- A small multi-agent harness built around the pattern from LangChain's post: use a fast, non-generative "System One" classifier (TypeSafe AI's Jev) for structured in-loop decisions -- routing and risky-tool-call gating -- and reserve a real chat LLM for the genuinely open-ended reasoning.
dhirajpatra/agent-harness-with-jev-llm · Python
10python - 1102agent-kitAgent make dozens of silent judgments a turn: is this done, is this correct, do I have enough to decide, which way now. Made inside your own text stream, those judgments are uncalibrated and biased toward finishing, you tend to certify your own work. judge hands one such judgment to Jev.
minhquan23102000/agent-kit · Python
10harnessharness-engineeringoh-my-pipython - agent-tool-router: TypeSafe Jev ecosystem repository.
van-vanich/agent-tool-router · TypeScript
10typescript - Standalone TypeSafe AI/Jev semantic-evidence adapter for bounded Agent-Workflow decisions, explicit uncertainty, compatibility evaluation, and host-owned policy.
ngallodev-software/agent-workflow-typesafe-ai · Python
10agentic-aiai-agentsdecision-supportdeveloper-toolsevaluationpythonsemantic-reasoning - A conservative Jev-backed auto-mode safety gate for Antigravity CLI tool calls
thomas-chong/agy-cli-jev-auto-mode · JavaScript
10agyai-safetyantigravitycoding-agentsnodejspretoolusetool-permissions - 1106ai-column-jevai-column-jev: TypeSafe Jev ecosystem repository.
milanterhes/ai-column-jev · TypeScript
10typescript - Fast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One.
greenyamao/Antigravity-mcp-semantic-search-with-TypeSafeAi · Python
10python - 1108ask-jevUtilizing Jev, the RLCD-type model provided by TypeSafe AI, to independently and cheaply judge agentic coding sessions.
omni-/ask-jev · PowerShell
10powershell - 1109askjevA tree housing every closed question humans or machines ask, answered by Jev (TypeSafe System One): capabilities, defaults, and jaggedness. Not a benchmark.
brian-w-zhang/askjev · Python
10python - 1110auto-effortClaude Code mod: picks /effort per prompt with Jev
peterlimg/auto-effort · TypeScript
11typescript - 1111awesome-jevProjects built on Jev (TypeSafe AI's System One model), curated by Jev itself.
rhc98/awesome-jev · TypeScript
10awesomeawesome-listtypescript - 1112awesome-jevOpen models, libraries, tools, and applications for Jev and System One decisions.
KuzanJ/awesome-jev · Python
10awesome-listdecision-modelmachine-learningpython - 1113awesome-jevA curated guide to Jev, TypeSafe AI's System One decision model — selection advice, API-verified cookbooks, independent evaluations, and 100+ community. 中英双语
dog-last/awesome-jev · Python
12awesomeawesome-listchinesellmpython - 1114awesome-jev-appsJev 优质应用与生态精选|System One 决策模型:开源应用·SDK·平台集成·开源复刻·教程 | curated apps & SDKs for TypeSafe AI's Jev model
JingHao-Leon/awesome-jev-apps · Python
11ai-agentsai-routingawesome-listchineseclassificationllmstructured-output - The Jev projects actually worth your time — picked, compared, kept current.
charetterat/awesome-jev-essentials · Python
10ai-agentsawesomeawesome-jevawesome-listdecision-modelllm - Website for reacher-z/Awesome-Jev: bilingual Jev research papers, typed decision models, benchmarks and source-backed guides.
AwesomeJev/AwesomeJev.github.io · HTML
10ai-agentsawesomeawesome-listbenchmarkcalibrationcurated-listdecision-model - 1117beat-jevA penalty shootout powered by Render Workflows, TypeSafe Jev, and Render Postgres. Python and TypeScript examples.
ojusave/beat-jev · TypeScript
11 - 仅供娱乐的 Jev 双人聊天关系观察应用:逐条读取文字消息,展示爱与不爱迹象百分比。
zhizunbao-studio/between-chat-insight · TypeScript
10chat-analysisprivacyreacttypescript - Agent Skill + estudo verbatim sobre a Jev (TypeSafe AI System One Model): choice/score/noul, RLCD, patterns, SDKs.
