Automated README summary
Automatically summarized from the README on 13 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An MCP server that lets any chat model delegate fast, calibrated decisions to Jev-style "System One" decision models served locally by Ollama, useful for batches, thresholdable numbers, and helping small models.
How it uses Jev
Tools take texts (1–100 strings) plus a typed question and return probabilities: classify returns a choice, confidence and probabilities; yes_no returns probability_yes; score returns the nearest level, raw score, scale max and confidence. Results come back in input order.
Primitives:choicescorenoul
Technique worth stealing
Batch many texts in one tool call and keep calibrated probabilities instead of a model saying "probably".
Try it
ollama pull nimble; npm install; npm run build; then add the stdio server to your MCP client.
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 material0.78
- Shows a System One patternnot found in the excerpt0.21
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.30
- Is a replica of the modelunclear0.52
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 2
- About JevFound in material0.97
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 13 Oct 2026.