English-Rules Semantic Linter

Jev powers a linter whose rules are plain-English sentences. It scores every function against all 14 rules in parallel.

View on X costa fifth of a centtime2.6 seconds

Ahmed Gagan@ahmedgagan11𝕏

ANOTHER JEV USECASE: a linter where the rules are plain english sentences. "swallows errors." "hidden side effect." "does too many jobs.", etc jev scores every function against all 14 in parallel. zustand: 29 functions, 464 judgments, 2.6 seconds, a fifth of a cent. syntax linters can't check meaning. this one does.

Sep 18, 2026X postsView on X

On zustand, it evaluated 29 functions and produced 464 judgments. The author reports a runtime of 2.6 seconds and a cost of a fifth of a cent.

Also filed under Tools & apps

TypeSafe Jev Decision-Model Client
It provides a shared TypeSafe Jev decision-model client for the dsh ecosystem, with strict response validation, keychain-first key resolution, and typed fail-open errors. It is Jev-optional by design.
Jev Reviews Changed Code
The Claude Code plugin uses Jev (TypeSafe AI) to assess changed code at the end of a turn and, when needed, propose a code review using Open Code Review rules.
Alerts on Company Data-Use Changes
TOS Watch sends an email when a company changes what it does with your data. It combines Open Terms Archive history, a Jev classifier, a static site, and a Cloudflare Worker.
OpenAI API-to-Jev Gateway
jev-gateway turns any OpenAI API backend into a gateway compatible with Jev.