Automated README summary
Automatically summarized from the README on 17 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A self-contained Rust binary exposing a TypeSafe-compatible REST API for agent decision models (Choice, Score, Noul, Route), aimed at developers running autonomous agents who want offline, zero-cost, low-latency decisions.
How it uses Jev
Jev-style decisions are served over HTTP: POST /v1/systemone/choice takes a state, question and options, extracts logits in a single forward pass, and returns a constrained softmax choice with confidence and per-option probabilities. Also exposes noul, route, batch, and a speculative tool-call proxy.
Primitives:choicescorenoul
Technique worth stealing
Single-forward-pass logit extraction with vocabulary masked to candidate options, then temperature-scaled softmax for calibrated choice probabilities.
Try it
cargo install local-jev, then run `local-jev serve --port 8080` and POST to /v1/systemone/choice.
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 material0.86
- Shows a System One patternnot found in the excerpt0.22
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.87
- Is a runnable toolFound in material0.89
- Top-10 learning shortlist signalnot found in the excerpt0.12
- Is a replica of the modelFound in material0.88
- Solves a common problem (0–2)score on a 0–2 scale1.03 / 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 17 Oct 2026.