Jev Show

184 runs 7,723 Jev calls 18m 10s judging last run 8 Nov 02:54 UTC 4.6M input tokens since 21 Sep

Unverified

Judged to be Jev projects, but short of a publishing threshold: 609 on category confidence (needs more than 0.60), 42 on Jev confidence (needs more than 0.65), 22 on both.

  • judge-jev

    Typesafe jev code judgement harness

    randlee

    benchmarkgithub8 Nov

  • JEV-testing

    PWA test console for Jev (TypeSafe System One) structured-decision primitives: noul, choice, score and box. Request builder, answer visualizers, presets, history, cost meters, and a bundled local CORS proxy.

    krishnakanthb13

    benchmarkgithub7 Nov

  • systemone-mcp

    MCP server for any System One backend (Ollama nimble/tev/clef, TypeSafe jev, Kev, Laya).

    es11225599

    dev-toolgithub7 Nov

  • ProbablyThisWay, has a live demo

    Map-first hiking decision support: scores a trail's route alternatives against live weather and daylight with TypeSafe AI's Jev, applies a deterministic safety policy, and replays the pick on 3D terrain.

    shivamshinde123

    demogithub7 Nov

  • smart-factory-ai-ops-center

    Smart factory AI operations center: closed-loop simulation with a structured decision model (TypeSafe Jev), safety gate, virtual PLC/MQTT — research code and data (simulation only)

    Imperfective

    demogithub7 Nov

  • jev-wingman

    Reply suggestions for Slack, Discord, LINE, Telegram, Messenger, Instagram and Threads on macOS, built on Jev (TypeSafe's System One decision model).

    chyiiiiiiiiiiii

    dev-toolgithub6 Nov

  • cognix-decisions-jev

    COGNIX[WS] extension: TypeSafe's Jev answers the agents' fast browser decisions

    cognixws

    agent-harnessgithub6 Nov

  • contact-cleaner, has a live demo

    Clean your Google Other contacts with TypeSafe's Jev: Keep / Review / Remove

    rubenhassid1

    dev-toolgithub6 Nov

  • jev-semantic-merge-gate

    Declared semantic merge policies with exact changed-line evidence.

    gbesse

    dev-toolgithub5 Nov

  • systemone-mcp

    MCP server for System One typed-decision endpoints (/v1/systemone). Works with TypeSafe Jev and Bailian decision models; tolerates missing usage.output_tokens.

    yaofeng

    dev-toolgithub5 Nov

  • jeview

    Local visualizer and gateway for TypeSafe AI Jev, with an agent-friendly architecture guide and direct yes/no chat panel

    toasterman234

    dev-toolgithub5 Nov

  • hermes-jev-thread-status

    Jev-powered Discord thread status titles for Hermes Agent: [Running] → [Needs feedback] → [Done], auto-retitle, delayed archive.

    xiaoyaner0201

    agent-harnessgithub4 Nov

  • jarvis

    Voice commands for your Mac: patterns first, Jev (TypeSafe) to decide, an LLM only to write.

    craigraphics

    dev-toolgithub4 Nov

  • tolerable-x-feed

    Are you tired of pretentious engagement-bait posts on X? Tolerable X Feed is a Tampermonkey userscript that hides bait, promo posts and paid ads using TypeSafe's Jev decision model (OpenRouter, TypeSafe, or self-hosted), for under 1 cent per 1,000 posts.

    nikkoxgonzales

    guardrailsgithub4 Nov

  • playwright-jev-testing-refactored

    Goal-driven Playwright E2E testing where TypeSafe Jev (System One) decides the next action. Reviewed and refactored: fixed agent callback signature and cleaned observer dead code.

    Sandesh-S-Dalvi

    agent-harnessgithub4 Nov

  • pi-jev-router-pro

    Single-surface TypeSafe Jev model router for the Pi coding agent: one virtual model (jev/auto) with judgment routing, mid-turn transient fallback, and first-class routing profiles.

    01Joseph-Hwang10

    agent-harnessgithub4 Nov

  • next-steps-jev

    Suggested next steps for Claude Code, scored by how much each one helps your goal. Claude proposes up to three prompts, TypeSafe's Jev scores them, and the best comes first.

    kevinyin9

    benchmarkgithub4 Nov

  • Show HN: Kairos – Open-source risk and fraud decisioning platform

    Hey HN, Ayan here from Finic. We’re launching Kairos, an open source alternative to Sift, Sardine, and other real-time fraud decisioning platforms. Kairos addresses two of the biggest problems facing traditional decisioning tools: a lack of labeled data to train on and dealing w…

    ayanb9440

    guardrailshn3 Nov

  • jev-router

    Mod Claude Code : Jev (TypeSafe, via OpenRouter) choisit l'effort de raisonnement de chaque message, avec bandeau pour épingler un effort

    pyxl-dev

    agent-harnessgithub3 Nov

  • typesafe-cascade

    Typed System 1 → System 2 cascade: TypeSafe Jev answers when confident, a reasoning model takes the rest.

    monumei

    agent-harnessgithub3 Nov

  • chargeback-clock

    AI dispute desk for D2C brands: fight, refund or get one document, with a verified response draft. Go + Claude, second opinion by Jev (TypeSafe).

    Shravan-Amberkar

    agent-harnessgithub3 Nov

  • omadia-jev-plugin, has a live demo

    TypeSafe Jev as the omadia decision model (decisionModel@1): model yes/no, data source and learned queries before any LLM call

    byte5ai

    librarygithub3 Nov

  • jev-toolkit

    Experiment: a judgement model (TypeSafe Jev) next to Claude. Router mod for Claude Code. Learning project, not original.

    Wrenik

    guardrailsgithub3 Nov

  • cc-cockpit-jev

    Jev (TypeSafe's typed classifier) as a cc-cockpit plugin service: choice, yes/no and score questions for other plugins, with usage counts and a monthly cap.

    BronOS

    dev-toolgithub3 Nov

  • murmur

    A customizable Twitch mascot that reacts to chat with TypeSafe Jev, optional Groq replies, Twitch Extension support, and an OBS overlay.

    Malekse21

    othergithub3 Nov

  • skills, has a live demo

    Agent skills by Tim Wolf: Claude Code plugin + npx skills pack. First up: wlf-jev (TypeSafe Jev questions, designed, calibrated and wired in).

    theamazingwolf

    dev-toolgithub3 Nov

  • systemone-lab

    Hands-on System One decision lab: Jev-compatible Noul/Choice/Score over local open-weight Laya, with playground UI, routing/eval examples, and CI smoke tests.

    baldellimtt

    benchmarkgithub2 Nov

  • Jev-Router

    Decision-first, OpenAI-compatible AI router powered by Jev typed decisions. Routes every request to the right LLM, agent or tool with explainable traces, fallbacks, guardrails and cost savings. #LLM #LLMRouter #AIGateway #Jev #OpenAI #AIAgents #LLMOps #FastAPI

    AIAnytime

    agent-harnessgithub2 Nov

  • pr-wall

    A House Elves elf: a repo's open PRs on a wall, each with what TypeSafe's jev says about its tests

    House-elves

    dev-toolgithub2 Nov

  • master-typesafe-jev

    Master TypeSafe Jev AI: Fast and Low-Cost AI Decision Models

    huytranvan2010

    librarygithub1 Nov

  • Jev relevance scoring for similar-channel search

    How Channel Finder uses Jev as one typed semantic relevance signal, while code and manual review keep deterministic rules and final judgment separate.

    maeshchenko.hashnode.dev

    othersubmission1 Nov

  • jev-trader

    Local CLI and web desk. Robinhood Agentic MCP is the tape. TypeSafe Jev votes. Simulate by default.

    Errr0rr404

    agent-harnessgithub1 Nov

  • astrbot-betterchat

    AstrBot 插件：私聊耐心等待用户说完再合并回复（可打断生成），群聊用 Jev 判断要不要插话

    AS214933

    agent-harnessgithub1 Nov

  • talk-to-jev

    Wire a cheap LLM to TypeSafe Jev with one OpenRouter key

    NatersGonnaN8

    demogithub1 Nov

  • netizen, has a live demo

    Simulate how Indonesian netizens react to a post before it goes live (TypeSafe/Jev)

    Seheta

    demogithub31 Oct

  • dsh-jev-mcp

    TypeSafe Jev decision tools for DeepSeek Harness: dependency-free client library and stdio MCP server (jev_check, jev_route, jev_score, jev_evaluate).

    bojansandhaus

    librarygithub31 Oct

  • antigravity-jev-skills

    Gemini implementation, TypeSafe Jev evidence triage, and Codex final-review skills.

    AJackTi

    demogithub31 Oct

  • JEV-27B-Desktop

    JEV 27B pulls jev ai model and jev huggingface. typesafe jev, jev llm, ollama gguf, quant lane, qwen base, local desk, vl caption, instruct tune, sock pull, weights, blob store, dtype cast.

    typesafe-inc

    dev-toolgithub · official31 Oct

  • fwd-proxy

    generic https forward proxy for typesafe jev

    sumnous

    dev-toolgithub30 Oct

  • jev-browser-mcp

    MCP tool exposing TypeSafe's Jev browser agent (via browser-use/jev-ultrafast) to Claude Code/Desktop

    eduardo-xyz

    agent-harnessgithub30 Oct

  • app-classification-harness

    AI harness for classifying PC application purpose and category with TypeSafe Jev typed decisions and quantitative scoring.

    x3nc0n

    agent-harnessgithub30 Oct

  • jev-resume-analyzer, has a live demo

    Resume and CV analysis: a 0-100 content score, layout checks, and job alignment. React, FastAPI, TypeSafe Jev.

    awun8191

    othergithub30 Oct

  • jevmoji

    Emoji reactions for your group chat, scored by TypeSafe Jev.

    amscotti

    librarygithub30 Oct

  • angular-flappy-bird-jevai

    Watch TypeSafe Jev (OpenRouter decisions API) play Flappy Bird — Angular 22 + Phaser 3, with every model decision logged live.

    IDaniel8

    demogithub29 Oct

  • building-with-jev-skill

    A skill for writing and improving programs that call Jev, TypeSafe's System One model

    dbreunig

    librarygithub29 Oct

  • 2026_system-one-drawer

    Draw objects from toy blocks, evolved with TypeSafe's Jev as the judge

    willirath

    demogithub29 Oct

  • opencode-jev-pruner

    OpenCode V2 plugin: dynamic context pruning for MCP tools and skills using Jev (TypeSafe System One)

    theroich

    dev-toolgithub29 Oct

  • fraudlens, has a live demo

    Base del MVP de FraudLens: Next.js, MongoDB, Mongoose y TypeSafe/Jev con AI SDK.

    mateolewinzon

    demogithub28 Oct

  • s1kit, has a live demo

    Test, calibrate and route System One decision models (Jev, Laya, kev, llama.cpp, Ollama) on your own data.

    Eliot5566

    librarygithub28 Oct

  • telegram-resender

    Telegram client (Telethon, runs on your own user account, not a Bot API bot) that watches chats/channels/folders and forwards matches to a target chat, topic, or webhook. Triggers: word lists, OpenAI prompts, 👍/👎 reactions, Typesafe JEV. Actions: source link & reason, auto-cre…

    popstas

    guardrailsgithub28 Oct

  • ticket-triage

    Support-ticket triage service in Go: Kafka, Postgres, and TypeSafe Jev classification (learning project)

    nacknime-official

    data-pipelinegithub28 Oct

  • jev-for-marketers

    A free guide and Claude skill for using TypeSafe's Jev model on marketing ops decisions: lead routing, reply triage, on-message checks and asset tagging.

    brent-phillips

    demogithub28 Oct

  • playbook-sales-copilot

    Copiloto de vendas ao vivo com o Jev (TypeSafe): probabilidade de fechamento, sinais e próxima jogada — em português

    felipenunes07

    demogithub28 Oct

  • jev-router-playground, has a live demo

    Interactive playground for testing Jev model-routing decisions against OpenRouter models

    hugo-alves

    benchmarkgithub28 Oct

  • opencode-auto-question

    opencode plugin that auto-answers the question tool for autonomous agents using Jev (TypeSafe decision model) or an LLM JSON contract, with tool-assisted context gathering

    jflowers

    agent-harnessgithub28 Oct

  • jev-guide

    Chrome extension that highlights the next thing to click to reach a goal on a website, using Jev (TypeSafe System One). The person does the clicking.

    some45bucks

    othergithub28 Oct

  • WechatSignals

    macOS 本地优先微信单聊分析客户端：只读读取、匿名化、官方 TypeSafe Jev、SQLite 与 Keychain

    Jelly-RayTian

    othergithub27 Oct

  • Jev-Auto-Router, has a live demo

    Jev Auto Router: turn-pinned model and effort routing for Codex via TypeSafe Jev.

    miniLV

    librarygithub27 Oct

  • hitbox

    Vision-driven, selector-free UI testing for Playwright and Selenium, powered by TypeSafe Jev. Automates canvas, WebGL, Flutter Web, and DOM interactions.

