jevbooks

← All projects

jevia-harness

sleepy0x13/jevia-harness

A local harness that puts Jev in front of the LLM.

What it is

A local agent harness for people running tasks that are mostly typed judgements. Jev handles every judgement expressible as a type; an ordinary LLM is paid for only when prose is actually needed.

How it uses Jev

Jev answers typed questions against material: classifications, ratings, yes/no calls, each with a calibrated probability. It plans, assesses, routes, sizes each step's model, picks skills and roles, and decides app composition. Results drive rules that pick models, tools and actions.

Primitives:choicescore

Technique worth stealing

Split typed judgement from prose: one Jev call carries many judgements, and the plan is compiled once and cached for reuse.

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-centricyes0.92
  • Shows a System One patternyes0.74
  • Handles uncertaintyno0.10
  • Measuredno0.23
  • Runnableyes0.75
  • Worth recommendingunclear0.48
  • Model replicano0.13
  • Problem scopescore on a 0–2 scale1.56
  • About Jevyes0.97

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.