Loading the docs…
DOCUMENTATION
Documentation for System One — publishing decision models, the systemone.yaml specification, the SDK and CLI, the HTTP API, and fine-tuning with System One Studio.
New to decision models? 9 short lessons, about 60 minutes, from what a System One model is to calling, running, fine-tuning and publishing one. With a certificate at the end.
Start the courseSystem One models decide instead of write. Why they need a registry of their own rather than a corner of a hub built for language models.
ReadCreate an account, publish a decision model, and understand what the registry stores.
ReadThe manifest specification — the decision-native metadata that makes models on the registry comparable.
ReadThe systemone Python package: browser login, search, pull with a shared cache, create and push.
ReadEvery systemone command and option, the environment variables it reads, exit codes, and recipes for scripts, CI and AI coding agents.
ReadCall the models the System One Engine serves from your own code: API keys, the request and the answer, plans and limits, and errors.
ReadThe registry API: authentication, search, downloads, publishing, device login, organizations and builds.
ReadTrain a decision model locally with System One Studio (formerly Laya Studio) and publish the result, with lineage recorded automatically.
ReadHow a decision model gets live inference on System One Models: the layouts the System One Engine runs, publishing, a live playground and analytics.
ReadNoulXP is the open standard for System One models: package a decision model once, prove it answers as its own code does, calibrate it, and run it anywhere over HTTP or MCP.
ReadA ten-minute guide: package a System One model so any engine runs it without your code, prove it with a conformance file, and publish it to earn the NoulXP compatible badge.
ReadThe open-source fine-tuning environment for Laya decision models. Train locally, evaluate calibration, and publish the result here.
Open System One Studio