System One Harness

The harness for System One models.</sub>
</h1>

<p align="center">
  <a href="https://github.com/HarnessRouter/SystemOneHarness" title="Star System One Harness on GitHub"><img src="https://img.shields.io/github/stars/HarnessRouter/SystemOneHarness?style=flat&amp;logo=github&amp;logoColor=white&amp;label=Stars&amp;labelColor=444c56&amp;color=285aff" alt="GitHub stars"></a>
  <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-285AFF?style=flat&amp;labelColor=444c56" alt="License: Apache 2.0"></a>
  <a href="pyproject.toml"><img src="https://img.shields.io/badge/Version-0.3.1-285AFF?style=flat&amp;labelColor=444c56" alt="Version 0.3.1"></a>
  <a href="docs/reports/uhp-conformance-core-2026-09-19.json"><img src="https://img.shields.io/badge/UHP-Core-16824B?style=flat&amp;labelColor=444c56" alt="UHP conformance: Core"></a>
  <a href="pyproject.toml"><img src="https://img.shields.io/badge/Python-3.10%2B-285AFF?style=flat&amp;labelColor=444c56" alt="Python 3.10 or newer"></a>
</p>

**Turn a System One decision model into an agent loop.** System One Harness observes an environment, compiles its finite action space into typed questions, gates each decision by confidence, executes the chosen action, and records the complete trace.

One model call per step. No generated actions. A probability on every transition.

<p align="center">
  <img src=".github/images/system-one-browser-gameplay-demo.gif" width="100%" alt="Jev uses System One Harness to play a live browser game by choosing one typed action per step.">
  <br>
  <sub><strong>Jev playing a live browser game through System One Harness</strong> — one typed decision per step, with no generated control text.</sub>
</p>

The first supported model is [Jev](https://typesafe.ai) by TypeSafe, available throu