index / dfranco-projects/jev-guardbench
jev-guardbench
Can a System One model (TypeSafe Jev, open-source Kev) replace an LLM-as-judge in agent guardrail callbacks?
Research and EvalsVerificationListedPython
Repository
Stars2
LanguagePython
License—
Created2026-09-22
Last pushed2026-10-04
Officialno
Judgment
Genuine Jev project0.95
gate 0.5
Uses Jev at runtime0.89
Is a meta list0.03
Is a reimplementation0.09
Quality scales
Substance2.01 / 3
gate 0.5
Docs2.72 / 3
Novelty2.78 / 3
Composite score0.82
Category distribution
Research and Evals1.00
Games and Simulation0.00
Agent and Dev Tooling0.00
Applications0.00
Learning0.00
SDKs and Clients0.00
Other0.00
Integrations0.00
Assigned categoryResearch and Evals
Category probability1.00
Category confidence1.00
PatternVerification
Pattern confidence1.00
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:"system one" jev
- search:jev in:name,description,readme created:2026-09-22
- search:jev typesafe
- list:hellogumbo/awesome-jev
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-10-05 13:16 UTC