What it is
A Python toolkit and nine agent skills that route models, filter retrieved passages, select skills, and choose bounded computer or browser actions for Hermes, Claude Code, and Codex agents.
How it uses Jev
Jev answers typed questions (Choice/Score/Noul) on agent state: which model, which passages, which skill, which turn, which action. Results are calibrated probabilities used by the agent to make small decisions without writing text.
Primitives:choicescorenoul
Technique worth stealing
Use a cheap decision model for small choices, leaving frontier models for writing.
Try it
git clone https://github.com/kerpopule/hermes-jev-skills ~/hermes-jev-skills && python3 ~/hermes-jev-skills/install.py
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-centricyes0.90
- Shows a System One patternyes0.90
- Handles uncertaintyno0.08
- Measuredno0.17
- Runnableyes0.96
- Worth recommendingunclear0.57
- Model replicano0.04
- Problem scopescore on a 0–2 scale1.35
- About Jevyes0.98
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 21 Sept 2026.