jevshield
lgy1027
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.
- License
- Apache-2.0
- GitHub Stars
- 3
- Source reviewed
- —
Where Jev makes a decision
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
What this project offers
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Review scope
Based on repository metadata and README with rule-based classification; pending human review, with no independent runtime or performance verification.
Sources and implementation
Related projects
safer-with-jev
andrelandgraf · Security & Guardrails
An HTTP inspection gateway that checks request content with Jev before optionally forwarding it to an HTTPS destination.
pi-jev
y0usaf · Security & Guardrails
A Pi extension that flags tool risks before execution and checks output for secrets and failure types.
pi-jev-auto-mode
jomatsu · Security & Guardrails
Adds rule checks to Pi commands and file operations, then uses Jev to assess cases that need further judgment.
jev-judgment
HyunjunJeon · Security & Guardrails
Adds judgment checks for authorization, operation risk, and failure causes to coding Agents.