모델 라우팅

70 · 각 항목의 검토 근거를 확인하세요. 수록은 독립적인 실행 검증을 뜻하지 않습니다.

• jev-codex-router

  0xNatoshi · 모델 라우팅

  Codex의 각 턴을 Jev가 분류하고 로컬 규칙으로 모델, 추론 깊이, 속도를 선택한다.

• jev-research

  sherajdev · 모델 라우팅

  Jev와 Herdr 연동 가이드와 작업을 여러 Agent에 배분하는 라우터 프로토타입.

• jev-demo

  minghanminghan · 모델 라우팅

  Jev에 경로 질문을 묶어 보내고 분류 결과에 따라 처리하는 고객 지원 데모.

• jev-router-playground

  hugo-alves · 모델 라우팅

  Jev가 후보 모델을 고르고 사용자가 실제 답변을 비교하는 라우팅 실험 화면이다.

• oh-my-pi

  can1357 · 모델 라우팅

  Oh My Pi에는 코딩 Agent의 한정된 판단에 쓰는 선택형 TypeSafe 제공자가 포함된다.

• litellm

  BerriAI · 모델 라우팅

  LiteLLM의 복잡도 라우터에서 Jev로 요청을 분류할 수 있다.

• firstmate

  kunchenguid · 모델 라우팅

  Firstmate는 선택적으로 Jev로 작업 개요와 배분 규칙을 비교한 뒤 Agent 설정을 고른다.

• openchamber

  openchamber · 모델 라우팅

  Jev로 메시지를 분류해 설정된 모델과 추론 수준을 고르는 OpenChamber의 선택형 라우터.

• atomic

  bastani-inc · 모델 라우팅

  Atomic 코딩 Agent의 선택적 Jev 백엔드로 라우팅 등 제한된 구조화 선택을 수행한다.

• WrongStack

  WrongStack · 모델 라우팅

  WrongStack의 전문 Agent를 선택하는 선택형 Jev 분류기.

• vexjoy-agent

  notque · 모델 라우팅

  VexJoy 요청을 전문 Agent·skill·workflow에 연결하는 선택형 Jev 경로.

• skillbox

  kitze · 모델 라우팅

  선택형 Jev 추천을 제공하는 자체 호스팅·버전 관리 Agent skill 라이브러리.

• hono-jev-router

  yusukebe · 모델 라우팅

  자연어 경로 설명을 사용하는 Hono의 실험적 HTTP 의미 기반 라우터.

• JevRouter

  BillionsBobby · 모델 라우팅

  모델, Subagent, Skill, MCP와 CLI를 공통 후보로 두고 라우팅한다.

• todo-jev

  maker-KK · 모델 라우팅

  skill 조건과 환경 점검으로 규칙·skill·대형 모델 경로를 추천하는 작업 라우팅 실험.

• jev-model-router

  davila7 · 모델 라우팅

  Jev로 Claude Code 하위 Agent의 모델·추론 수준을 제안하는 커뮤니티 mod.

• loki

  wundercorp · 모델 라우팅

  Loki의 선택 기능으로 Jev 판단 도구와 같은 gateway 안의 세션 모델 선택을 추가한다.

• typesafe-skill-router

  DECRUX9812 · 모델 라우팅

  모델 호출 전에 관련 skill 하나를 제안하는 선택형 Hermes Agent 플러그인.

• jev-router

  gargpratyush · 모델 라우팅

  Claude Code / CLI 프록시. Jev가 작업 복잡도를 매기고 계정에서 쓸 수 있는 모델 중 하나를 고른 뒤, 로컬 정책이 교체 여부를 정한다.

• opencode-jev-orchestrator

  aaronshaf · 모델 라우팅

  OpenCode 오케스트레이터. 세션은 저비용 부모 모델에 두고, Jev가 이번 턴을 어렵다고 볼 때만 도구로 더 강한 자식 Agent를 띄운다.

• tiershift

  iamvatsalpatel · 모델 라우팅

  YAML 정책을 바탕으로 Jev가 약 180ms 내에 요청을 판별하여 가장 저렴한 적합 모델 계층으로 전달하는 라우팅 프레임워크입니다.

• Janus

  FirasSX914 · 모델 라우팅

  자체 데이터셋에서 Jev와 일반 생성형 모델의 효율을 측정하고 실측치에 기반하여 최적 경로로 분기하는 라우팅 프레임워크입니다.

