# System One

> Discover, publish and version System One decision models — models that return a typed decision with calibrated confidence instead of generated text.

System One models return a typed decision — choose, score, rank, classify, extract or route — with a
calibrated probability, usually in milliseconds on a CPU, instead of generated text. This registry hosts
them: versioned files, a decision-native manifest (`systemone.yaml`), evaluation numbers (accuracy,
calibration error, latency) and lineage from base model to fine-tune.

Facts an agent needs:

- Install the client with `pip install systemonemodels` (Python 3.10+). It provides the `systemone` command and the `systemone` Python package.
- Models are addressed as `namespace/name`; versions are immutable strings like `0.1.0`, and `latest` resolves to the newest.
- Non-interactive use: set `SYSTEMONE_TOKEN` to a personal access token (`s1_pat_…`) and skip `systemone login`, which needs a person to approve it in a browser.
- Download: `systemone pull namespace/name [--version V] [--variant FOLDER] [--dest DIR]`. Files are SHA-256 verified and cached by content.
- Publish: `systemone push DIR --repo namespace/name` for one model folder, or `systemone push DIR --all` to publish every model found under DIR; run it with `--dry-run` first. The version defaults to the next free one, and a README.md becomes the model card.
- HTTP API base: https://api.systemonemodels.tech, documented at https://systemonemodels.tech/docs/api. Errors are `{"detail", "code", "errors"}`; honour `Retry-After` on 429.

## Docs

- [Why a different home](https://dev.systemonemodels.tech/docs/why-a-different-home.md): System 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.
- [Getting started](https://dev.systemonemodels.tech/docs/getting-started.md): Create an account, publish a decision model, and understand what the registry stores.
- [systemone.yaml](https://dev.systemonemodels.tech/docs/manifest.md): The manifest specification — the decision-native metadata that makes models on the registry comparable.
- [SDK and CLI](https://dev.systemonemodels.tech/docs/sdk.md): The systemone Python package: browser login, search, pull with a shared cache, create and push.
- [CLI reference](https://dev.systemonemodels.tech/docs/cli.md): Every systemone command and option, the environment variables it reads, exit codes, and recipes for scripts, CI and AI coding agents.
- [HTTP API](https://dev.systemonemodels.tech/docs/api.md): The registry API: authentication, search, downloads, publishing, device login, organizations and builds.
- [Fine-tuning with Laya Studio](https://dev.systemonemodels.tech/docs/fine-tuning.md): Train a decision model locally with Laya Studio and publish the result, with lineage recorded automatically.

## Client

- [CLI reference](https://dev.systemonemodels.tech/docs/cli.md): every command, option and environment variable
- [systemonemodels on PyPI](https://pypi.org/project/systemonemodels/): the published package
- [Source code](https://github.com/systemonemodels/systemonemodels-sdk): Apache-2.0

## API

- [HTTP API guide](https://dev.systemonemodels.tech/docs/api.md): authentication, search, downloads, publishing, device login

## Optional

- [All documentation in one file](https://dev.systemonemodels.tech/llms-full.txt)
- [Browse models](https://dev.systemonemodels.tech/models): search by capability, architecture, licence, accuracy and latency
- [Builds](https://dev.systemonemodels.tech/builds): things people have built with System One models
- [Compare](https://dev.systemonemodels.tech/compare?models=a/b,c/d): up to four models side by side — accuracy, calibration, latency, size
- [Hosted models](https://dev.systemonemodels.tech/models?availability=hosted-api): commercial System One models served behind an API, with provider, price and status
- [Blog](https://dev.systemonemodels.tech/blog): articles on decision models, Laya and Jev ([RSS](https://dev.systemonemodels.tech/blog/rss.xml))
- [About](https://dev.systemonemodels.tech/about): why System One models need their own home