jev-gates

Six hook gates for Claude Code that catch broken rules, out-of-scope edits, unfinished asks, and false claims, each judged by Jev against a fixed checklist and one piece of evidence.

Six calibrated gates for Claude Code, judged by TypeSafe Jev: rules, scope, intent, done, claims, and commit honesty. Each one escalates, none ever approves.

How it uses Jev

Nine calibrated gates for Claude Code, judged by TypeSafe Jev. Each one escalates. None of them ever approves.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to jev-gates

Browse all
jev-belay project preview
Agent tooling
Claude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything else
jev-guard (muratcakmak) project preview
Probability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your docs into each prompt, and check the final answer against the turn's own evidence.
clear-head project preview
Agent tooling
Claude Code Stop hook that checks an AI assistant's claims against what it actually read this session, using TypeSafe's Jev as the judge
typesafe-adblock project preview
Browser & computer use
🧹 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker.
ask-jev-ai project preview
Demos & playgrounds
A public wall where anyone asks a question in three to fifteen words and Jev, TypeSafe's judgment model, answers yes, no, or it depends in about 100 milliseconds. Every judged ask lands on the wall in realtime, with a running count toward one million, showing cost.
jev-chat-jarvis project preview
Browser & computer use
装在手机上的对话副驾:在微信 / QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框,发不发由你。非侵入,只读屏幕,不 hook 不改包。
jev-pr-labeler project preview
Applications
Semantic GitHub PR labels using Jev's typed decisions, with conceptual scope instead of line counts
jev-browser-control project preview
Browser & computer use
Let Claude code, chatgpt codex or control your own Chrome. Chrome extension + MCP server: Jev, TypeSafe's decision model, picks each click in ~0.5 s for a fraction of a cent. MIT, bring your own OpenRouter key.
jev-semgrep project preview
Applications
grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できる