    Azri-Muhsin

    librarygithub27 Oct

  • jev-ad-pattern-lab

    Painel local para analisar padrões de anúncios ativos da Biblioteca de Anúncios da Meta com o modelo Jev (TypeSafe).

    barral0

    demogithub27 Oct

  • jev-assistant

    Jev desktop voice assistant: LiveKit, TypeSafe judgments, saved tasks, Chrome/Mac control and optional Orgo/Composio integrations. Phase 1 Mac preview.

    jbellsolutions

    agent-harnessgithub26 Oct

  • jobme-job-scout

    This tool allows user with a Claude or ChatGPT AUD$30 p/m subscription and a Typesafe JEV API key to run a regular schedule that scrapes the web for jobs they'd want to do and sends a report with the highest rated jobs.

    hwillysim

    data-pipelinegithub26 Oct

  • claudecode-jev-marketplace

    TypeSafe Jev (System One) wired into Claude Code: a decision primitive for hooks, and the Skylence herdr agent-org with Jev measuring tier and review gates.

    skylence-org

    agent-harnessgithub26 Oct

  • instinct

    A Balatro-playing agent: simulated decision tree, TypeSafe Jev judgments, live dashboard

    Vasiniks

    agent-harnessgithub26 Oct

  • omp-maestro, has a live demo

    🎼 My oh-my-pi (omp) setup in one command: public plugins & skills I use, my own Jev Router, and three switchable model ensembles — Claude, ChatGPT, or a mix where Claude leads and GPT codes.

    hsmoviich

    agent-harnessgithub26 Oct

  • x-post-classifier

    Chrome Extension that categorizes posts on x.com as you scroll your feed, powered by TypeSafe's System One decision model (Jev).

    aslamdoctor

    othergithub26 Oct

  • jev-tos-checker, has a live demo

    Chrome extension that flags terms-of-service clauses that may work against you, using TypeSafe's Jev model

    shohei81

    guardrailsgithub26 Oct

  • toolscout

    Claude Code mod: compact MCP tool catalog and per-message tool routing with TypeSafe Jev

    adapt-to-it

    agent-harnessgithub26 Oct

  • jevit

    JevIt: AI mail triage for Thunderbird with TypeSafe's Jev model. Unofficial.

    Xvectorio

    othergithub26 Oct

  • JEV-Arcade, has a live demo

    Fifteen live AI games: TypeSafe Jev vs. Claude, GPT, OpenRouter and Ollama models

    Analytics206

    benchmarkgithub26 Oct

  • omp-jev-compaction

    Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter

    jerryfane

    dev-toolgithub25 Oct

  • openclaw-plugin-typesafe-ai

    TypeSafe AI (Jev System One) plugin for OpenClaw - sub-100ms group triage, tool safety guardrails, compaction curation, and model routing

    jason-allen-oneal

    guardrailsgithub25 Oct

  • jev-pii, has a live demo

    Column-level PII and compliance discovery in DuckDB SQL with typed TypeSafe Jev answers; runs in the browser via Pyodide

    senthilsweb

    demogithub25 Oct

  • opencode-context-pruner

    Continuous verbatim context pruning for OpenCode, powered by TypeSafe Jev. Port of fast-jev-compaction adapted to OpenCode's context hook.

    hoshinodis

    librarygithub25 Oct

  • legends-jev

    Optical character recognition (OCR), storefront signage verification, bounding-box grounding, and typed computer-use decision CLI powered by TypeSafe Jev 1.14.

    avalonreset

    agent-harnessgithub25 Oct

  • smart-doc-vision

    智审图档 SmartDoc Vision 是一个面向档案、图纸、扫描件与文本内容的审核中台。后端使用 Go + Gin，数据层使用 MySQL + Redis，管理后台使用 Vue 3 + TypeScript + Naive UI + ECharts。平台支持通用大模型（OpenAI 兼容协议或 Anthropic Claude Messages API，两者属于同一业务分类，仅协议不同），并原生支持 JEV / TypeSafe System One 结构化决策模型。

    ImYoyoData

    guardrailsgithub25 Oct

  • laya-serve

    A container image for [Laya](https://pypi.org/project/laya/), the open-weight typed-decision model, served over the `POST /v1/systemone` protocol (the same wire format as TypeSafe's Jev API). tuvl's `decide` agents use it as a decision model; anything that speaks `/v1/systemone`…

    tuvl-io

    agent-harnessgithub24 Oct

  • engram

    Persistent local memory for TypeSafe Jev-powered agents.

    Paras5Yadav

    librarygithub24 Oct

  • discoprint

    Classify an artist's discography by theme, mood, and lyrical complexity with Jev (TypeSafe AI), and view it as a colorful terminal dashboard

    lirantal

    data-pipelinegithub24 Oct

  • jev-game-agent

    Autonomous Android Game Agent using TypeSafe AI Jev

    felix0123456

    agent-harnessgithub24 Oct

  • dsh-jev

    DeepSeek Harness plugin: Jev (TypeSafe System One) as an injectable ctx.jev service, plus a jev_ask tool.

    gjy1992

    agent-harnessgithub24 Oct

  • skills, has a live demo

    Agent skills for building with TypeSafe's System One API

    typesafe-ai

    demogithub · official24 Oct

  • jev-scalper

    Paper-trading scalper for Binance meme coin perps that uses TypeSafe’s Jev as a signal classifier, with live data, simulated fills and real fees.

    tchesa

    demogithub24 Oct

  • jev-dashboards

    Live data-monitoring dashboards with TypeSafe Jev as the decision engine, plus an independent evaluation of Jev

    sukritisehgal-28

    benchmarkgithub24 Oct

  • shapes-of-stories

    Chart the shape of a story: ten qualities, events and a named arc for any book, screenplay or transcript, scored with TypeSafe's Jev.

    Ferrum-Citadel

    data-pipelinegithub24 Oct

  • typesafe-mcp

    A standard Model Context Protocol (MCP) server that exposes TypeSafe AI's Jev decision model as typed tools.

    devbux

    librarygithub23 Oct

  • playwright-system1-triage

    Autonomous Playwright failure triage, CI quality gate, and AI QA calibration benchmark powered by System 1 decision models (Laya local ONNX & TypeSafe Jev API).

    kint4

    benchmarkgithub23 Oct

  • jev-cua-android

    Jev (TypeSafe) driven Android UI test agent: accessibility perception, probability-guarded actions, decision cache + plan replay

    Bafise-nh

    agent-harnessgithub23 Oct

  • hollow-knight-jev

    Experimental Hollow Knight state bridge and bounded TypeSafe Jev controller. Source only; bring your own game and API key.

    mbrajk

    librarygithub23 Oct

  • Jevatar

    An AI companion that replies only with facial expressions. Jev (TypeSafe System One) judges your message and picks 1 of 14 moods; blobatar morphs its face. React + Vite + Bun.

    AppChainAI

    demogithub23 Oct

  • ollaya, has a live demo

    Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 24 model families (Laya, pplx-decider, Clef, Winnow, Kev...) locally or self-hosted behind /v1/systemone. TypeSafe SDK works by changing one env var. CLI, daemon, desktop app, Docker,…

    ollaya-dev

    dev-toolgithub23 Oct

  • jev-libero

    Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.

    Dimweaker

    agent-harnessgithub23 Oct

  • jev

    JEV（TypeSafe）判斷模型等級與分類／打分／是非判斷的 Claude Code 外掛

    ricky94511

    dev-toolgithub23 Oct

  • jevmulator

    Local daemon serving the pinned TypeSafe Jev wire surface, backed by a configurable OpenAI-compatible model.

    esinecan

    dev-toolgithub22 Oct

  • courtvision

    Real-time basketball computer vision, live stats, TypeSafe Jev decision layer, and grounded AI narration with an operator dashboard.

    aiden-guan

    demogithub22 Oct

  • tcxJev

    TrussC addon for TYPESAFE AI Jev

    tettou771

    librarygithub21 Oct

  • filament, has a live demo

    Filter Filament tables with a plain-English statement. Each row is scored by TypeSafe Jev.

    vibefilter

    dev-toolgithub21 Oct

  • fmev

    TypeSafe Jev-compatible decision API on Apple's built-in on-device Foundation Model

    mrubens

    librarygithub21 Oct

  • tinyAIassistant

    using a decicion model (like typesafe jev) running locally to do natural language input, controlling things like home assistant devices via a sort of "choose your own adventure game" prompt "ui"

    EmiliaThorsen

    agent-harnessgithub21 Oct

  • krasivo-jev

    Training data and models for "system one" classifiers: one forward pass, no reasoning. 100 Hugging Face datasets turned into one format (state → question → options → label), a Qwen3.5-2B LoRA model with a pointer head, held-out benchmarks, and a vLLM plugin that serves TypeSafe'…

    SergeyBazhmin

    librarygithub21 Oct

  • JEV-from-Scratch

    In this repository, I have tried to build JEV model from TypeSafe AI from scratch

    ES7

    othergithub21 Oct

  • ai-jev-filter, has a live demo

    JEV 检索台 · 对话式网络信息筛选工作台：官方 /v1/systemone 协议接入、noul/score/choice 三原语判定、真伪+匹配+分类、脱敏前置、知识库与提示词工作台（纯前端，双击即用）

    Wu-love-han

    guardrailsgithub21 Oct

  • mcp-server-jev

    Typed AI decisions for Codex, Claude and any MCP client, powered by TypeSafe Jev. Classify, score and evaluate with one generic tool.

    MattiooFR

    dev-toolgithub21 Oct

  • Ripple

    주식 관련 뉴스를 자동으로 모으고 Jev(TypeSafe AI)로 관련도와 호재·악재를 골라 웹으로 보여 주는 개인용 앱

    anjfgkfkrh

    othergithub21 Oct

  • jevdict

    Decisions with probabilities, not prose. Typed decision specs, gate exit codes, CI-ready — built on Jev (TypeSafe System One).

    Hashimlokasher

    dev-toolgithub21 Oct

  • picode-decisions-jev

    COGNIX[WS] extension: TypeSafe's Jev answers the agents' fast browser decisions

    cognixws

    librarygithub21 Oct

  • medgemma_Ophthalmology_jev

    Agentic AI System for Diabetic Retinopathy Screening using Fine-Tuned MedGemma 1.5 4B & TypeSafe AI Jev.

    harsaas

    agent-harnessgithub21 Oct

  • jev-mcp

    Minimal community MCP adapter for TypeSafe Jev structured decisions. Local-first, typed tools, no bundled credentials.

    asimons81

    librarygithub21 Oct

  • system-one-projects

    Monorepo for System One AI decision models (TypeSafe Jev, Cloudflare Clef) applications and services

    parth5012

    othergithub20 Oct

  • jevulator

    A locally run emulation of TypeSafe’s Jev, served via llama-server + Qwen3.6-35B-A3B.

