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. 01recondistro, version and package manager (apt or dnf)
2. 02reconOllama already installed? which version?
3. 03reconservice active? listening on 127.0.0.1:11434 or exposed (OLLAMA_HOST=0.0.0.0)? port taken by something else?
4. 04reconNVIDIA GPU present with a working driver (name, VRAM, driver version)? otherwise: GPU without driver, or no GPU (CPU mode)
5. 05reconRAM (≥ 8 GB for a 7-8B model, ≥ 16 GB for 13B) and free disk (a model = 2 to 40 GB, stored under /usr/share/ollama)
6. 06actInstall Ollama (official script)verify
7. 07actService active and local APIverify
8. 08actPull the model (only if a model is provided)verify

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 Ollama (official script)Verified byollama --version
2. 02verifyService active and local APIVerified bysystemctl is-active ollama && curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:11434/api/version
3. 03verifyPull the model (only if a model is provided)Verified byollama list | grep -cF '${model}'

SEC.03

Guardrails

Non-negotiable instructions the run must respect, whatever it finds on the server.

SEC.04

Variables

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

SEC.05

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.06

Deploy on Servor button

Maintain Ollama or a project that needs it? Put this button in your README or on your site: one click and your users install it on their own server.

SEC.07

More ai / ml recipes

1. 01JupyterLabJupyterLab via Docker, on 127.0.0.1 with a generated access token (access through an SSH tunnel).
2. 02Open WebUIOpen WebUI, a web interface for LLMs (Ollama), via Docker on 127.0.0.1, wired to the local Ollama.
3. 03NVIDIA drivers + CUDANVIDIA driver, CUDA toolkit and Docker Container Toolkit from the official repositories. Destructive: kernel modules, restart likely.
4. 04ComfyUI (Stable Diffusion)ComfyUI for image generation, installed from the official repository as a systemd service (NVIDIA GPU recommended, CPU possible).
5. 05vLLM inference servervLLM to serve an LLM through an OpenAI-compatible API on 127.0.0.1, protected by a generated key. NVIDIA GPU required.