index / openlayer-ai/jevals
jevals
Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.
Agent and Dev Tooling?Feature ScoringListedPython
Repository
Stars111
LanguagePython
LicenseMIT
Created2026-09-20
Last pushed2026-11-02
Officialno
Judgment
Genuine Jev project0.91
gate 0.5
Uses Jev at runtime0.81
Is a meta list0.03
Is a reimplementation0.23
Quality scales
Substance2.59 / 3
gate 0.5
Docs2.91 / 3
Novelty1.92 / 3
Composite score0.89
Category distribution
Jev's confidence in this category is below 0.5, so the category is shown with a question mark. It is not a listing condition: this entry's status was decided by genuine and substance alone.
Agent and Dev Tooling0.39
Research and Evals0.29
SDKs and Clients0.26
Integrations0.05
Applications0.01
Games and Simulation0.00
Learning0.00
Other0.00
Assigned categoryAgent and Dev Tooling (uncertain)
Category probability0.39
Category confidence0.30
PatternFeature Scoring
Pattern confidence0.39
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:jev typesafe
- search:topic:jev
- search:jev in:name,description,readme created:2026-09-20
- list:hellogumbo/awesome-jev
- list:AnotiaWang/awesome-jev
Provenance
Modeljev-1.14.0
Question setv2
Judged at2026-11-04 13:52 UTC