    Huberdoggy

    demogithub20 Oct

  • jev-decision-api-lambda-web

    Hono API on AWS Lambda Web Functions that exposes Jev (typesafe/jev-1.13 via OpenRouter) typed decisions. Terraform IaC, plan-only CI.

    miqui

    agent-harnessgithub20 Oct

  • claujev

    Jev (TypeSafe AI) as a second pair of eyes for Claude Code: request triage, automatic effort, command guard, rule review and a final check. Claude Code plugin, zero dependencies.

    Civalski

    guardrailsgithub20 Oct

  • Show HN: Photo Ferret – open-source photo album with creative filters

    I wanted a way to filter my photo album using more creative continuous filters (scene complexity, presence of curvy lines, portion of photo occupied by mountains, etc.) Photo Ferret has two components: 1) Run the application on your computer and use the TypeSafe Jev API to gener…

    SteveVeilStream

    data-pipelinehn20 Oct

  • system-one-incident-triage

    Incident triage as System One questions: a report in, typed decisions with probabilities out. Keyword rules vs a local model, through the TypeSafe SDK.

    gsaini

    demogithub20 Oct

  • decidealot

    Make the call. Run local Laya, Von, CLM or hosted Jev for typed classification and scoring through one HTTP and MCP API, with resource-aware batches.

    psyb0t

    data-pipelinegithub20 Oct

  • JEVgotiator

    Text an agent about a used Tesla, get five Jev-scored picks with decision traces and a deal plan. JEVathon 2026 build (Next.js, Eve/iMessage, TypeSafe Jev).

    benikigai

    demogithub20 Oct

  • jev-mobile

    One TypeSafe Jev decision per step over the A11Y tree, executed via ADB. No screenshots and ultra fast!

    xinwang-nwpu

    agent-harnessgithub20 Oct

  • recoveriq

    Cost-aware recovery for AI coding agents, guided by TypeSafe's Jev decision model. Live benchmark: 108 runs with real Claude + Jev.

    sanghamitrajohri

    agent-harnessgithub20 Oct

  • jev-judge

    Universal Model Context Protocol (MCP) server and CLI runner for TypeSafe Jev decision models. Calibrated evaluation for code reviews, acceptance gating, and agent guardrails across Claude Code, OMP, and Cursor.

    Ridlo543

    guardrailsgithub19 Oct

  • jev-agent

    Chrome extension that runs browser tasks from a prompt: DeepSeek plans, TypeSafe Jev grounds. IRCTC + MakeMyTrip flows, stops before payment.

    sknitd

    agent-harnessgithub19 Oct

  • quicksilver

    Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.

    Yusuf02653

    agent-harnessgithub19 Oct

  • jev-align

    Build calibrated AI Functions from human feedback using Jev and GEPA.

    sutro-sh

    librarygithub19 Oct

  • omo-jev-plugin

    Jev-powered decision support for OmO and senpi agents

    brianhong-dev

    librarygithub19 Oct

  • graph-composition-with-dLLMs

    A Graph-Compiled Specification RAG system built with **Dagster**, **PostgreSQL (`pgvector` + Recursive CTEs)**, **Diffusion LLMs (`mercury-2`)**, **TypeSafe System One (`jev-latest`)**, and **OpenAI (`gpt-6.1-sol`)** to resolve multi-hop engineering specification overrides and T…

    JosephHardy91

    guardrailsgithub19 Oct

  • jevision

    Typesafe Jev image prototype

    yexerik

    demogithub19 Oct

  • glimpse-jev

    Computer use on the GNOME desktop: a planner plans, Jev (TypeSafe) acts and checks.

    Viverun

    agent-harnessgithub19 Oct

  • job-scan-public

    Daily job alert that uses TypeSafe Jev to judge which jobs fit you. Includes a build prompt and a non-technical guide for building your own copy with Claude.

    ido-barnoam

    data-pipelinegithub19 Oct

  • jev-job-matching

    Experiment: Jev (TypeSafe AI) scored 400 real job posts against 30 fictional candidates. 12,000 decisions in 3m17s for $0.17, with an answer key and what it got wrong.

    kaucap08

    benchmarkgithub19 Oct

  • dsh-judgment

    Structured judgment plugin for DeepSeek Harness: ask batched named questions (choice, score, yes-probability) and get calibrated probabilities from TypeSafe Jev, Luna, or any compatible endpoint. Strict validation, per-connection config, audit ledger, budget metering. It judges;…

    j62268781-alt

    librarygithub19 Oct

  • siteeye

    Construction-site near-miss prediction: YOLO vision + TypeSafe Jev 1.14 decision model, local web app

    seominpapa

    demogithub19 Oct

  • laya

    Laya open-weights decision model behind a TypeSafe/Jev-compatible API, as a Railway template

    two-workspaces

    librarygithub19 Oct

  • BotStory

    BotStory: Cosmic v83 + cosmic_agents companions, living world, citizens, TypeSafe Jev, skill probe harness

    Incluwin

    agent-harnessgithub18 Oct

  • jev-telegram-agent

    Agente de navegación web y descargas de música por Telegram, con Jev (TypeSafe) + Playwright

    ScriperX

    agent-harnessgithub18 Oct

  • quick-qa-helper

    Hand an Android UI QA task to a fast loop: Claude Haiku plans, TypeSafe Jev picks elements and verifies, adb acts. Claude Code plugin + CLI.

    ouor

    agent-harnessgithub18 Oct

  • INployed

    Find, rank, tailor and apply to jobs from one Windows desktop app: a scheduled cloud scrape feeds a scorer that filters in code, then ranks in two Gemini or Claude stages; a PySide6/Qt dashboard tailors a one-page LaTeX résumé from facts you wrote; a Playwright runner judged by…

    yib7

    agent-harnessgithub18 Oct

  • handoff-graph

    Issue routing that remembers who hands what to whom. FalkorDB graph memory + TypeSafe Jev. Graph Hacks 2026, Track 2.

    aashish-g03

    guardrailsgithub18 Oct

  • jev-cascade, has a live demo

    Jev answers first; only the uncertain band goes to a stronger model, with a check that stage two really is stronger.

    CapCurious

    agent-harnessgithub18 Oct

  • aftercall

    aftercall: you keep your conversations, we handle the rest. Conversation intelligence on Google Cloud (Gemini, Cloud Run, Firestore) with TypeSafe Jev.

    Siddamnn

    agent-harnessgithub18 Oct

  • qiaomu-ban-bot

    用 Jev 折叠 X 上的疑似 AI 回复，保留有价值的讨论。A Chrome extension powered by TypeSafe Jev.

    joeseesun

    guardrailsgithub18 Oct

  • pi-jev-auto-mode

    Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.

    jomatsu

    guardrailsgithub18 Oct

  • jev-game-mvp

    Jev 1.14 as an NPC decision brain: a tiny grid game where NPC actions come from TypeSafe's decision model (Choice/Score/Box). API key via env var.

    h1bomb

    gamegithub18 Oct

  • quicksilver

    Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.

    donnahughes06

    agent-harnessgithub18 Oct

  • JevHypa

    RisuAI long-term memory plugin powered by TypeSafe Jev + embeddings

    happydesk213124

    librarygithub18 Oct

  • jev-trader

    30-day paper-trading experiment: TypeSafe's Jev manages a copy of my portfolio

    SHRIVP

    benchmarkgithub17 Oct

  • jev-seri

    Guncel Gundem: Jev videolarinin kodlari ve olcumleri(TypeSafe Jev, System One)

    an80x86

    benchmarkgithub17 Oct

  • jev-vehicle-classifier

    TypeSafe Jev + vision features로 도로교통량 12종 차종을 식별하는 ITS 딥러닝 연재 프로젝트 (ep.1)

    kh20134

    demogithub17 Oct

  • jev-check, has a live demo

    Snap a photo, know if everything's there. Customise your own rules, get answers from Jev in under a second, and benchmark the results.

    Shobhnik13

    benchmarkgithub17 Oct

  • effortless-hermes

    Hermes Agent plugin: picks the reasoning effort for every prompt via a fast judge (Jev/TypeSafe, local model, or any custom API). Port of effortless for Claude Code.

    ivcained

    agent-harnessgithub16 Oct

  • jev-advisor-gateway

    Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).

    1arley

    guardrailsgithub16 Oct

  • s1-studio, has a live demo

    S1 Studio — 開源的 /v1/systemone 結構化決策模型 Web UI 測試沙盒（支援 TypeSafe Jev、Ollama clef / clef-flash 與自建端點的 Choice / Score / Noul 視覺化機率診斷、A/B 端點對比與 SDK 匯出）

    doggy8088

    dev-toolgithub16 Oct

  • ext-typesafe-ai

    Flow Steward extension for Jev is TypeSafe’s flagship model and the first System One model

    Flow-Steward

    agent-harnessgithub16 Oct

  • kenteiscript

    KenteiScript: a small JSON language for quizzes and tests, written by an LLM (DSL as Harness). People answer in their own words; a decision model (TypeSafe JEV) grades them. Includes MulmoKentei, a sample runtime on Cloudflare.

    receptron

    agent-harnessgithub16 Oct

  • jev-fast-skills

    TypeSafe Jev 4 Core Fast Skills Plugin (fast-context, fast-memory, fast-browser, prompt-engineer) for Google Antigravity & Claude Code

    stkang9409

    librarygithub16 Oct

  • Show HN: Three philosophers vote on your questions

    I'm RN developer in South Korea, i built this on my own. Non-native speaker, sorry for my English. - Sometimes it is very hard to decide something. - So I made simple service for get decisions from "Three Old Awesome philosophers’ vote". - No sign-up needed. - Using Jev(Pro…

    notkant

    gamehn16 Oct

  • facet-photo

    AI photo culling & sorting for macOS and Windows. Custom labels, local face recognition and RAW support, powered by TypeSafe Jev.

    CeelNok

    othergithub16 Oct

  • gavel

    Governed AI judgments for Salesforce. Works with TypeSafe Jev.

    shivanathd

    guardrailsgithub16 Oct

  • wellposed, has a live demo

    Lints Jev requests before they are sent: offline checks for missing none-of-the-above options and broken state paths, then Jev itself for what structure cannot decide.

    suraj-phanindra

    dev-toolgithub16 Oct

  • jev-trolley-switch, has a live demo

    Interactive Trolley Problem decision lab powered by Pollinations POST /alpha/decisions and TypeSafe Jev (choice, noul, score) with Bring Your Own Pollen.

    xiaotian1171

    demogithub16 Oct

  • universal-jev

    Universal TypeSafe Jev Runtime Plugin & MCP Server for Coding Agents

    raj8525

    agent-harnessgithub16 Oct

  • jev-bot, has a live demo

    JEV-powered market decision bot for stocks, crypto and memes. State in, BUY/SELL/HOLD/AVOID out, paper by default

    bl888m

    othergithub16 Oct

  • jev-claud

    Decisões tipadas para o código (TypeSafe Jev) e texto livre para pessoas (LLM). Custo zero por padrão.

    thiago-lage

    dev-toolgithub16 Oct

  • is-lesion

    Detect lesions in MRI and medical scans using TypeSafe Jev System One, local OpenJev vision models, and Hugging Face dataset choices.

    hemanth

    demogithub15 Oct

  • system-one-mcp

    MCP server for any System One backend (Ollama nimble/tev/clef, TypeSafe jev, Kev, Laya).

    es11225599

    dev-toolgithub15 Oct

  • jev-tutorial, has a live demo

    Jev (TypeSafe System One) for workflow gates, n8n and design systems: tutorial plus use cases run on real data

    OutThisLife

    demogithub15 Oct

  • decision-models-lab, has a live demo

    Learn decision models by building with them. TypeSafe Jev and Microsoft Decision-1 route support tickets in under a second for about $0.02 per 1,000 calls; Claude handles the hard cases. Interactive site, benchmark, calibration tests and docs.

    shashikantdev3

    guardrailsgithub15 Oct

  • quicksilver

    Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.

