Automated README summary
Automatically summarized from the README on 14 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A dated snapshot of glue code, setup scripts, Jev-compatible servers, and a benchmark harness for running open typed-decision models (Laya, Decider, imajev, Winnow-12B, decider-12b) on a Snapdragon X Elite laptop's NPU, GPU, and CPU.
How it uses Jev
The harness (jevcmp.py) runs any /v1/systemone endpoint, including TypeSafe's Jev API, to compare accuracy and latency. Jev is used as a reference for benchmark scores; the README does not describe using Jev to make decisions in the project's own code.
Primitives:choicescorenoul
Technique worth stealing
Packing multiple typed questions into one NPU pass to reduce latency.
Try it
Run laya/win/setup_env.ps1 -Name npu, then build NPU contexts.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectnot found in the excerpt0.27
- Shows a System One patternnot found in the excerpt0.10
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.10
- Is a runnable toolnot found in the excerpt0.24
- Top-10 learning shortlist signalnot found in the excerpt0.28
- Is a replica of the modelnot found in the excerpt0.31
- Solves a common problem (0–2)score on a 0–2 scale0.71 / 2
- About JevFound in material0.97
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 14 Oct 2026.