jevbooks

← All projects

OpenDecision

deepanwadhwa/OpenDecision

Open-source semantic decision engine for structured state and documents.

Scoring & Ranking26%Runner-up: Agent Decisions

What it is

OpenDecision is a local semantic decision engine for developers. It accepts application state or documents and typed questions, returning structured answers without generating text. It provides a Python API, FastAPI server, and TypeSafe SDK compatible endpoint.

How it uses Jev

OpenDecision uses the same core pattern as Jev: state plus typed questions in, structured answers out. It answers Choice, Noul, and Score questions from structured state or documents. Results are used directly in code, e.g., result["choice"] returns the selected option.

Primitives:choicenoulscore

Technique worth stealing

Local zeroshot classification with ModernBERT-large-zeroshot-v2.0 for calibrated probabilities.

Try it

pip install OpenDecision; run engine.choice() or opendecision 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-centricyes0.91
  • Shows a System One patternno0.38
  • Handles uncertaintyno0.04
  • Measuredno0.05
  • Runnableyes0.83
  • Worth recommendingno0.27
  • Model replicayes0.90
  • Problem scopescore on a 0–2 scale1.32
  • About Jevyes0.93

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 21 Sept 2026.