Automated README summary
Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Jev-Lite is an open-source decision engine for backend systems that need fast, structured decisions from state context. It evaluates typed questions in a single forward pass, returning probabilities and confidence scores without text generation.
How it uses Jev
Jev-Lite uses Jev to evaluate Choice, Score, and Noul questions against a cached state context. It ingests state once, expands the KV cache across candidate sequences, and scores them via length-normalized log-likelihoods. Results are returned as probabilities and confidence for direct code branching.
Primitives:choicescorenoul
Technique worth stealing
Use vocabulary log-likelihoods with cached state KV and length-normalized sequence scoring instead of embedding heads.
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 projectFound in material0.62
- Shows a System One patternunclear0.43
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.76
- Top-10 learning shortlist signalnot found in the excerpt0.20
- Is a replica of the modelFound in material0.84
- Solves a common problem (0–2)score on a 0–2 scale1.90 / 2
- About JevFound in material0.80
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 6 Oct 2026.