Automated README summary
Automatically summarized from the README on 31 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A dependency-free Node 20+ client library and stdio MCP server that expose Jev's typed judgments (check, route, score, evaluate) to DeepSeek Harness native modes and code mode.
How it uses Jev
Jev answers typed questions against a state: noul for yes/no checks, choice for routing, score for rubric ratings, or a mixed evaluate call. The library returns probabilities, verdicts, choices, scores, model id and usage; code mode imports it directly, and the MCP server exposes the same four operations as tools.
Primitives:choicescorenoul
Technique worth stealing
Map jev_check probabilities to coarse verdicts with tunable thresholds (act 0.7, ask 0.4) rather than treating them as calibrated policy.
Try it
Run node examples/demo.mjs for four end-to-end judgments, or node examples/triage.mjs "npm test".
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 projectFound in material0.96
- Shows a System One patternnot found in the excerpt0.28
- Describes handling uncertaintynot found in the excerpt0.25
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.25 / 2
- About JevFound in material0.99
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 31 Oct 2026.