Find the LLM calls you should move to JEV — scan logs & code for decision-shaped calls, price the migration, calibrate decision models, generate the migration PR. Zero deps, fully local.
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.
Are stated probabilities trustworthy? Point it at decision records — `{"p": 0.82, "correct": true, "model": "jev-latest", "question": "ticket-router"}` (Jev returns `p` natively; for LLMs use the top-choice probability) — and get:
Evidence commit: 21157949afb1517dc6f9100a6f05bb016822b6b3
Discovered through: github-search.
How we review →