Jev-powered Judgment layer for Claude Code. Stops paying reasoning prices for if-statements: a PreToolUse hook scores every tool call against a YAML policy you own — allow / deny in ~100 ms, no LLM in the loop. TypeSafe Jev now, local models next. Dry-run by default, calibration table published.
Stars measure the whole repository, including work unrelated to Jev.
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
Live run against `jev-1.13.0` on 2026-09-19, on the policy in this repository. Confidence
Evidence commit: 1145df8ed9b3c5493263d596494c3864ad018be5
Discovered through: github-search.
How we review →