判断ツール

42 · 各項目の確認根拠をご覧ください。掲載は独立した実行検証を意味しません。

• jev-playground

  Little-Planet-Labs · 判断ツール

  状態や選択・採点の質問を入力し、Jev の回答と確率分布を見る Web 実験画面。

• jev-predict-skill

  DanielKillenberger · 判断ツール

  規則と証拠から別の skill の閉じた選択肢での結論を予測する Agent 用レシピ。

• jevify

  altryne · 判断ツール

  Jev に適した判断箇所を探し、質問と比較実験を設計する Agent Skill。

• jevchat

  kt3k · 判断ツール

  定義済みまたは独自の選択肢から回答する、チャット形式の Jev デモ。

• hermes-jev

  keeltrace · 判断ツール

  関連性・完了・復旧・任意の許可判断を補助する、Hermes Agent 用の非同期 Jev 連携。

• killmyidea

  monteduro · 判断ツール

  Jev の複数スコアから KILL・FIX・SHIP を付ける起業アイデア評価デモ。

• jev-commit

  valentynkit · 判断ツール

  commit-msg フック。1 回の Jev リクエストで staged diff と照合し 5 つの Noul を付け、既定では警告のみ。既定の停止は追加行に対するローカル正規表現ベルトの高信頼ヒット。secret_shaped Noul は --strict のときだけ止める。

• jev-belay

  valentynkit · 判断ツール

  Claude Code の Stop フック。まずローカルで今ターンにファイル変更があったか、通過した検査があるかを見、そのときだけ Jev に終了文が未確認の完了宣言かを問う。

• jev.nvim

  valentynkit · 判断ツール

  Neovim プラグイン。自然言語で今の buffer に問い、Treesitter が関数単位に切り、Jev が各関数に確率を付ける。命中はすべて確率順で quickfix に入る。

• jev-skip

  valentynkit · 判断ツール

  Chrome 拡張。字幕だけを読み、区間を Jev に分類させる（区間数や Token 予算を超えたらリクエストを分割）。シークバーに五類を描き、しきい値以上の sponsor、self_promo、intro、outro、recap を自動で飛ばす。

• jev-plays-pokemon-red

  valentynkit · 判断ツール

  PyBoy 上の Pokemon Red。経路と算術はコードが持ち、ゲームが本当に分岐するときだけ Jev が既に合法な動作から 1 つ選ぶ。

• turing-jail

  bugkiwi · 判断ツール

  Interactive three-level AI interrogation game powered by TypeSafe Jev; write responses and pass plea, logic, and paradox verdicts to earn release.

• wechat-jev-assistant

  yushen100 · 判断ツール

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• claude-jev

  0x7067 · 判断ツール

  Claude Code plugin: Jev for rule checks, verbatim compaction, and prompt routing

• Jev-in-the-Loop

  Tongyun1 · 判断ツール

  Researching how Jev can accelerate tasks that rely on LLM decision-making.

• jev-chat-windows-deepseek-jev

  Aimark-dai · 判断ツール

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-slop-guard

  davertor · 判断ツール

  Jev Slop Guard — a Chrome extension that scores and stamps AI slop on your X and LinkedIn feeds as you scroll

• jev-codex-router-skill

  455-dIAO · 判断ツール

  Portable Codex Skill for Jev model and reasoning-effort routing, with safe installation and Chinese usage guides

• jev-bot

  nssmd · 判断ツール

  Self-hosted Jev decision workbench and Feishu bot: automatic choices, probabilities, and experimental word/character writing.

• jev-chat-windows-laya

  ZJemYoung · 判断ツール

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• Jevatar

  AppChainAI · 判断ツール

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-laya-benchmark

  harrymunro · 判断ツール

  Speed and accuracy benchmark: TypeSafe's Jev API vs the local Laya MLX typed-decision model on synthetic tasks

• typesafe-jev-ruby

  dtheofr · 判断ツール

  Ruby client for Jev, TypeSafe's System One model: typed questions, probabilistic answers. Zero runtime dependencies.

• jev-triage

  ccai40359-wq · 判断ツール

  Millisecond-class test-failure triage for coding agents: RETRY / FIX_CODE / FIX_ENV, powered by TypeSafe Jev.

• jev-skill-router

  shimo4228 · 判断ツール

  Claude Code plugin: asks TypeSafe Jev which installed skill fits each prompt and logs the answer (shadow-first). A working reference for the skill-suggestion cookbook on Claude Code — the README records why it is unlikely to help a strong model as a router.

• jev-apply

  TheAdaply · 判断ツール

  In Codex, Claude Code, or another CLI agent:

• astra-jev-harness

  Oranquelui · 判断ツール

  The default `batch` policy retains an entire batch when any judgment is uncertain. The experimental `select --policy per-file` retains uncertain/unjudged files while omitting confidently irrelevant siblings. Dependencies and the global no-match fallback still apply. Compare before changing policy; fewer bytes alone do not establish correctness.

• fake-real-jev

  DansiDanutz · 判断ツール

  See link entry, the live scan timer, JEV's evidence-checking role, a saved REAL example, a saved FAKE example, and the linked sources. The live documentation scan shown ended without a verdict; its credit was returned. The coffee reports are clearly labeled saved examples, with their original analysis times.

• jev-crawlers

  russfranky · 判断ツール

  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.

• JevCode

  coasty-ai · 判断ツール

  JevCode - Jev can code. We want to dogfood JevCode

• jev_projects

  X0EF · 判断ツール

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-linter-action

  sable-inc · 判断ツール

  `glob` accepts one pattern or a newline-separated list. All matched files are reviewed together by default; `per-file: true` reviews each file independently. Missing inputs, malformed questions and ambiguous combinations fail before calls.

• jev-no-enem

  patryckalves · 判断ツール

  Reproducible benchmark evaluating TypeSafe AI's Jev (System One paradigm) on Brazil's ENEM 2025 standardized exam. Evaluates typed decision-making, domain-specific accuracy, and RLCD uncertainty calibration against open LLM baselines with an interactive GitHub Pages dashboard.

• Jev-chat-assistant

  QCJLchina · 判断ツール

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• dsh-jev

  noetion · 判断ツール

  DSH bundle that registers jev_ask for TypeSafe Jev noul, choice, and score answers.

• jev-demos

  DataGobes · 判断ツール

  Every demo lives in its own folder with its own README, dependencies and instructions. Most run without an API key in a clearly labelled `SIMULATED` mode; put `TYPESAFE_API_KEY=...` in the demo folder's `.env` for live results.

• xjevboost

  sedthh · 判断ツール

  Add as much tabular data as you want to Jev models using adaptive ensembles that learn to query only the rows and columns needed.

• jev-book-tags

  iamjonatha · 判断ツール

  A free calibre plugin that suggests genre and subject tags for individual books, selected books or an entire library, with configurable thresholds and review controls.

• spending-effort-with-jev

  Yaxin9Luo · 判断ツール

  Jev-powered /effort advisor for Claude Code: tells you when to switch effort, per prompt

• jev-chat-gate

  pandore · 判断ツール

  A framework-independent participation gate for AI agents in group chats, powered by typed Jev decisions.

• jev-nethack

  statico · 判断ツール

  TypeSafe's Jev model plays NetHack 5.0: code lists the legal moves, Jev picks one, no LLM in the loop

• jev-demo

  harsha89 · 判断ツール

  Showcase of TypeSafe JEV classifying emails: spam (noul), category (choice) and urgency (score) - Next.js + MUI app and Python script