    DianeUchida2774

    agent-harnessgithub15 Oct

  • jev-claude

    Decisões tipadas para o código (TypeSafe Jev) e texto livre para pessoas (LLM). Custo zero por padrão.

    thiago-lage

    dev-toolgithub15 Oct

  • ecom-cs-agent

    电商售后客服 Agent：用 TypeSafe Jev 做意图+置信度判断，低置信度自动转人工；含三组对比实验（基于 learn-claude-code）

    guow7394

    agent-harnessgithub15 Oct

  • jev-polymarket-desk, has a live demo

    Shadow-mode Polymarket desk using TypeSafe's Jev as a typed judgment layer

    lazuli111

    agent-harnessgithub15 Oct

  • sensibility

    Give Claude Code a second opinion it can ask for in half a second. Reusable "battery" checks plus optional risk and finish gates, powered by TypeSafe's Jev.

    rajnandan1

    dev-toolgithub15 Oct

  • onboarding-pulse

    Onboarding Pulse: first-90-day attrition radar for People Ops, scored by TypeSafe Jev

    omoniyi-ipaye

    data-pipelinegithub15 Oct

  • jevkit

    TypeSafe Jev as a bounded judgement layer for computer use: verify, pick, classify over Cua Driver and phone-harness

    alexbejan

    guardrailsgithub15 Oct

  • doj, has a live demo

    A turn-based dungeon crawler where every enemy is chosen and played by Jev, TypeSafe's System One model — an example and exploration of what Jev can do.

    ericosg

    demogithub15 Oct

  • jevnatureimage

    Nature Lens: classify nature photos with TypeSafe Jev image models

    JonesSteven

    librarygithub15 Oct

  • minecraft-agent

    A bot that learns to play games by playing them and by watching you play. First game: Minecraft (Voyager-style skill library, Mineflayer, Claude, TypeSafe Jev).

    fthsrbst

    agent-harnessgithub15 Oct

  • decisionlint

    Lint the questions you send to TypeSafe's Jev model: a VS Code extension, a command line for CI and an MCP server for AI agents

    nolindnaidoo

    dev-toolgithub15 Oct

  • pi-ras-compact

    Jev (TypeSafe System One) verbatim compaction for Pi

    rasatpetabit

    dev-toolgithub15 Oct

  • jev-skill-suggestion

    Claude Code mod: TypeSafe Jev picks the one skill each prompt needs, while every skill stays loadable by name (fork of claude-code-templates' jev-skill-suggestion)

    audichuang

    dev-toolgithub15 Oct

  • jev-box-study, has a live demo

    Findings from building an AI-image hallucination detector on TypeSafe Jev 1.14 Box + image input: what worked, what didn't, why

    RINNECODER

    guardrailsgithub15 Oct

  • decisionlint-le

    Lint the questions you send to TypeSafe's Jev model: a VS Code extension, a command line for CI and an MCP server for AI agents

    nolindnaidoo

    dev-toolgithub14 Oct

  • pi-skimmer

    Goal-directed text and JSON filtering for Pi, powered by Jev with explicit consent and recoverable results.

    jon-devlapaz

    data-pipelinegithub14 Oct

  • quicksilver

    Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.

    Myers6198

    agent-harnessgithub14 Oct

  • quicksilver

    Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.

    Bachd22

    dev-toolgithub14 Oct

  • sys1npc

    System One for NPCs — hot-swap scripted NPC decision points with decision models (Jev/TypeSafe, OpenAI Decisions).

    SafiullahRattar

    librarygithub14 Oct

  • open-webui-router-jev-boilerplate

    A simplified, universal boilerplate for an Open WebUI router pipe using pure TypeSafe Jev, with clean minimal code, concise explanations, fast unit tests, sample evals, and an AI agent instructions guide

    foteev

    guardrailsgithub14 Oct

  • judging-with-typesafe

    Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev)

    carlsonchik

    benchmarkgithub14 Oct

  • dsh-jev-advisor

    Jev (TypeSafe System One) gives the human a second opinion, not the agent. When DSH's model asks you a multiple-choice question, dsh-jev-advisor builds a structured Jev request and floats the recommendation, probability spread and confidence beside the options - one click to ado…

    gordan-code

    dev-toolgithub13 Oct

  • system-one-deslop

    Detect and rewrite AI slop with TypeSafe System One judgments

    jomi-se

    guardrailsgithub13 Oct

  • jev-mail-triage

    Dry-run-first Proton Mail Bridge triage using TypeSafe Jev

    soderlind

    guardrailsgithub13 Oct

  • jev-swap, has a live demo

    Find the LLM calls in your codebase that are really decisions, see what they'd save on TypeSafe Jev, and prove it on live traffic before you swap. TypeScript, JavaScript, Python.

    0xjba

    dev-toolgithub13 Oct

  • nifi-jev

    Apache NiFi processor for TypeSafe Jev semantic routing with uncertainty lane

    gbesse

    guardrailsgithub13 Oct

  • zearch

    Perplexity-style open-source UI for TypeSafe Jev: search → evidence state → typed decisions

    zearchcomputer

    agent-harnessgithub13 Oct

  • brightroom-proposal-desk

    BrightRoom proposal desk: client enquiry to feasible draft proposal (Convex, Claude Sonnet, TypeSafe Jev). MSc DSAIB Case 02

    guustgoossens

    demogithub13 Oct

  • jev

    Local CPU-only TypeSafe System One decision service + oh-my-pi plugin

    7n1m4

    guardrailsgithub13 Oct

  • 000

    Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.

    Sajjat4

    demogithub13 Oct

  • astrbot_plugin_jev_active_reply

    Jev主动回复插件 · 作者木有知 · TypeSafe/MindsHub多Key与同人连续补充合并

    muyouzhi6

    agent-harnessgithub13 Oct

  • seo-jev-analyzer, has a live demo

    Measures how closely each page matches its search intent, using the TypeSafe Jev decision model with a calibrated noise band.

    matthelam

    dev-toolgithub13 Oct

  • ai-si-or-whatever

    Choose AI, SI, an alternating preference, or your own name for webpage terminology. Chrome extension with optional TypeSafe Jev.

    SjJ1017

    dev-toolgithub13 Oct

  • typesafe-mcp, has a live demo

    MCP server for TypeSafe AI's Jev: typed yes/no, choice and score answers with act / review / abstain gating.

    MarkChu-git

    librarygithub13 Oct

  • inbox-classifier

    Claude skill: triage a Gmail inbox with the TypeSafe Jev decisions model via OpenRouter

    toml0006

    data-pipelinegithub12 Oct

  • jev-arena

    Jev (TypeSafe) contre Claude Opus 5.5, en direct : trading à la seconde, Tetris, course aux leads, tri d'avis. Docker + ta clé OpenRouter.

    AlanECE

    benchmarkgithub12 Oct

  • gjc-plugin

    Plugins for gajae-code (gjc) — jev-advisor: decision-model tier advisories for subagent task delegation (TypeSafe Jev / OpenRouter / local)

    jjongguet

    agent-harnessgithub12 Oct

  • slidepilot

    Voice-driven semantic auto-advance for Slidev, powered by Cloudflare Agents and TypeSafe AI Jev

    harshil1712

    dev-toolgithub12 Oct

  • ontoken-auto-omp

    Native OMP extension for adaptive OnToken model routing with TypeSafe Jev

    priaculun

    librarygithub12 Oct

  • jev-pilot

    control your desktop smoothly. powered by typesafe's jev.

    amapara27

    agent-harnessgithub12 Oct

  • crosstalk-lab

    Find where an API router confuses look-alike operations, rewrite the wording, and rerun. Runs offline in mock mode; live mode uses TypeSafe's Jev.

    Chaddacus

    benchmarkgithub11 Oct

  • Focus

    Browser extension that blocks distracting websites using TypeSafe: Jev

    bramtechs

    othergithub11 Oct

  • hamazap.github.io

    Deploy self-hosted Laya structured decision models with a TypeSafe Jev API-compatible interface and web UI.

    hamazap

    agent-harnessgithub11 Oct

  • jevshelf

    JevShelf — portable lazy agent skill loading with Skillshare and TypeSafe Jev

    ham-zax

    librarygithub11 Oct

  • jev-skill-suggestion

    Claude Code mod: TypeSafe Jev scores every skill as you type; observe, block or steer skill loading

    ray-amjad

    dev-toolgithub11 Oct

  • jev-apps

    Pipeline failure triage and a customer support router built on TypeSafe AI's Jev model

    mani-bellan

    guardrailsgithub11 Oct

  • tg-crush

    Real-time Telegram conversation analysis with Jev (TypeSafe System One). You write the draft, Jev judges it.

    BrickerP

    demogithub11 Oct

  • claude-jev

    Jev (TypeSafe System One) as a Claude Code plugin: typed decisions for sorting, routing, triage and calibration

    zachshallbetter

    dev-toolgithub11 Oct

  • jevrake

    Selector-free scraping powered by TypeSafe AI's Jev.

    RKasai127

    librarygithub11 Oct

  • StocksSignal

    AI-powered stock signals with Buy, Hold, Sell probabilities and severity scores using Olostep and TypeSafe Jev.

    kingabzpro

    othergithub10 Oct

  • jev-inference-router, has a live demo

    Observable TypeSafe Jev decision routing with local Apple Silicon LLM inference, retrieval, and reproducible evaluations

    sunilmehta-si

    guardrailsgithub10 Oct

  • dsh-jev-zxh

    DSH plugin: expose TypeSafe Jev (System One decision model) as the model-callable jev_decide tool.

    TiChuXiXi

    librarygithub10 Oct

  • piloto-jev

    Piloto mínimo de Jev (TypeSafe AI): triage de tickets con decisiones tipadas, explicado for dummies

    arturo-cobos

    agent-harnessgithub10 Oct

  • app-review-triage, has a live demo

    Claude Code skill: turn app-store reviews into a ranked 'what to fix first' report with TypeSafe's Jev model

    Ying8109

    demogithub10 Oct

  • plan-anchor

    Plan anchoring skill using TypeSafe Jev agent to remove drift

    randlee

    agent-harnessgithub10 Oct

  • jev-playground

    Local playground for TypeSafe System One (Jev): compose Choice/Noul/Score questions in the browser, call the live API, and pull real questions from the arXiv 2609.37647 benchmark (offline)

    Teddy9710

    demogithub9 Oct

  • Codex-Decision, has a live demo

    Local Codex tool-output filtering with OpenAI Decisions by default and optional TypeSafe Jev support.

    PhilippElhaus

    guardrailsgithub9 Oct

  • classifier-skill

    Agent skill that turns many-item judgments (tag, sort, filter, route, triage, score) into typed questions for a fast, cheap non-generative classifier (TypeSafe Jev via OpenRouter, or a local model)

    clark-mackey

    librarygithub9 Oct

  • hn-jev-sorter

    Sort Hacker News comments into buckets in real time with Jev by TypeSafe

    ritza-co

    data-pipelinegithub9 Oct

  • modelrudder

    Experimental local LLM router for OpenAI Codex CLI and Claude Code. Automatically selects models per task using TypeSafe Jev. Free, MIT-licensed, bring your own provider account.

    cybrking

    dev-toolgithub9 Oct

  • ripwire-broker

    Task-oriented, budgeted MCP code context over Ripwire: three tools, hooks for Claude Code and Codex, optional relevance scoring and per-workspace memory via TypeSafe Jev, optional local-model notes

    aquental

    agent-harnessgithub9 Oct

  • ddx, has a live demo

    DDx — Differential: Science-Baked Clinical Differential Diagnosis & Bedside Triage Studio (QMR-DT + Phrank IC + TypeSafe System One + OpenJev Qwen3.5-4B)

    hemanth

    demogithub9 Oct

  • cc-jev-teacher

    Claude Code plugin: TypeSafe-judged hooks that make Claude finish the job before it reports

    masseater

    dev-toolgithub9 Oct

  • sanity-plugin-jev-fields

    Enrich fields in Sanity with an instant feedback utilising the decision model Jev from Typesafe. Show a score to the editors realtime on things like readability, tone, trustworthiness, credibility or anything else.

    frederikvonsperling

    dev-toolgithub9 Oct

  • jev-hooks

    Three Claude Code hooks backed by TypeSafe's Jev: a Bash risk gate, compaction triage that preserves decisions, and verification of subagent reports. Fails open.

    austpryb

    guardrailsgithub9 Oct

  • bing-rewards-automation

    云手机 Bing (Microsoft Rewards) 每日积分任务自动化：纯 adb+Python，规则引擎为主、Jev 单步判别（TypeSafe AI /v1/systemone）兜底，置信度门控

    ljcyt

    othergithub9 Oct

  • jev-radar

    📡 The most rigorously verified tracker of the Jev (TypeSafe AI System One) ecosystem — 1,038 confidence-graded entries (A454·B584) · 136 scans in 24 days, every 3 hours · bilingual EN/中文 · API access guide + key giveaway

    everyinfra

    data-pipelinegithub8 Oct

  • pi-jev-context-filter

    tool result filter with TypeSafe Jev to keep main agent context smaller

    MaxIvanyshen

    librarygithub8 Oct

  • pi-jev-compaction

    better context compaction with TypeSafe Jev judging what to keep

    MaxIvanyshen

    librarygithub8 Oct

  • jev-cleaning-and-tagging

    Messy documents in, tagged library out. Jev scores every file against your taxonomy, Haiku reads the scans, and every tag is written into the file and verified.

