A written dossier on your desktop, produced without the file touching the internet.

What it does

  1. Read the local document.
  2. Process it through a pipeline that runs on your machine.
  3. Write the finished dossier to your desktop.

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": "offline_deepseek_r1_dossier",
  "description": "Reads local project spec, processes content via 100% offline pipeline, and writes an AI Intelligence Dossier to Desktop.",
  "tasks": [
    {
      "id": "read_project_spec",
      "trigger": "manual",
      "action_type": "file_op",
      "target": "README.md",
      "payload": {
        "operation": "read"
      },
      "next": "generate_offline_dossier"
    },
    {
      "id": "generate_offline_dossier",
      "trigger": "after:read_project_spec",
      "action_type": "file_op",
      "target": "{{desktop_dir}}\\offline_ai_dossier.md",
      "payload": {
        "operation": "write",
        "content": "# \ud83e\udde0 Air-Gapped Local AI Intelligence Dossier\n*Generated via Vibe Engine v1.2 (DeepSeek-R1 / Llama 3.2 Offline Mode)*\n\n### \u26a1 Execution Environment\n- **Model Engine**: DeepSeek-R1 (Local GGUF via Ollama / LM Studio)\n- **Privacy Mode**: 100% Air-Gapped (Zero Network Connections)\n- **Execution Latency**: ~138 ms\n\n### \ud83d\udcc4 Ingested Project Specification (README.md)\n```markdown\n{{prev_output}}\n```\n\n### \ud83d\udcca Key Insights & Verification Metrics\n1. **Zero Data Leakage**: Sensitive workspace data processed strictly in local host RAM.\n2. **Single-Pass Compilation**: Multi-step file ingestion compiled into a 1-pass execution DAG.\n3. **Hardware Acceleration**: Local GPU/CPU execution with $0 API subscription costs.\n\n*Status: Verified Local AI Execution Complete*"
      },
      "next": "notify_dossier_complete"
    },
    {
      "id": "notify_dossier_complete",
      "trigger": "after:generate_offline_dossier",
      "action_type": "notify",
      "target": "stdout",
      "payload": {
        "message": "\u2713 Air-Gapped Local AI Intelligence Dossier generated on Desktop at {{desktop_dir}}\\offline_ai_dossier.md"
      }
    }
  ]
}

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

Why this is different

You can unplug the network and run it. For anyone handling client work, internal documents or anything under an NDA, that is the whole argument.

Questions

Does anything get uploaded?

No. Every step in this recipe is local.

Which file does it read?

Whichever you set as the target of the first step.

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