Automated README summary
Automatically summarized from the README on 1 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Rust command, library and Python package that asks OpenRouter decision models typed questions about text or images and returns probabilities instead of prose. Jev is the default model; fuzzy rules combine answers into policy outcomes.
How it uses Jev
Jev answers each typed question (Choice, Score, Noul) about the same state independently, returning calibrated probabilities. A rules file reads each probability as the degree a condition holds, combines them with AND, OR, NOT and hedges into support scores or crisp outputs, and can be drawn as SVG.
Primitives:choicescorenoul
Technique worth stealing
Treating model probabilities as fuzzy membership degrees, then combining them with fuzzy logic operators into policy support scores.
Try it
cargo install fuzzy-jev --locked, set OPENROUTER_API_KEY, then run jev with --noul, --choice or --score flags.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 excerpt0.25
- Shows a System One patternnot found in the excerpt0.32
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalnot found in the excerpt0.31
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.20 / 2
- About JevFound in material0.98
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 1 Nov 2026.