index / lgy1027/jevshield
jevshield
Sub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev (System-1) decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready.
Agent and Dev ToolingVerificationListedPython
Repository
Stars2
LanguagePython
LicenseApache-2.0
Created2026-09-20
Last pushed2026-09-20
Officialno
Judgment
Genuine Jev project0.84
gate 0.5
Uses Jev at runtime0.76
Is a meta list0.03
Is a reimplementation0.12
Quality scales
Substance2.56 / 3
gate 0.5
Docs2.74 / 3
Novelty1.97 / 3
Composite score0.82
Category distribution
Agent and Dev Tooling0.99
Integrations0.01
Learning0.00
Games and Simulation0.00
Applications0.00
SDKs and Clients0.00
Research and Evals0.00
Other0.00
Assigned categoryAgent and Dev Tooling
Category probability0.99
Category confidence0.98
PatternVerification
Pattern confidence1.00
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:jev typesafe
- search:topic:jev
- search:topic:system-one
- search:jev in:name,description,readme created:2026-09-20
- list:hellogumbo/awesome-jev
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-09-21 12:34 UTC