    ClehmanGit

    data-pipelinegithub8 Oct

  • model-router

    Claude Code mod: route each subagent to the cheapest Claude model, judged by TypeSafe Jev

    Akurganow

    agent-harnessgithub8 Oct

  • model-router

    Picks the Claude model and reasoning effort for each task with Jev, TypeSafe's System One decision model

    muhx

    guardrailsgithub8 Oct

  • master-jev-hook

    Hooks and MCP that make Claude Code, Claude Desktop and Codex delegate decisions to TypeSafe JEV through a local gateway.

    sophia-phillipa

    agent-harnessgithub8 Oct

  • omarchy-laser

    Laser: AI focus mode & distraction blocker for Omarchy / Hyprland. Judges every screen against your task (TypeSafe Jev), privacy-first, ADHD-friendly, ~1¢/day.

    iYassr

    dev-toolgithub8 Oct

  • Super_Gpt

    SUPER GPT — Desktop control center with Jev Intelligence powered by TypeSafe

    jubarthi

    agent-harnessgithub8 Oct

  • swaraga

    Classify Hindustani and Carnatic ragas from human vocal audio using 12-swarasthana pitch telemetry and TypeSafe System One (Jev) or local OpenJev WASM

    hemanth

    librarygithub7 Oct

  • hunch

    CLI for asking TypeSafe's Jev model yes/no, multiple-choice and scoring questions

    bastiankoetsier

    benchmarkgithub7 Oct

  • desicio-ai, has a live demo

    ⚡ Desicio.ai — Sub-200ms System 1 Decision Engine powered by TypeSafe Jev & Neon Postgres

    saagnik23

    agent-harnessgithub7 Oct

  • keyed_james_bible

    Turn a question into a span of KJV verses, keyed via Jev (TypeSafe System One)

    mccartykim

    librarygithub7 Oct

  • eyedot, has a live demo

    用 Jev（TypeSafe System One 决策模型）把上传的学习材料变成可自动判分的自助考试：逐得分点判定、置信门控、错题本与薄弱点。支持 DeepSeek / 智谱 GLM / 通义千问 / Kimi / OpenAI / Claude 等自带 Key。Self-exam generator and point-level grader built on a decision model.

    Simon-zj1

    othergithub7 Oct

  • Mark58

    Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.

    Sajjat4

    demogithub7 Oct

  • mev-decider

    mev-decider is a 0.4B-parameter System One decision model. It reads a state (text or JSON) and typed questions about it, and returns calibrated probabilities in a single forward pass, with no text generation. The questions use the same format as TypeSafe's Jev

    him4318

    librarygithub7 Oct

  • mappity, has a live demo

    Ask the map anything. Every place answers with a probability. OpenStreetMap + Mapillary + TypeSafe Jev + Cactus Needle.

    kortexa-ai

    librarygithub7 Oct

  • jev-pr-judge, has a live demo

    Typed verdicts on pull requests with TypeSafe System One (Jev): one parallel call, policy in code, usable as a GitHub Action

    juanegido

    dev-toolgithub7 Oct

  • gmail-auto-cleanup

    Triage your Gmail inbox with a System One model (Jev or Laya): typed yes/no judgements, probabilities, and reversible actions.

    nani-stack

    data-pipelinegithub7 Oct

  • competitor-hunter-typesafe

    Competitor Hunter with Jev called directly from the TypeSafe console instead of via OpenRouter. Fork of charlesdove977/competitor-hunter.

    netflyapp

    agent-harnessgithub7 Oct

  • pi-safely

    Claude Code-style auto mode for pi, gated by System One decision models (Cloudflare Clef via OpenRouter, or TypeSafe Jev)

    dcowsill

    agent-harnessgithub7 Oct

  • zsh-jev-suggest

    zsh history autosuggestions ranked by Jev (TypeSafe System One) — instant inline ghost text from a pre-warmed cache, plus a live reranked Ctrl-Space picker

    404priyanshu

    dev-toolgithub6 Oct

  • account-intel-jev-layers

    Stage 4: Jev (TypeSafe) typed judgments: site verdicts with a source check, function/modality chips, posting labels, news.

    NickKostovny

    librarygithub6 Oct

  • jev-gemini

    Turning Gemini Flash on Vertex AI (google-genai SDK) into a fast, calibrated "System One" decision model implementing all three primitives from TypeSafe AI's Jev

    JoaquinMen

    librarygithub6 Oct

  • typesafe-jev

    Code keeps the rules. Jev, a System One model, answers one Choice question per step.

    hoanganh25991

    librarygithub6 Oct

  • omarchy-mail

    Terminal Gmail client for Omarchy. Jev (TypeSafe AI) files your inbox into Gmail labels and checks your replies as you write

    petrzpav

    othergithub6 Oct

  • tg-x-copilot

    Telegram -> X publishing copilot: Jev (TypeSafe) triage, original LLM rewrites, compliant image handling, R2 free-tier storage

    stackoracode

    agent-harnessgithub6 Oct

  • jev-mail

    AI Gmail organizer Chrome/Brave extension: auto-label Gmail, classify emails, and safely bulk-clean junk with undo. Uses your own OpenRouter or TypeSafe key, no server.

    KirtanUgreja

    othergithub6 Oct

  • judgment

    Typed, calibrated judgments from TypeSafe System One models (Jev) and compatible backends: questions with typed handles, validated probabilities, SDK-default retries, differences stated

    chussenot

    librarygithub6 Oct

  • Show HN: Jurl – curl that reads the page for you

    jurl is a CLI. Tell it what you want from a page and it picks exactly that out: the paragraphs that answer a question, the code, the links worth following, or a photo you describe. On Wikipedia's Cologne page it finds the cathedral among 73 images in 2.3 s; on the Jevons pa…

    rayoplateado

    dev-toolhn5 Oct

  • Heliotrope, has a live demo

    Carbon-aware load scheduler: shifts EV charging, water heating, laundry and pumps into the cleanest grid hours without missing a deadline. Next.js + FastAPI + OR-Tools CP-SAT, live weather-based carbon signal, System One decisions, execution tracking.

    StellarieX

    othergithub5 Oct

  • silly-searcher

    Semantic find-in-page Chrome extension. Calls TypeSafe Jev directly with your own API key — no backend.

    smsheik1

    othergithub5 Oct

  • jev-incident-timeline, has a live demo

    Start from one confirmed-malicious process; Jev links the rest of the incident into a reviewable timeline. Browser portal, local portal and CLI.

    tsale

    dev-toolgithub5 Oct

  • typesafe_llm

    Experimental autoregressive text generation using TypeSafe System One Choice evaluations

    mottopanikeiku

    benchmarkgithub5 Oct

  • jev-data-engineering-tribunal

    ⚡ High-throughput Data Engineering decision engine using Jev (TypeSafe AI) for sub-second deterministic pipeline gates and DeepSeek for PySpark remediation.

    nithadya

    data-pipelinegithub5 Oct

  • jev-arena, has a live demo

    Run a Pokémon Champions battle arena locally with Jev, TypeSafe, and Pokémon Showdown.

    neurogabo

    gamegithub5 Oct

  • jevkit

    jev: a Jev (TypeSafe System One) toolkit CLI for coding agents — read less, decide with calibrated confidence. Unofficial.

    bragamat

    dev-toolgithub5 Oct

  • ask-jev

    Ask Jev lets users ask probabilistic questions about the current webpage using TypeSafe's Jev model, with optional user-attached documents as context.

    JoseMiguelHerrera

    demogithub5 Oct

  • criteria-adapter-decision

    Decision adapter (System One decision models: TypeSafe Jev, Ollama /v1/systemone) for the criteria workflow engine

    brokenbots

    agent-harnessgithub5 Oct

  • tdm

    Typed decision model (TDM): Rust core engine + tdmm CLI, napi-rs binding, and harness adapters (opencode / pi / dsh / MCP). First provider: jev (TypeSafe System One); pluggable provider interface reserved for more TDMs.

    Cle2ment

    agent-harnessgithub4 Oct

  • jev-saver

    Local semantic memory in front of TypeSafe Jev: answers repeated decisions on CPU in ~30 ms, asks Jev only when unsure, and remembers the answer.

    ghraibeh

    librarygithub4 Oct

  • jeff-docker, has a live demo

    CPU-first, multi-arch Docker distribution for Jeff (TypeSafe jev-compatible classification API powered by GLiFormer) with GHCR images, Docker Compose and Dokploy support.

    tommasomarchionni

    dev-toolgithub4 Oct

  • jev-mcp

    MCP server + CLI exposing TypeSafe Jev (System One) typed judgments to AI agents

    IIXINGCHEN

    dev-toolgithub4 Oct

  • hydro-jev

    Hydrofoor aansturen met TypeSafe's Jev

    Denbergvanthijs

    librarygithub4 Oct

  • jev-claude-skills, has a live demo

    Unofficial Claude skills for Jev, TypeSafe AI's decision model: SEO internal linking, buyer-intent prospecting, outreach checks, ICP lists, bookkeeping review, claim verification and agent cost-cutting. Node/Python clients, n8n template, tested scripts.

    jlacera

    agent-harnessgithub4 Oct

  • decision-router

    Pick the right LLM for each prompt with a calibrated decision model (TypeSafe Jev). CLI, Claude Code plugin and Pi extension.

    Ruivalim

    guardrailsgithub4 Oct

  • JEV-MODEL-PROJECT

    Jev Model Q&A Prediction and Answer Suggestion Engine using TypeSafe AI System One architecture

    ratn7921

    demogithub4 Oct

  • jev-plays-chess, has a live demo

    Jev, TypeSafe AI's decision model, plays human-like Maia-3 opponents on an Elo ladder

    dmallory42

    demogithub4 Oct

  • jev-effort-router

    Fork of AlphaPerseii3000/jev-effort-router: route Hermes turns via OpenRouter (openrouter/auto + typesafe/jev-router) through TypeSafe Jev

    jdm0830

    agent-harnessgithub4 Oct

  • jev-workflow

    Decision contracts, adversarial testing, tracing, stability, and privacy controls for TypeSafe Jev

    gbesse

    guardrailsgithub4 Oct

  • JEV-AI

    A Python application powered by the TypeSafe SDK (Jev AI model) to automatically categorize incoming customer support tickets and analyze customer urgency levels.

    agrSaket

    data-pipelinegithub4 Oct

  • draftpulse

    Experimental: live X draft viral scorer powered by TypeSafe Jev

    pekth

    demogithub4 Oct

  • quilt-matrix

    The external mind: a spreadsheet-viewable neural network of relational weights. Small cells ask, typesafe answers, a mechanical bot transcribes, the JEV walker thinks, moth entropy rolls the die, and the weights become music.

