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. 02reconNVIDIA GPU present with a working driver (name, VRAM, driver version)? otherwise: GPU without driver, or no GPU (CPU mode)
3. 03reconPython ≥ 3.10 (3.12/3.13 recommended) and git available?
4. 04reconComfyUI already installed (folder, service or container)? healthy → verify and skip; never delete the models
5. 05reconport 8188 free?
6. 06reconRAM ≥ 8 GB (16 GB recommended), disk ≥ 20 GB (PyTorch + models of 2 to 7 GB each)
7. 07actInstall git, Python and venvverify
8. 08actCreate the dedicated comfyui userverify
9. 09actClone ComfyUIverify
10. 10actCreate the venv and install PyTorch (CUDA with a GPU, CPU otherwise)verify
11. 11actInstall the ComfyUI dependenciesverify
12. 12actcomfyui systemd service (127.0.0.1:8188)verify
13. 13actResponds over HTTPverify

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 git, Python and venvVerified bypython3 -m venv --help >/dev/null && git --version
2. 02verifyCreate the dedicated comfyui userVerified bystat -c '%U' /opt/comfyui
3. 03verifyClone ComfyUIVerified bytest -f /opt/comfyui/app/main.py && echo ok
4. 04verifyCreate the venv and install PyTorch (CUDA with a GPU, CPU otherwise)Verified by/opt/comfyui/venv/bin/python -c "import torch; print(torch.__version__, torch.cuda.is_available())"
5. 05verifyInstall the ComfyUI dependenciesVerified by/opt/comfyui/venv/bin/pip check
6. 06verifycomfyui systemd service (127.0.0.1:8188)Verified bysystemctl is-active comfyui
7. 07verifyResponds over HTTPVerified bytimeout 180 bash -c 'until curl -sf -o /dev/null http://127.0.0.1:8188/; do sleep 5; done'; curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8188/

SEC.03

Guardrails

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

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

Deploy on Servor button

Maintain ComfyUI (Stable Diffusion) 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.06

More ai / ml recipes

1. 01OllamaOllama to run local LLMs (NVIDIA GPU if present, CPU otherwise), API on 127.0.0.1, optional model pull.
2. 02JupyterLabJupyterLab via Docker, on 127.0.0.1 with a generated access token (access through an SSH tunnel).
3. 03Open WebUIOpen WebUI, a web interface for LLMs (Ollama), via Docker on 127.0.0.1, wired to the local Ollama.
4. 04NVIDIA drivers + CUDANVIDIA driver, CUDA toolkit and Docker Container Toolkit from the official repositories. Destructive: kernel modules, restart likely.
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.