TypeSafe Jev / System One 模型的免费 GitHub 项目目录按用途查找官方 SDK、智能体工具、开源替代实现与 Jev 最新资讯

数据更新

  • 1301jev-mcp
    MCP server exposing TypeSafe's Jev typed-decision model over the TypeSafe API or OpenRouter

    tphakala/jev-mcp · Go

    10
    go
  • 1302jev-mcp-open-source
    Self-hosted Jev MCP on Cloudflare Workers with intent routing, retrieval reranking and batch judgments

    baize7815/jev-mcp-open-source · TypeScript

    10
    typescript
  • 1303jev-measured
    Measured cost, latency, accuracy and raw output: TypeSafe's Jev and 12 other decision models (OpenAI Decisions API, Clef, Decider, d1…) — reproducible

    WallerChen/jev-measured · Python

    10
    benchmarkdecision-modelllm-routingopenai-decisions-apipython
  • 1304jev-model-labs
    Companion code for Engineering Decision Systems with JEV (AI Engineering Insider). A production-style toolkit (jevkit) plus eleven hands-on labs, one per chapter, for building decision systems on TypeSafe's Jev System One model.

    lamhotsiagian/jev-model-labs · Python

    10
    jev-apipython
  • 1305jev-model-router
    Routes each Claude Code turn's model and reasoning effort with TypeSafe Jev, and keeps small-window models away from large sessions.

    moelahmady/jev-model-router · TypeScript

    10
    typescript
  • 1306jev-observer
    A local proxy and dashboard for TypeSafe Jev decisions, with an embedded web UI.

    LimePencil/jev-observer · HTML

    10
    html
  • 1307Jev-Orchestrated-Decision-Mesh
    Jev-Orchestrated Decision Mesh (CIDM): training-free GPT-6 Luna/Sol routing with checked gates, source-linked evidence, and reproducible benchmarks. Created by Kenneth Vic A. Caber.

    kentilaok/Jev-Orchestrated-Decision-Mesh · Python

    10
    python
  • 1308jev-pdp-flow
    jev-pdp-flow: TypeSafe Jev ecosystem repository.

    arlequine/jev-pdp-flow · TypeScript

    11
    typescript
  • 1309jev-pi-skills
    pi extension: TypeSafe Jev decisions as tools (search, rerank, supervise, pick) and hooks (skill select, compaction)

    damian87x/jev-pi-skills · JavaScript

    10
    pi-packagejavascript
  • 1310jev-pick-and-place-study
    A small reproducible MuJoCo pilot comparing Jev, Claude Haiku, and reactive rules for pick-and-place.

    tryaksh/jev-pick-and-place-study · Python

    10
    python
  • 1311jev-playground
    Toy projects testing Jev (TypeSafe System One): snake autopilot, Todoist sorter, HN re-ranker, Dangerous Dave autopilot

    nikhil1raghav/jev-playground · C

    10
    c
  • 1312jev-playground
    System One-Compatible API Playground

    wagnerjt/jev-playground · TypeScript

    10
    typescript
  • 1313jev-playground
    A small Next.js app for experimenting with TypeSafe AI's Jev model (System One)

    Little-Planet-Labs/jev-playground · TypeScript

    11
    typescript
  • 1314jev-plays-pokemon
    Like Claude Plays Pokemon, but with Jev

    zbloss/jev-plays-pokemon · Python

    11
    ai-agents
  • 1315Jev-POC-Lead-Gen
    Jev-POC-Lead-Gen: TypeSafe Jev ecosystem repository.

    shailesh-svg/Jev-POC-Lead-Gen · TypeScript

    10
    typescript
  • 1316jev-practice-speed
    A WebGL demo where you play the card game Speed against a CPU whose brain is TypeSafe AI's Jev. The whole point of the app is to measure and show Jev's decision speed and decision accuracy in real time.

    tubone24/jev-practice-speed · JavaScript

    10
    card-gamejavascript
  • 1317jev-project-fit-review
    Review independente sobre a adequação do Jev a produtos e desenvolvimento multiagente

    Teagar/jev-project-fit-review

    10
    ai-routingdecision-model
  • 1318jev-prompt-optimization
    automatically optimizing the instructions and decision criteria of TypeSafe Jev Choice from labeled data

    j341nono/jev-prompt-optimization · Python

    10
    python
  • 1319jev-reach
    chrome-devtools-mcp plus one tool: Jev walks the browser to the spot, your agent makes one devtools call there.

