Jev learns your repo's decision norms, then adversarially judges past decisions against them. Unix-style primitives (seed, expand, judge, verify, report, norms) with per-node typed judgments from typesafe-ai/jev.
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.
The trick is cheap judgment. [Jev] (typesafe-ai/jev, via the Vercel AI Gateway) returns typed verdicts, choice, boolean, and score, for about $0.00006 per normal node in our calibration runs. When each judgment costs a fraction of a cent, you can judge every node instead of every scan.
Evidence commit: 3a8a4ab735ab2709afa72f6c43ff992c67e41aa8
Discovered through: github-search.
How we review →