Jev application
Build and run agents you can see, understand and trust.
Details →★ 32,297
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。
Project facts
- Relationship to Jev
- Jev application
- Evidence
- Documented
- Language
- TypeScript
- License
- Not reported; check the repository
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-21
- GitHub stars
- 1
- Evidence checked
- 2026-09-24T08:40:10.508Z
- Metadata checked
- 2026-09-24T08:40:10.508Z
- Check status
- current
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
`jev-metrics` complements [`jev-review`]: while `jev-review` turns each Jev call into a one-shot structured evaluation, **`jev-metrics` persists those evaluations over time and, crucially, audits whether Jev's confidence is actually trustworthy.**
Evidence commit: e37580f151b6cc89ebb49f047e2aef9d0e98bc98
Discovered through: github-search.
How we review →