What it is
A software development framework for AI coding agents, upgrading the obra/superpowers methodology with TypeSafe Jev System One to gate architecture, dependency, shell, and completion decisions.
How it uses Jev
Jev gates architectural forks, dependency selection, shell commands, and completion checks. The README does not specify the exact state or typed questions passed to Jev, nor how its probabilities are consumed in code.
Primitives:choicescore
Technique worth stealing
Gate every agent decision with sub-second deterministic mathematical judgments instead of generative LLM calls.
Try it
curl -fsSL https://raw.githubusercontent.com/AkashPriyadarshii/jev-superpowers/master/install.sh | bash
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-centricyes0.79
- Shows a System One patternunclear0.60
- Handles uncertaintyno0.07
- Measuredno0.05
- Runnableyes0.67
- Worth recommendingno0.32
- Model replicano0.09
- Problem scopescore on a 0–2 scale1.36
- About Jevyes0.97
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.