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
A Unix-friendly command-line interface for TypeSafe AI's System One API and the Jev model, plus Cloudflare's Clef and Clef Flash. It lets scripts and pipelines ask typed questions and get calibrated probabilities.
How it uses Jev
Jev makes decisions via three primitives: Noul (does a condition hold?), Choice (which option?), and Score (where on a scale?). The CLI sends state and questions to the API and returns structured answers with probabilities, which scripts can branch on without parsing prose.
Primitives:choicescorenoul
Technique worth stealing
Use typed questions with calibrated probabilities so scripts can branch on structured output instead of parsing prose.
Try it
Download the v0.3.0 release, verify checksum, run `jev doctor`, then `jev auth login` and `jev 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 projectnot found in the excerpt0.10
- Shows a System One patternnot found in the excerpt0.07
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.32
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale1.00 / 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 6 Oct 2026.