    rashedInt32/jev-reach · TypeScript

    10
    ai-agentsbrowser-automationchrome-devtoolsclaude-codeclaude-code-pluginllm-toolsmcp
  • 1320jev-readability
    jev-readability: TypeSafe Jev ecosystem repository.

    hifizz/jev-readability · JavaScript

    11
    javascript
  • 1321jev-report
    发明 RLHF 的人，这次做了个不会说话的模型：Jev 独立研究报告。52 页 PDF + 50 条中文实测复现包 + 143 条可回溯数据表

    HackSing/jev-report · Python

    10
    pythonai-researchchinesellm-evaluation
  • 1322jev-review
    https://www.webreactiva.com/blog/empezar-jev-typesafe

    delineas/jev-review · TypeScript

    10
    typescript
  • 1323jev-review
    Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation

    thiago-ss/jev-review · Python

    10
    python
  • 1324jev-router
    Jev picks the right Claude or OpenAI model, effort and skill for each prompt. Claude Code plugin + TypeScript/Python router + Codex launcher

    Hoppin-Sorter/jev-router · TypeScript

    10
    claude-codeclaude-code-plugincodexmodel-routingopenaitypescript
  • 1325jev-routing
    Go Jev harness for Claude Code, Codex, and Grok Build. No npx. Not an MCP server.

    nekowasabi/jev-routing · Go

    10
    gogrok
  • 1326jev-sandbox
    Test bench for TypeSafe's Jev

    amr05008/jev-sandbox · TypeScript

    10
    typescript
  • 1327jev-screening-benchmark
    Benchmark of TypeSafe Jev (System One decision model) for systematic review title/abstract screening vs GLM/Sonnet on Cohen_2006 gold standard

    Saeedabdf/jev-screening-benchmark · TypeScript

    10
    typescript
  • 1328jev-sheets
    Jev for Google Sheets

    Cab14bacc/jev-sheets · TypeScript

    12
    typescript
  • 1329jev-should-i-apply
    Typesafe/Jev public X demo

    cardotrejos/jev-should-i-apply

    10
  • 1330jev-showdown
    Jev plays Pokemon Showdown: 40 battles, 940 decisions, reproducible results, and an annotated replay.

    izzuddin8803/jev-showdown · Python

    10
    ai-evaluationpokemon-showdownpython
  • 1331jev-sim
    Jev-compatible /v1/systemone server reading typed decisions from LLM logits, benchmarked against TypeSafe's Jev on the same items via JevBench

    dashbi1/jev-sim · Python

    10
    benchmarkcalibrationclassificationllmlogprobspython
  • 1332jev-sinhala-review
    Empirical zero-shot benchmark of TypeSafe Jev (v1.13.0) on low-resource Sinhala and Singlish NLP benchmarks (SOLD, SinhalaMMLU, NSINA)

    Azri-Muhsin/jev-sinhala-review · Python

    10
    benchmarkdecision-modelindic-nlpnlpsinhala-nlppython
  • 1333jev-skill
    Agent skill for TypeSafe AI's Jev decision model: fit assessment, integration recipes, calibration, multi-Jev, benchmarks

    abhisheksharma001/jev-skill · Python

    10
    python
  • 1334jev-skill
    Jev skill for Claude Code and Codex: TypeSafe System One guide, Python CLI, 5 tested recipes, and findings from 19,367 Jev calls.

    marcodicesare-dev/jev-skill · Python

    10
    agent-skillsai-agentsclassificationclaude-codecodexdecision-modelllm-evaluation
  • 1335jev-skill
    Unofficial agent skill for TypeSafe AI's Jev: typed Choice, Score, and Noul decisions with calibrated confidence, and eleven implementation shapes, each with a code sketch.

    PyModel/jev-skill · Python

    11
    agent-skillsantigravity-clicalibrated-confidenceclaude-codecodexmusestructured-output
  • 1336jev-skill
    jev-skill: TypeSafe Jev ecosystem repository.

    heyman333/jev-skill · JavaScript

    10
    javascript
  • 1337jev-skill-scout
    Finds the turns where Claude Code should have loaded one of your skills and did not, judged by TypeSafe's Jev. Audit CLI plus the mod that fixes it live.

    karanb192/jev-skill-scout · JavaScript

    10
    javascript
  • 1338jev-slop-detector
    Chrome extension + local relay that labels X posts with a Jev (TypeSafe) hype-over-substance probability

    SylphAI-Inc/jev-slop-detector · JavaScript

    10
    javascript
  • 1339jev-snake
    Snake autoplay powered by TypeSafe Jev (System One)

    lalitsonawane/jev-snake · TypeScript

    10
    typescript

第 1301–1350 条，共 3057 条