    SuperInstance

    agent-harnessgithub4 Oct

  • smartvitae, has a live demo

    Plataforma de Adequação Curricular Factual e Alinhamento de Carreira com Zero Alucinação de IA. Combinando TypeSafe JEV (Julgamento cognitivo rápido System One) e Claude 3.5 Sonnet para submeter candidaturas a testes de estresse implacáveis, auditar evidências documentais e elim…

    rafaelleaomed

    othergithub3 Oct

  • pitchpanel, has a live demo

    A panel of five investor archetypes scores your startup pitch. Verdicts, heatmap and versions, on TypeSafe Jev.

    Sahilll15

    demogithub3 Oct

  • Jeffort

    Jeffort: scores each prompt with TypeSafe Jev and sets Claude's effort level, never touching the model

    andrewstephenson-v1

    librarygithub3 Oct

  • jev-agent-kit

    Complete Jev and TypeSafe skill, API documentation, examples, evidence, and email application build brief for Codex

    jbellsolutions

    agent-harnessgithub3 Oct

  • jev-form-fill

    Fill Chrome forms from clipboard text with TypeSafe Jev, reviewed proposals, readback and undo.

    takasek

    dev-toolgithub3 Oct

  • typesafe-jev-1.13

    Web chat with decisions analysis via OpenRouter.

    KiaAgentX

    demogithub3 Oct

  • openkind

    A Jev compatible rust client and custom local model with server. Custom model documented and researched.

    whit3rabbit

    librarygithub3 Oct

  • kd-jev-mcp

    Authenticated MCP gateway to the TypeSafe JEV System One reasoning API, with D1-backed per-user quotas, rate limits, audit logs and OAuth 2.1 connectors.

    ctaxnagomi

    agent-harnessgithub3 Oct

  • docent_chrome_plugin

    A pluign for TypeSafe AI's Jev

    yepher

    dev-toolgithub3 Oct

  • jev-gateway

    Claude API proxy that uses TypeSafe Jev to route, escalate, trim tools and cache - and shows the savings

    mavericksxx

    guardrailsgithub3 Oct

  • jev-browser-wingman

    Browser automation where TypeSafe's Jev model picks each step. Attaches to an existing Chrome via CDP and runs alongside Playwright MCP. Not affiliated with TypeSafe.

    coderexpert123

    agent-harnessgithub3 Oct

  • jev-skills-router

    Fast, cheap AI agent skill routing powered by TypeSafe's Jev — a System One decision model that replaces an LLM call for routing with single-digit-millisecond latency at a fraction of the cost.

    saviooo02

    agent-harnessgithub3 Oct

  • linkscout

    Scores search-result links before you click: browser extension + Cloudflare Worker + Jev

    ianTPE

    othergithub3 Oct

  • plugins

    Plain-English browser QA for Claude Code, judged by TypeSafe's Jev on Cloudflare Workers AI

    c9r-dev

    dev-toolgithub3 Oct

  • jevon

    This is my Jev - TypeSafe AI project from campusx

    dumpydon

    librarygithub3 Oct

  • jev-brand-check

    Streamlit app: check whether a brand is mentioned and recommended in LLM prompt results, using TypeSafe Jev

    chapter42

    benchmarkgithub3 Oct

  • dertek

    Dertek AI - A fast, cost-efficient AI agent for coding and knowledge work. Agentic cli with TypeSafe Jev that uses fewer LLM tokens, lowers LLM cost, and routes tasks to the right model.

    CodesInTheShell

    dev-toolgithub3 Oct

  • ComfyUI-SystemOne

    ComfyUI nodes that branch workflows on natural-language judgments from System One models (local Laya or hosted Jev)

    dante01yoon

    librarygithub3 Oct

  • sortroom

    Self-hosted IMAP mail sorter: a classification model (any TypeSafe API service, e.g. Jev) files new mail into your folders, stars what needs action and tracks expiring offers. Docker image with a web admin UI.

    mhoenes

    data-pipelinegithub2 Oct

  • nu_plugin_jev

    Nushell plugin for TypeSafe Jev structured decisions

    gleb-chipiga

    librarygithub2 Oct

  • jev-trader

    Backtesting US stock strategies with pandas indicators, OpenAI fundamentals and Jev (TypeSafe) decisions

    dnevado

    demogithub2 Oct

  • jev-decisionops

    Production evaluation and gateway tooling for Jev and System One-compatible decision models

    gbesse

    benchmarkgithub2 Oct

  • switchyard

    Every link on the right track in Dia. A menu-bar router that opens links in the right Dia profile, decided by TypeSafe's Jev and learned as local rules.

    kevinebaugh

    dev-toolgithub2 Oct

  • jev-emoji-claude-lesson

    Developer preview: macOS menu bar app that suggests emoji with TypeSafe Jev (Apple Silicon, macOS 14+, not notarized)

    seulkikaang

    demogithub2 Oct

  • jev--system-one-for-claude

    Jev: TypeSafe's System One model as a Claude Code tool. Evidence-backed calibrated odds, typed judgments at scale (classify, search, rerank, score, guard, cite, route, extract), and a corpus → set → run → eval → train loop around fixed weights. Unofficial.

    brookcs3

    dev-toolgithub2 Oct

  • dsh-typesafe-ai-skill

    把 TypeSafe / Jev（System One 判断模型）的构建技能注册进 DeepSeek Harness 的全局技能层，每个会话自动可用。不含任何密钥。 | Registers the TypeSafe/Jev skill into DeepSeek Harness's global skill layer. Ships no API key.

    chen112233usa

    agent-harnessgithub2 Oct

  • jev-questions-skill

    Claude Code skill: designing typed Noul/Choice/Score questions for Jev / TypeSafe System One. Lessons measured while building jevcut.

    VBS2004

    benchmarkgithub2 Oct

  • blind-earth-clef-jev

    Blind-Earth land/water maps with Cloudflare Clef / Clef-flash and TypeSafe Jev (System One choice)

    dylanler

    demogithub2 Oct

  • certradar, has a live demo

    Certificate ticket triage with Jev: finds the cert, reads the ticket, routes or asks the reporter

    mervin008

    guardrailsgithub2 Oct

  • jev-skills

    Jev-powered decision skills for Claude Code and Codex. Opt-in, advisory, fail-open.

    n23eos

    dev-toolgithub2 Oct

  • jev-claude-code

    Jev (TypeSafe's typed yes/no judge) inside Claude Code via OpenRouter: a scored catalog of 983 community integrations, an integration report, and jev_triage, a small hardened MCP server for cheap bulk yes/no screens.

    Axiumine

    agent-harnessgithub2 Oct

  • ollajev

    Run System One decision models from Hugging Face locally behind the Jev / System One API, Ollama style

    nvkudva

    agent-harnessgithub2 Oct

  • jev-observer-public

    A local proxy and dashboard for TypeSafe Jev decisions, with an embedded web UI.

    LimePencil

    dev-toolgithub2 Oct

  • bio-topic-discovery

    DEG/omics and meta-analysis evidence inspection with local Laya or TypeSafe Jev API, reusable Codex skill, auditable coverage, and evaluation charts. Experimental research prototype.

    hpend2373

    dev-toolgithub2 Oct

  • quilt-jev-toolkit

    JEV (TypeSafe) canon oracle toolkit for Quilt

    SuperInstance

    librarygithub2 Oct

  • cot-quilt

    The CoT-decomposition cell: deepseek-v4-pro chain-of-thought -> cellular graph via deepseek-flash + typesafe.ai JEV; mothquantum-certified seeds; the large model judges its own decomposition.

    SuperInstance

    agent-harnessgithub1 Oct

  • mailroom, has a live demo

    Your Gmail, sorted. Rules you can read, typed AI judgments from TypeSafe's Jev for pennies, receipts and undo for everything.

    Kevin-Liu-01

    othergithub1 Oct

  • jev-the-spire2

    An agent plays Slay the Spire 2. Single-call factored decisions via TypeSafe Jev: 15x faster and 259x cheaper than Claude on identical state. Fork of alexmeckes/jev-the-spire (MIT).

    shoemoney

    demogithub1 Oct

  • n8n-nodes-typesafe, has a live demo

    Evaluate content with fast probabilistic checks, classifications, and custom scoring rubrics using TypeSafe AI

    nativeship

    librarygithub1 Oct

  • btx-skill-jev-judge

    Claude Code plugin: hand a judgment repeated over many items to TypeSafe's Jev from a tested script, with redaction, rate limiting and a flat-question check.

    bitranox

    benchmarkgithub1 Oct

  • jev-pii-checker, has a live demo

    CLI that finds PII in text with TypeSafe Jev: presence, sensitivity, and located spans

    coo-quack

    dev-toolgithub1 Oct

  • jarvis-merces

    จาร์วิส เมอร์เซส — ผู้ช่วยเสียงภาษาไทยบน Windows ตัดสินใจด้วย Jev (TypeSafe AI) ตอบไว คุยได้ คุมเครื่องได้

    ctben

    agent-harnessgithub1 Oct

  • olla-jev

    Run System One decision models from Hugging Face locally behind the Jev / System One API, Ollama style

    nvkudva

    agent-harnessgithub1 Oct

  • QuantVault-Jev

    Paper-trading scaffold: brainbrick-trades strategy vault + TypeSafe Jev judgments, with a Streamlit dashboard

    Dento77384

    demogithub1 Oct

  • jev-experiments

    Hands-on experiments with Jev, TypeSafe's System One model, used from coding agents

    uguremrah

    demogithub1 Oct

  • jev-spire-strategist

    Slay the Spire 2 agent: TypeSafe Jev picks each move, a Claude Code session plans the run as strategist

    greenlittleapple

    agent-harnessgithub1 Oct

  • AIDataAgentwithJev

    AI Data Agent for basic Data Engineering and Analytics with Typesafe's new Jev model.

    maskedwolf4

    agent-harnessgithub1 Oct

  • fusion-jev

    Local coding evidence and optional guarded TypeSafe Jev choices for MCP hosts

    Tlkh201313

    librarygithub30 Sep

  • jev-ids, has a live demo

    Blazing-Fast Token-Efficient Intrusion Detection System (IDS) based on TypeSafe's Jev.

    jev-sec

    guardrailsgithub30 Sep

  • jev-focus

    Keep YouTube for focus music and learning while it hides everything else. A Chrome extension that classifies feed videos with TypeSafe Jev. Bring your own key.

    MateusRogien

    othergithub30 Sep

  • dsh-jev-loop

    Jev (TypeSafe System One) judgments at the DeepSeek Harness agent-loop gates. No UI dependency.

    JWE24-code

    agent-harnessgithub30 Sep

  • moqi-jev-loop

    The /JevLoop control panel for moqi, on top of dsh-jev-loop.

    JWE24-code

    agent-harnessgithub30 Sep

  • kost-compass

    Evidence-first, multi-source kost discovery with geospatial ranking and TypeSafe Jev classifiers.

    ramdhanhdy

    data-pipelinegithub30 Sep

  • BizzJev

    Experiments with TypeSafe/Jev semantic gates and a Semantic Operations Lab demo.

    havietkok-sys

    demogithub30 Sep

  • jev-tools

    TypeScript tools built on TypeSafe AI's Jev: an agent tool-call guardrail, a GitHub issue-triage Action, and a bulk classification CLI (npm workspaces monorepo).

    CMaintz

    guardrailsgithub30 Sep

  • Show HN: Jev as the Bletchley Park Analyst: A Software Bombe on Enigma

    Watched a recent youtube veritasium on the enigma machine and was curious on how JEV would do in regards to the analysts calls made at Bletchley's. I rebuilt the historical sequence into the software ux. Results were a mixed, which is what made it interesting. Given the rig…

    ag_21

    demohn30 Sep

  • typesafe-quilts

    System One as judge: calibration battery + routing judgments + the judge protocol for quilt lanes. Live jev-1.13.0.

    SuperInstance

    guardrailsgithub30 Sep

  • system-one-model-gateway

    Gateway in front of TypeSafe's System One API: routes each call to a backend by model, merges calls that share a state, paces upstream traffic and splits usage per caller.

    kaleido-labo

    guardrailsgithub30 Sep

  • Jev_TypeSafe_AI

    Tutorial for TypeSafe AI decision model Jev.