BFLabsAI/bf-jev-deep-research · PowerShell
10agent-skillsai-agentsclassifierclaude-codecodexcursordecision-model - 1120BizzJevExperiments with TypeSafe/Jev semantic gates and a Semantic Operations Lab demo.
havietkok-sys/BizzJev · C#
10c# - 1121bluff-royalebluff-royale: TypeSafe Jev ecosystem repository.
lvzhaobo/bluff-royale · JavaScript
10javascript - 1122bobcatBobcat: a typed-decision model. State in, Choice / Noul / Score out, with a probability for every answer you name; no generated text. Compiler, server, training and evaluation code for Bobcat 1.1 and Bobcat Flash 1.1.
foxl-ai/bobcat · Python
10calibrationclassificationhuggingfacellmtyped-decisionsvllmpython - 1123bouncerJev-powered Judgment layer for Claude Code. Stops paying reasoning prices for if-statements: a PreToolUse hook scores every tool call against a YAML policy you own — allow / deny in ~100 ms, no LLM in the loop. TypeSafe Jev now, local models next. Dry-run by default, calibration table published.
clownware/bouncer · TypeScript
12claude-code-plugintypescript - 1124browser-jevRun Jev-like decisions in your browser with the Prompt API.
daidr/browser-jev · TypeScript
10chromeprompt-apitypescript - 1125browserjevLow-memory autonomous web classification with HTTPX, Lightpanda and Jev
hermespromox/browserjev · Python
10ai-agentslightpandapythonweb-agentweb-crawler - Claude Code plugin and Python CLI: hand a judgment repeated over many items to TypeSafe's Jev, with redaction, rate limiting, a pilot and a flat-question check.
bitranox/btx-skill-jev-judge · Python
10agent-skillsai-agentsanthropicbatch-processingclassificationclaudeclaude-code - 1127callpointAn inspectable incident decision-support demo. The model judges, the code decides.
rcmeadow/callpoint · TypeScript
10cloudflare-clefdecision-supportincident-responseollamatypescript - 1128chess-with-jevChess with Jev: every legal move's facts worked out in code, Jev's move as one typed Choice. The Jev client (MIT) and chess engine (GPL-3.0) behind chriswijnia.com/lab/chess.
cwdx/chess-with-jev · TypeScript
11chesschess960nuxttypescript - 1129claude-jevJev (TypeSafe System One) as a Claude Code plugin: typed decisions for sorting, routing, triage and calibration
zachshallbetter/claude-jev · Python
10python - 1130clojevUnofficial portable Clojure SDK for TypeSafe System One
antlobach/clojev · Clojure
10clojure - 1131clueSemantic ranking for CLI output, local search, and bounded agent context. Works with gh, bd, Cider, SQLite, and JSON/JSONL.
thrashr888/clue · Rust
10rust - 1132codex-jevJev-powered selective context handoffs for Codex, with a GitHub Copilot portability plan.
nomper/codex-jev · JavaScript
10codexcontext-managementmcpjavascript - 1133compact-jev/compact-jev: Jev-guided verbatim compaction for Claude Code through Vercel AI Gateway, separate from /compact.
edoproch/compact-jev · TypeScript
11claudeclaude-codeclaude-code-plugincontextcontext-compactioncontext-engineeringcontext-window - 1134conductorRun your Mac by voice: hold Fn, say a task, and Claude Code or Codex carries it out. Built on Jev Voice by TypeSafe.
Seryozh/conductor · Swift
10ai-agentsclaude-codecodexcomputer-usemacosswiftswiftui - 1135cribrixA precision-first RAG orchestrator: filters before it generates, verifies before it answers.
david96182/cribrix · Python
11agentic-ragdockerfact-checkingfastapihallucination-preventionlarge-language-modelsllm - 1136decideOne client for every decision model: Choice, Score and Noul over Jev, OpenRouter, laya, MLX, CrossEncoders and LLM fallback
gopaljigaur/decide · Python
10classificationdecision-modellayallmmlxpythonrouting - 1137decideBulk decisions for AI agents. Jev classifies files and logs; your agent reviews exceptions. Reproducible cost and quality benchmarks.
alsoleg89/decide · Python
10ai-agentsclassificationclaude-codecodexcontext-engineeringllm-evaluationmcp - 1138decidoProbabilistic decisions for Python. Use Jev or bring your own provider; crawl with Playwright.
yairshy/decido · Python
10python - 1139decision-kitAgentic UI demonstrations for rapid, context-aware decisions with TypeSafe AI Jev, LLMs, and the GitHub Copilot SDK
BrettReifs/decision-kit · JavaScript
10javascript
1101–1150 of 3054