• jev-decision-gateway

  kuldeepsinh19 · 모델 라우팅

  계속할지, 어떤 도구인지, 검증할지를 Jev에 묻고 정책이 허용할 때만 생성 LLM을 부른다.

• jev-router

  prismhq · 모델 라우팅

  An open-source LLM router built on LiteLLM and Jev: dynamically routes requests based on task complexity and context.

• pi-jev-router

  mejiasd3v · 모델 라우팅

  Automatic model router for Pi coding assistant: integrates Jev via Vercel AI Gateway to dispatch tasks efficiently.

• jev-router

  rajdhakad9826 · 모델 라우팅

  Cost-aware LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.

• grok-bot-jev

  Bodila51 · 모델 라우팅

  Connect TypeSafe Jev to Grok Bot as a cheap decision layer - usage gates, skill template, examples

• hermes-jev-skills

  kerpopule · 모델 라우팅

  Hermes, Claude Code, Codex를 위한 Jev 결정 툴킷으로 모델 라우팅, 메모리 압축, 동적 Skill 선택을 경량 판정으로 구현합니다.

• Jev-Auto-Router

  miniLV · 모델 라우팅

  Jev Auto Router (Jev Router): experimental per-call GPT model routing for Codex via TypeSafe Jev and a local Responses proxy, with independent task verification.

• jev-model-router

  lucianfialho · 모델 라우팅

  Cost-optimized OpenRouter model router using TypeSafe's Jev, with a live full-catalog scorer instead of a hardcoded model list

• tool-prune

  hemanth · 모델 라우팅

  Calibrated tool selection and schema pruning for AI agents. Dual-engine: zero-dependency offline TurboQuant or TypeSafe System One (Jev). Prunes candidate MCP tools and schemas down to the relevant set before calling LLMs to eliminate hallucinations and save tokens.

• JevLoop

  zjunlp · 모델 라우팅

  The agent loop where decisions don't cost a large language model call. Zero deps, runs offline, no API key needed.

• jev-codex-pilot

  Charlyhno-eng · 모델 라우팅

  A Codex overlay incorporating JEV to make the best decisions regarding model selection and depth of reasoning. All while automating the process via an automated Kanban system.

• jev-codex-model-and-effort-router

  gholtzap · 모델 라우팅

  Copy and paste this into your coding agent:

• laya-jev-lab

  yibie · 모델 라우팅

  Independent measurements of typed-decision models: Jev (TypeSafe API) vs Laya (open weights), and a local-first cascade that matches Jev's accuracy at 1.8x the speed

• switchboard

  ruban-24 · 모델 라우팅

  Switchboard is a local Claude Code and Codex router. It assesses a new conversation's task with Jev, applies deterministic confidence rules to select the model and reasoning effort, and pins that route through follow-ups, tool calls, and resume to avoid unnecessary prompt-cache disruption.

• jevbus

  zkjoie · 모델 라우팅

  A streaming event bus whose routing, subscription and consumption are decided by a probabilistic judge. The reference judge is TypeSafe AI's Jev (System One) model: send it a payload and a set of typed questions, get back calibrated probabilities instead of prose.

• jev-routing-experiment

  TokenTrim · 모델 라우팅

  Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena

• stuntdouble

  ReallyArtificial · 모델 라우팅

  Drop-in /v1/systemone proxy that shadows Jev with local decision models (Kev, Laya) and reports whether you can swap

• dejevu

  idovmamane · 모델 라우팅

  Jev? Déjà vu. Browser agents that run on instinct, no Jev needed. One look at the page, one call to any open model, one action. Faster than the Jev demo on Google Flights.

• jev-lab

  Pasblinn · 모델 라우팅

  Open lab: Jev (TypeSafe System One) routing in front of Claude Code - measured bugs, patch, and a hard fallback with alerts

• jev-agent-hooks

  onlyjq04 · 모델 라우팅

  TypeSafe Jev hooks for Claude Code, Codex and pi: per-turn skill suggestion and subagent model routing

• sabi

  vizuh · 모델 라우팅

  Adaptive inference scheduling for AI agents — per-round model, effort and provider routing for coding harnesses: a Command Code mod or a local OpenAI-compatible proxy.

• muse-jev-playbook

  Bodila51 · 모델 라우팅

  Jev decision layer for Muse: a fast, cheap TypeSafe AI gate before expensive agent work — confidence policy, recipes, reference router, honest measurement.