    SystemSolution21

    demogithub30 Sep

  • liuyao, has a live demo

    中国风六爻起卦网站 · 程序排盘 + TypeSafe Jev 语义判断 · 源码公开，禁止商用

    masonweb3

    othergithub30 Sep

  • jev-lite

    Production-grade System One decision engine inspired by TypeSafe AI. Evaluates state and typed questions in a single forward pass with zero generation latency.

    Atulmishra22

    librarygithub30 Sep

  • jev_fsd

    A driving simulator on real OpenStreetMap streets where TypeSafe's Jev model drives the car, with a decision inspector and a benchmark.

    BrendanH18

    benchmarkgithub30 Sep

  • pollinations-idea-judge

    A Pollinations code agent where Jev (typesafe/jev-1.13) decides KILL/FIX/SHIP for an idea and a text model explains.

    Guest453

    agent-harnessgithub30 Sep

  • laya-skill

    Claude Code skill/plugin for System One typed decisions: Laya (local, WebGPU, fine-tune) + TypeSafe Jev

    StevenLi-phoenix

    dev-toolgithub30 Sep

  • slopmop, has a live demo

    Mop the slop out of your LinkedIn feed. Not an AI detector: a bad-writing detector. Chrome extension + Vercel server, powered by Jev from Typesafe AI. MIT.

    tomfrazier

    dev-toolgithub29 Sep

  • BiliBili-Filter

    通过 Quantumult X 重写，使用 TypeSafe Jev 根据标题、简介、分区和标签等元数据过滤 B站推荐。Rewritten using Quantumult X, this tool uses TypeSafe Jev to filter Bilibili recommendations based on metadata such as title, description, category, and tags.

    RzMY

    guardrailsgithub29 Sep

  • jev-voice

    Controle o Chrome por voz: o Chrome transcreve, o Jev (TypeSafe via OpenRouter) decide, a extensão age na página.

    Lucky-Level

    agent-harnessgithub29 Sep

  • btc-jev-signal

    Experimental multi-horizon BTC signal generator using TypeSafe Jev probabilities and Binance market data.

    WebGrga

    othergithub29 Sep

  • jev-playground

    Weekly builds on Jev (TypeSafe AI), benchmarked honestly enough to publish.

    deepdave98

    benchmarkgithub29 Sep

  • jev-Classifier

    VeloCity × Jev: Schadenmeldungen eines Leihradsystems mit TypeSafe Jev (System One) beurteilen – Lehrprojekt THWS, Datenbasierte Fallstudien

    swrobuts

    data-pipelinegithub29 Sep

  • dsh-auto-review-jev

    DeepSeek Harness plugin: per-tool-call Auto-permission review powered by TypeSafe Jev, with account usage and API-key management inline on its settings page

    sperictao

    agent-harnessgithub29 Sep

  • jev-vs-laya-inbox-test

    Test TypeSafe's Jev vs the free open-source Laya on your own inbox. Label, run, fine-tune, score. Works with Claude Code or Codex via AGENTS.md.

    joshpocock

    benchmarkgithub29 Sep

  • zearch, has a live demo

    Perplexity-style open-source UI for TypeSafe Jev: search → evidence state → typed decisions

    brandononchain

    agent-harnessgithub29 Sep

  • jev-mcp

    MCP server for typed decisions with Jev / System One via OpenRouter or TypeSafe

    freepik-company

    agent-harnessgithub28 Sep

  • ComfyUI-ScriptFlow

    Safe Python-like script node with a System One decision model: ask yes/no, choice, and score questions via TypeSafe AI's Jev API, with local GGUF LLMs as a fallback. Multiple inputs and outputs let one node handle math, logic, text editing, conditional routing, resolution select…

    kantan-kanto

    librarygithub28 Sep

  • hand

    Voice agent in the MacBook notch that controls your Mac, powered by TypeSafe's Jev

    arjun-354

    agent-harnessgithub28 Sep

  • Show HN: Onesie – An expressive CLI for System One models like Jev

    onesie is a Unix-style CLI for using System One models in shell pipelines, scripts, and agentic workflows: https://github.com/frodi-karlsson/onesie echo 'EVERYTHING IS DOWN, CALL ME NOW' | onesie 'does this convey urgency' -r # 0.99 It pro…

    frodikarlsson

    dev-toolhn28 Sep

  • jevkit

    Policy + evaluation framework for Jev / Kev (TypeSafe System One): typed probabilities in, auditable actions out — calibration, budget-compiled thresholds, permutation & drift checks. Zero-dependency core, kev-native.

    JasmineAIGC

    guardrailsgithub28 Sep

  • heihua-translator

    职场黑话翻译器：贴一句工作消息，先猜，再揭晓 AI 怎么读 + 它有多确定。基于 Jev（TypeSafe System One）的判断工具，含 30 句真实语料评测。

    casperkwok

    benchmarkgithub28 Sep

  • speedy-jev

    My new browser extension (building in progress...): A fast, lightweight browser extension that sends the selected text (or the whole page) to Jev by TypeSafe AI and shows the typed answers in the popup. Bring your own API key.

    onlineeric

    othergithub28 Sep

  • jev-skill

    A skill that teaches your coding agent to use Jev (TypeSafe's decision model), measured on real work: rules, costs, tested question sets, mistakes.

    marcodicesare-dev

    benchmarkgithub28 Sep

  • jev-pi

    Jev for pi: TypeSafe System One judgments in the agent loop — permission gate, output ladder, conditional context, agent router (pi package: extension + skills + prompts)

    weiping

    guardrailsgithub28 Sep

  • Decis

    Self-hosted, Jev-compatible decision-model API — one /v1/systemone endpoint, open weights (Laya, kev), one Docker image per engine.

    chaitin

    agent-harnessgithub28 Sep

  • hermes-teaching-decision-plugin

    Teaching Decision Layer for Hermes education profiles using TypeSafe Jev

    hfm77788

    librarygithub28 Sep

  • langgraph-jev-router

    A native LangGraph conditional edge that replaces slow generative LLMs with TypeSafe AI's deterministic System One model (`Jev`). It enables ultra-fast (sub-500ms), schema-safe routing between specialized agents.

    JTankariya

    agent-harnessgithub28 Sep

  • jev_decide

    Ask Jev (TypeSafe System One) for calibrated decisions — stdin-JSON CLI helper plus an OpenCode jev_decide tool, with agent-facing docs.

    auxon

    dev-toolgithub27 Sep

  • kev-onnx

    Self-hosted, TypeSafe-compatible /v1/systemone API server for the KEV decision model - CPU-only ONNX inference via FastAPI, no GPU required.

    aleskxyz

    othergithub27 Sep

  • HA-Crop-Steering-Jev

    Crop Steering, Jev edition: the HA crop-steering engine with TypeSafe Jev judging every decision across P0-P3, probes, shots, salt and alerts, inside a deterministic safety envelope.

    JakeTheRabbit

    agent-harnessgithub27 Sep

  • jev-cli

    Jev's TypeSafe judgment model, exposed via OpenRouter, as MCP tools

    pyck-ai

    dev-toolgithub27 Sep

  • typesafe-mcp

    TypeSafe System One dispatch pipeline as a ZCode plugin: typed subagent routing (Battery #1), deterministic thresholds, destructive-op guard, usage ledger

    cyrusasco

    agent-harnessgithub27 Sep

  • hev

    Android client for TypeSafe Jev System One — structured choice with probabilities and confidence.

    tozetsu

    othergithub27 Sep

  • verdict, has a live demo

    Perplexity-style open-source UI for TypeSafe Jev: search → evidence state → typed decisions

    brandononchain

    agent-harnessgithub27 Sep

  • jevk5-typesafe-server

    TypeSafe-compatible System One API server backed by JevK5 on llama-server

    Code2qing

    librarygithub27 Sep

  • jev-watch

    Watchdog for AI coding agents: stops Codex/OpenCode when they loop, stall or drift off task, then resumes the same session with a correction. Built for Claude Code orchestrators. Uses Jev via OpenRouter.

    polaminggkub-debug

    agent-harnessgithub27 Sep

  • mobile-jev

    Automate real Android tasks on live phones with Jev, Mobilerun, and TypeSafe—no ADB needed.

    Capitalofgeorgiapolitician1569

    agent-harnessgithub27 Sep

  • jev-engineering, has a live demo

    Jev use cases that ship. review-router: a GitHub Action that tells your AI code reviewer when to read the whole PR. It caught 13 of 13 CVE fixes a path rule missed. Plus a tool-call safety gate, inbox triage, AI-writing detection and more.

    eugeniughelbur

    guardrailsgithub27 Sep

  • fab-evidence-gate

    Evidence-aware semiconductor alert triage research demo with TypeSafe Jev, policy guards, and reproducible evaluation

    hongdroid94

    demogithub27 Sep

  • jevbrief

    Clean, traceable state briefings for TypeSafe's Jev model

    Parthkomalwad

    dev-toolgithub27 Sep

  • fastgate-jev

    Jev (TypeSafe AI) as a System One decision layer for a multilingual EN/UZ/RU RAG helpdesk, with an independent benchmark

    rajantripathi

    guardrailsgithub27 Sep

  • jev-realtime-trading

    Paper trading agents on a live tape, decided every second by TypeSafe's Jev (System One). Electron desktop app.

    rthomas24

    agent-harnessgithub27 Sep

  • fast-jev-opencode

    OpenCode v1 + v2 plugin: prune stale tool calls and truncate bulky tool results from the outgoing request using TypeSafe Jev decisions (verbatim compaction, no summarization).

    roshan-shaik-ml

    librarygithub27 Sep

  • jev-hermes-router

    Escolhe o modelo certo pra cada mensagem no Hermes, usando o Jev da TypeSafe. Codex e Claude via assinatura.

    okjpg

    agent-harnessgithub27 Sep

  • jev-mail-filter

    Gmail filters written in plain English, judged by Jev (TypeSafe)

    ziyacivan

    guardrailsgithub27 Sep

  • jev-gmail-classifier

    Google Apps Script that classifies Gmail messages with Jev, TypeSafe's decision-only AI model. Runs on a time-driven trigger, sends each email's sender, subject, and trimmed body to Jev (via TypeSafe, OpenRouter, or Vercel AI Gateway), and applies Gmail labels based on typed Cho…

    kellystuard

    data-pipelinegithub27 Sep

  • Verdict

    A local System One server for your Mac: open decision models on MLX, compatible with the System One API (TypeSafe Jev).

    TobyNoSkillSon

    dev-toolgithub26 Sep

  • Jev-AI-Model

    Hands-on repository for **Jev**, the groundbreaking "System One" model created by **TypeSafe AI**

    Jithin-jith

    othergithub26 Sep

  • jev-ercot

    Texas retail electric plan shopper: Power to Choose corpus, Jev (TypeSafe System One) classifier, Next.js app

    cdubiel08

    demogithub26 Sep

  • jev-pi-model-router

    pi extension: TypeSafe Jev picks the model for each turn, only from models pi can use

    damian87x

    guardrailsgithub26 Sep

  • jev-pi-skills

    pi extension: TypeSafe Jev decisions as tools (search, rerank, supervise, pick) and hooks (skill select, compaction)

    damian87x

    librarygithub26 Sep

  • jev-switch

    A fast, local-first gateway for aggregating and routing TypeSafe Jev model endpoints | 一款快速、本地优先的网关，用于聚合与路由 TypeSafe Jev 模型入口

    ARCJ137442

    dev-toolgithub26 Sep

  • pi-jev-thinking

    pi extension: TypeSafe Jev picks the thinking level for each prompt

    lancejohnson

    librarygithub26 Sep

  • jev-browser-use

    Fast browser QA from Claude Code or pi: TypeSafe Jev picks every click via Jev Ultrafast, you supply text and the pass check.

    damian87x

    dev-toolgithub26 Sep

  • jev-tactics

    Perception par vision et decision tactique confiee a Jev (TypeSafe AI) sur un combat isometrique au tour par tour. Recherche.

