Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A macOS menu-bar app, browser Workbench, and shared POST /v1/decision gateway for local and hosted decision models, used to benchmark local LLMs against TypeSafe on logic and bounded-decision tasks.
How it uses Jev
The gateway accepts Choice, Score, and Noul schemas and adapts each request to the selected provider (TypeSafe, Ollama decision models, OpenRouter, Liquid D1, OpenAI adapters). The Workbench sends one evidence context with multiple typed fields per request and displays returned fields, probabilities, latency, and raw response.
Primitives:choicescorenoul
Technique worth stealing
Score all bounded decision fields from one context in parallel, return probabilities, and assemble the JSON in code instead of generating free-form text.
Try it
Open http://127.0.0.1:8096 in the Workbench, select a case, and run it through the selected provider.
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 excerpt0.33
- Shows a System One patternnot found in the excerpt0.10
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.84
- Top-10 learning shortlist signalnot found in the excerpt0.39
- Is a replica of the modelnot found in the excerpt0.14
- Solves a common problem (0–2)score on a 0–2 scale1.27 / 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 4 Nov 2026.