Commands

One page per command. spinloop version prints the version, and spinloop help the usage summary.

Command	What it does
spinloop status	What every engine you run is doing, one row each — a fleet, or one environment
spinloop dashboard	The live tiled view of the same, with the keys to drive it
spinloop metrics	What each engine is doing with its hardware, and what it has cost
spinloop logs	What each engine has said — a daemon's log file or an environment's log store
spinloop code	Launch the active harness — a one-word shortcut for spinloop harness open
spinloop harness	Configure the agent (add, remove, apply, unapply, show, export), launch it (open), and set the default (config)
spinloop provider	Work with the provider catalogue (list, init)
spinloop serve	Run the inference server for the model a Spinloop names
spinloop daemon	Supervise an engine over the control API, so anything that can reach the machine can start, stop, and watch it
spinloop up	Start the engine this directory holds: the fleet, or the Spinloop's server
spinloop fleet	Drive the engines on every machine you run: start, stop, deploy, route
spinloop gateway	Serve the fleet under one OpenAI-compatible endpoint
spinloop orchestrator	Work a backlog of items against the fleet, at the fleet's declared pace
spinloop work	Drive the orchestrator's work list from the shell: add, list, logs, abort, remove
spinloop remote	Run the model on a cloud GPU that stops when you do
spinloop hf	Write a Spinloop for a Hugging Face model, from its page reference
spinloop alias	Name a Spinloop so the name works anywhere a path does
spinloop unalias	Drop a registered name
spinloop completion	Tab completion for your shell