jev-mode
I kept watching coding agents burn context on decisions that aren't hard - triage 400 tickets, tag 600 files, route to one of six teams. jev-mode moves those verdicts to a typed-judgment model. I A/B'd it: 78% fewer tokens, 16x less work-attributable input, accuracy 96.1% vs 93.7%. Python, no deps, MIT.
How it uses Jev
Your agent burns tokens deciding the same kind of small question over and over: which team owns this ticket, is this file stale, does this message report a bug, which category is this row. jev-mode moves those judgments out of the model context and into TypeSafe Jev, a typed-judgment model: you send one item and a map of typed questions, and you get answers constrained to the options you supplied, each with a calibr…
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.