SEC.01

The playbook

The run starts read-only: the recon probes decide what happens next. The steps that follow are adapted to the distribution and state found — a real machine is rarely clean.

1. 01reconHomebrew present?
2. 02reconOllama already present?
3. 03actInstall Ollamaverify
4. 04actDownload the modelverify

SEC.02

What it verifies

Each step ships its own check. The run only moves on when the check passes, so what the recipe reports as done is what is actually on the server.

1. 01verifyInstall OllamaVerified bycurl -sf http://localhost:11434/api/tags >/dev/null && echo ok
2. 02verifyDownload the modelVerified byollama list | grep -c "${model}"

SEC.03

Variables

What you choose before launching — the recipe fills in the rest.

SEC.04

How a recipe runs in Servor

Servor is zero-knowledge: the platform cannot execute anything on its own. When you launch this recipe, a run reads the reconnaissance, plans the steps and asks for your approval. Each approved command is signed by your browser — with a key the server never sees — then relayed verbatim to the agent, which verifies the signature locally before executing.

SEC.05

More ai / ml recipes

1. 01OllamaOllama to run local LLMs (optional model pull).
2. 02JupyterLabJupyterLab via Docker, with an access token.
3. 03Open WebUIOpen WebUI, a web interface for LLMs (Ollama) via Docker.
4. 04NVIDIA drivers + CUDANVIDIA drivers and CUDA toolkit. Destructive: kernel modules, reboot likely.
5. 05ComfyUI (Stable Diffusion)ComfyUI for image generation via Docker (GPU recommended).