index / gordan-code/jev-metrics
jev-metrics
用 TypeSafe Jev 给 AI coding agent 做持续代码质量 review 的校准审计层。持久化 19 维质量分数,输出趋势矩阵、假阳性置信检测、rubric 漂移与 ECE 校准曲线。Node 22+,零运行时依赖,CLI + GitHub Action,直接消费 jev_review 的 MCP 评估结果。
Research and EvalsFeature ScoringListedTypeScript
Repository
Stars1
LanguageTypeScript
License—
Created2026-09-21
Last pushed2026-09-21
Officialno
Judgment
Genuine Jev project0.82
gate 0.5
Uses Jev at runtime0.16
Is a meta list0.04
Is a reimplementation0.06
Quality scales
Substance2.23 / 3
gate 0.5
Docs2.39 / 3
Novelty2.92 / 3
Composite score0.84
Category distribution
Research and Evals0.84
Agent and Dev Tooling0.13
Applications0.01
SDKs and Clients0.01
Integrations0.01
Other0.00
Learning0.00
Games and Simulation0.00
Assigned categoryResearch and Evals
Category probability0.84
Category confidence0.82
PatternFeature Scoring
Pattern confidence0.75
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:jev in:name,description,readme created:2026-09-21
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-09-21 12:34 UTC