• jev-model-router

  satviksinha · 모델 라우팅

  Model router for Claude Code using Jev

• jev-smart-router

  rmosleydb · 모델 라우팅

  JEV Smart Router — a Databricks App that uses TypeSafe JEV to pick which model answers each message, then runs inference on the chosen Databricks Foundation Model API endpoint.

• openclaw-jev-plugin

  herval · 모델 라우팅

  A silenced message never reaches the language model, so it costs one Jev call and no model tokens. Direct messages always get an answer unless you choose to gate them too.

• jev-gateway

  TexasOct · 모델 라우팅

  Session-aware OpenAI-compatible model-routing gateway powered by JEV

• chat2jev

  Chandler-Sun · 모델 라우팅

  Convert OpenAI-compatible Chat Completions requests into TypeSafe System One (Jev) **State / Questions**, compare generated text with structured judgments, and publish reusable question sets as proxy routes.

• stuntd

  bladedevoff · 모델 라우팅

  Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

• jev-route

  mcftira · 모델 라우팅

  **Run it. Log it. Distill it. Own it.**

• jev-for-all

  emirbartu · 모델 라우팅

  Jev for every agentic development workflow — the System One decision model wired into whatever harness an agent codes in: OpenCode today, Claude Code and Hermes adapters next.

• jev-claw

  trietphan · 모델 라우팅

  Typed model routing for OpenClaw agents, powered by TypeSafe Jev

• jev-pilot

  Akramovic1 · 모델 라우팅

  Let Jev steer Claude Code: the right reasoning effort, subagent model and skill for every prompt. A Claude Code plugin powered by TypeSafe's Jev (OpenRouter / TypeSafe).

• codex-jev-router

  suenot · 모델 라우팅

  Portable JevRouter setup for cost-aware Codex subagent model selection, with English and Russian instructions

• jev-claude-router

  Flam1ngFir3ball · 모델 라우팅

  Model router for Claude Code using Jev

• jev-opus

  WXK-AI · 모델 라우팅

  Claude Opus 5.5 with the effort level re-decided every step by the TypeSafe Jev reflex — without breaking the prompt cache. CLI + Claude Code plugin.

• jev-router

  dirien · 모델 라우팅

  Pass-through model router for Claude Code and Codex CLI that picks a model tier per human turn with Jev, TypeSafe AI's decision model

• hermes-jev

  ourines · 모델 라우팅

  Jev decision sidekick for Hermes Agent — TypeSafe and Cloudflare, explicit tools and official skill

• JudgeJev

  shyamsridhar123 · 모델 라우팅

  The public site replays **17 real, recorded Jev evaluations** of fictional support cases. It starts with a false shipping guarantee that scored **15.1%**, alongside a correct control that scored **95.5%**. You can inspect raw requests and responses, adjust decision rules, and see why a five-pair candidate fails a release gate.

• hermes-jev-router

  punkcanyang · 모델 라우팅

  Hermes Agent plugin: TypeSafe Jev model routing + trim-then-compress

• omp-plugin-jev-router

  atulify · 모델 라우팅

  Route Oh My Pi prompts between simple and advanced models with TypeSafe AI's Jev classifier.

• Jev-Model-Router-Claude-Code

  AlexPEClub · 모델 라우팅

  Begleitmaterial zum Video „Jev + Claude Code: 3 Use Cases".

• codex-jev-native-router

  itscloud0 · 모델 라우팅

  Experimental native Codex Desktop and CLI model routing with Jev and a configurable allowlist

• jev-cc-codex-router

  peterwanghot · 모델 라우팅

  Per-turn model routing proxy for Codex: asks Jev which tier each task needs, rewrites the model, retries flaky upstream errors.

• cribrix

  david96182 · 모델 라우팅

  Self-hosted RAG service that uses Jev to decide which retrieved context reaches the generator and whether the generated answer is released.

• jevia

  assistant-ui · 모델 라우팅

  outcome-aware & adaptive model routing for coding agents with deterministic cache powered by Jev

• opencode-jev-router

  robertn702 · 모델 라우팅

  Adaptive reasoning effort for OpenCode via Jev, with an in-process plugin and Responses API proxy

• jev-codex-factory

  VyetGokyra · 모델 라우팅

  Route smarter. Code in parallel. Resume what breaks. A Jev-powered multi-agent factory for Codex.

• mu

  qybaihe · 모델 라우팅

  A coding agent built on pi and AionUi whose routine calls at 38 decision points are made by Jev.