jevshield
lgy1027/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.
- Stars
- 5
- Forks
- 0
Why it is listed
A framework-neutral control layer using Jev/System One for intent routing and tool-call decisions while the application retains orchestration, retries and final responses.