jevbooks

← All projects

ruling

bradAGI/ruling

Typed, calibrated decisions from a local model. No text generated.

What it is

ruling turns any open chat model into a decision engine like TypeSafe's Jev. You send a state and typed questions; you get back a probability for every option you declared. Nothing is generated, so there is nothing to parse and the model cannot invent an answer you did not list.

How it uses Jev

ruling is a System One-compatible server that scores typed questions from a stock model's logits with no training. It accepts the official SDK unchanged and re-scores the 256 public judgments that carry Jev's own answers (231 vs 238, no significant difference). It serves MLX checkpoints or any OpenAI-compatible endpoint.

Primitives:choicescorenoul

Technique worth stealing

Score typed questions from a stock model's logits with no training, then calibrate confidence with a short LoRA fine-tune on your own labeled decisions.

Try it

uv sync && uv run ruling serve

View on GitHub

judged by Jevjev-1.13.0

Evidence

Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.

  • Jev-centricyes0.70
  • Shows a System One patternno0.30
  • Handles uncertaintyno0.05
  • Measuredyes0.93
  • Runnableyes0.94
  • Worth recommendingno0.31
  • Model replicayes0.84
  • Problem scopescore on a 0–2 scale1.06
  • About Jevyes0.97

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 23 Sept 2026.