    Stephane-Dedu

    demogithub26 Sep

  • herdr-jev-auto-compaction

    Auto-compact Claude Code sessions when a task finishes, not when context fills up. Jev judges task completion; Herdr types /compact.

    jpwinans

    agent-harnessgithub26 Sep

  • jev-decide

    System One decision layer for browser automation: offload page-state judgments to TypeSafe Jev — element picks, challenge detection, routing. ~1s, ~$0.001/decision.

    abdullahaamuda-code

    agent-harnessgithub26 Sep

  • typesafe-eval

    Fast, typed multi-dimensional document evaluation CLI powered by TypeSafe System One (Jev).

    s-0-a-r

    benchmarkgithub26 Sep

  • jevemu

    Open emulator of TypeSafe's Jev API on open models, plus a paired benchmark of local and hosted models against Jev

    sinkarusa

    benchmarkgithub26 Sep

  • jeva, has a live demo

    A 2B browser-agent decision model. Speaks the TypeSafe System One protocol, so jev-ultrafast is repointed with one line. Answers do not move with the page title or the form layout. 100% on the action suite.

    chemany

    agent-harnessgithub26 Sep

  • okx-jev-desk

    Multi-bot crypto trading desk. Jev (TypeSafe System One) as the brain, TypeScript as the body, Next.js as the glass. OKX v5 venue.

    AtticusG3

    agent-harnessgithub26 Sep

  • kit-jev, has a live demo

    Kit gratuito para probar Jev (TypeSafe) con tus datos: clasificador, test de indexación, las pruebas del vídeo y habilidad para Claude Code. Por Centry.

    contacto939

    demogithub26 Sep

  • agent-skills

    Agent Skills (SKILL.md) for Claude Code, Codex & ZCode: fast browser automation with TypeSafe Jev, cross-model code review, pre-writing coach, Xiaohongshu/WeChat article to Markdown

    sageri

    dev-toolgithub26 Sep

  • sf-early-learning-mcp

    Model Context Protocol (MCP) server & OpenCode skill for San Francisco Early Learning For All (ELFA) preschool search, voucher calculations, and TypeSafe Jev System One evaluation

    pmerlin1

    dev-toolgithub26 Sep

  • jev-gmail-filter

    Filter Gmail with plain-English topics, powered by jevfilter and TypeSafe's Jev.

    damiensmith1

    dev-toolgithub26 Sep

  • jev-discord-bot

    Discord bot for TypeSafe's Jev (System One): /jev choice, score and noul

    glennwiz

    othergithub26 Sep

  • jev-dsh

    System One (TypeSafe Jev) decision tool for DeepSeek Harness — bounded choice / noul / score judgments as an agent tool + skill.

    ZhengSJCode

    agent-harnessgithub26 Sep

  • trialscout

    TrialScout (trialscout.cc) reads a patient's plain-language profile, checks it against every eligibility criterion of recruiting solid-tumour oncology trials on ClinicalTrials.gov using TypeSafe AI's Jev, and shows which trials are worth raising with a doctor. Each criterion is…

    tushar-im

    othergithub26 Sep

  • opencode-jev-plugin

    TypeSafe Jev System One decision and aggressive token-saving plugin for OpenCode and OmO

    fsodanogm2dev

    dev-toolgithub26 Sep

  • claude-jev

    Jev System One for Claude Code — typed Choice/Noul/Score via live TypeSafe API (mirror of opencode-openjev, live-only MCP)

    darwintechlab

    agent-harnessgithub26 Sep

  • JEV_ADK

    Agent Development Kit for System-One AI: Sub-100ms non-autoregressive decision pipelines, guardrails, and dual-brain agent orchestrator powered by TypeSafe AI's Jev

    abyakod

    agent-harnessgithub26 Sep

  • jev-game-engine

    Observable Rust AI game engine with latency-aware Jev goals, local execution, and a native UI. Minecraft Java prototype.

    King4s

    gamegithub26 Sep

  • jev-mcp

    MCP stdio servers for TypeSafe Jev typed judgments and a separate local Laya-MLX decision model

    nik1tsyganov

    dev-toolgithub26 Sep

  • jev-bot

    Control native Mac apps from Codex or ChatGPT via persistent JavaScript with element numbers or TypeSafe descriptions.

    sandracam64

    agent-harnessgithub26 Sep

  • jev-pi-token-reduction

    Pi extension that uses TypeSafe's Jev to trim retrieved tool output before the model sees it (~15% lower cost on read-heavy work)

    auschoi96

    librarygithub26 Sep

  • jev-effort

    Per-turn reasoning effort for coding agents, classified by TypeSafe's Jev via AI SDK (Vercel AI Gateway / OpenRouter / TypeSafe). Claude Code plugin; Codex, Cursor, Amp next.

    pc-style

    benchmarkgithub26 Sep

  • jev-riffs

    Music pattern ripper: MIDI → interval tokens → code mines candidate motifs → Jev (TypeSafe System One) grades their significance. Web UI with piano roll, click-to-play, WAV export.

    hazlema

    dev-toolgithub25 Sep

  • system-one-connector

    System One MCP connector to evaluate anything fast and cheap. Give your AI agent direct access to models like: Typesafe AI's Jev model and Laya

    itsmostafa

    librarygithub25 Sep

  • jevguard-mcp, has a live demo

    Official Model Context Protocol (MCP) server for JevGuard and TypeSafe AI

    seb4ez

    guardrailsgithub25 Sep

  • jev-media-bridge

    Local-first image and video evidence bridge for TypeSafe Jev / System One

    yashkhou

    dev-toolgithub25 Sep

  • claude-x-jev

    Fast, cheap, typed decisions for Claude Code. Jev (TypeSafe's decision model on OpenRouter) sorts, checks, scores, gates and verifies at 0.3s and a fraction of a cent per item. Claude keeps the reading, writing and judgment.

    charlesdove977

    guardrailsgithub25 Sep

  • quicksilver

    Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.

    UditAkhourii

    agent-harnessgithub25 Sep

  • Jevstiller, has a live demo

    Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.

    tomerglick57

    dev-toolgithub25 Sep

  • gremlins-ai-agent

    Powered by TypeSafe Jev: an experimental AI player for Gremlins, Inc., with a BepInEx bridge and Python agent.

    caiweike

    gamegithub25 Sep

  • firstlight

    Early warning for Irish brand impersonation, read from public Certificate Transparency logs. Built on Jev (TypeSafe AI) - a decision-only model returning calibrated probabilities.

    Kandarp-Joshi-007

    guardrailsgithub25 Sep

  • social-credit

    The Party watches you work. A joke productivity monitor and a real field test of Jev (TypeSafe System One).

    cayman2142

    benchmarkgithub25 Sep

  • adecider

    Typed System One decisions for any coding agent: one call, many typed questions, calibrated probabilities instead of prose, pluggable backends (local Laya, TypeSafe Jev, any OpenAI-compatible)

    Agents365-ai

    agent-harnessgithub25 Sep

  • jev-ios-bridge

    Bridge that lets Claude Code verify an iOS app on a simulator, with TypeSafe's Jev choosing each step (planning stage)

    hugues-vnsgn

    agent-harnessgithub25 Sep

  • sooth

    Verify AI-generated text against source material. Claim-by-claim PASS/FAIL/REVIEW verdicts with calibrated probabilities, powered by Jev.

    naufalhilmiaji

    benchmarkgithub25 Sep

  • jev-trading-arena, has a live demo

    TypeSafe Jev 판단으로 한국·미국 주식을 모의 매매하고 전략별 수익률을 겨루는 백테스트·랭킹 서비스

    SungHoonKim-Ski

    benchmarkgithub25 Sep

  • agent-model-router

    Experimental TypeSafe Jev model routing for Codex, with Claude Code shadow recommendations.

    starhn87

    agent-harnessgithub25 Sep

  • Jev

    PowerShell decisions with TypeSafe AI's Jev model: https://typesafe.ai/blog/introducing-system-one-models-and-jev

    dfinke

    demogithub25 Sep

  • krino

    Krino (κρίνω) — probing, analysis, and replication toolkit for JEV-class decision models

    Oaklight

    benchmarkgithub25 Sep

  • jev-decision-gateway

    Governed decision-model gateway: TypeSafe Jev vs GPT-6 Sol vs rules on 100 withdrawals

    kartikanand73

    benchmarkgithub25 Sep

  • jev-compact

    Prune-not-summarise context compaction for Claude Code, guided by Jev (TypeSafe System One)

    HAR5HA-7663

    dev-toolgithub24 Sep

  • pi-ask-jeff

    An advisor called Jeff for pi: calibrated decisions via ask_jeff, backed by the Jev-compatible System One API (OpenRouter / TypeSafe / jev-agent)

    a-chris

    agent-harnessgithub24 Sep

  • Jev-Trades

    Trading bot with the all new TypeSafe AI's first system one model named as Jev

    zadescoxp

    othergithub24 Sep

  • openjev

    OpenJev: An Opencode plugin that replaces text-generation decisions with Jev (TypeSafe System One).

    darwintechlab

    librarygithub24 Sep

  • jev-mcp

    Servidor MCP que expõe o Jev (TypeSafe System One) como ferramenta de julgamento tipado para agentes: Noul, Choice e Score com validação por regra.

    tmbmartell

    agent-harnessgithub24 Sep

  • jev-skills

    Practical agent skills and examples for building with Jev. API setup, routing, ranking, and evidence checks.

    laguagu

    demogithub24 Sep

  • jev-send-check

    A bilingual pre-send message checker with communication goals, tone analysis, and A/B comparisons, powered by TypeSafe Jev.

    WeiS49

    dev-toolgithub24 Sep

  • jev-mcp

    Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.

    jkudish

    dev-toolgithub24 Sep

  • jev-receipt-country-classifier

    Experimental receipt country classification with Typesafe Jev and OCR, evaluated on multilingual text and image datasets from Hugging Face.

    Kripta-Studios

    data-pipelinegithub24 Sep

  • Intel-Phi-Jev

    XKEYSCORE for Jev: TypeSafe System One judgments (noul/choice/score) served locally, with the Xeon Phi cards doing the model's matrix work

    Lasimeri

    demogithub24 Sep

  • Mechanical-Jev

    TypeSafe's Jev (System One: noul, choice, score) from Rust: client library, mjev CLI, evaluation harness. Client side only.

    Lasimeri

    librarygithub24 Sep

  • usejev

    Run Laya locally with Bun: native ONNX inference, a TypeSafe-compatible API, and a bilingual decision playground.

    ali-master

    demogithub24 Sep

  • conduit

    Loopback gateway for Claude Code or OpenCode: automatic Anthropic → GLM → DeepSeek failover, breaker-driven, plus optional per-call model routing by Jev (TypeSafe System One) — capability-first across all three providers — with manual pinning, control UI and CLI

    pmagnomuller

    agent-harnessgithub24 Sep

  • open-jev-bridge

    MCP plugin to connect jev-like system one API (local hosted or typesafe jev) to codex and claude code for decision tasks like compaction, verification judgement, etc.

    louis-szeto

    dev-toolgithub24 Sep

  • omp-jev-toolkit

    Jev (TypeSafe System One) judgments for omp: verbatim context compaction, a tool-result block sieve with recall, and a walker-based file finder

    BingChanCN

    dev-toolgithub24 Sep

  • jev-dojo

    Jev（TypeSafe AI の System One モデル）を級・段で学ぶハンズオン教材。APIキーなしで動くサンプルとテスト付き / Hands-on course for Jev (TypeSafe AI's System One model), in Japanese and English

    kenmori

    demogithub24 Sep

  • obsidian-jev-inbox-router

    Obsidian plugin: route incoming notes to the right folder using JEV (TypeSafe System One) typed decisions. It never writes your content — it only decides where it belongs.

    liyifan2004

    guardrailsgithub24 Sep

  • snap, has a live demo

    Typed decisions from unstructured state: one forward pass, zero generated text. Local, deterministic, Jev-compatible. Not affiliated with typesafe.ai.

    emnlmn

    librarygithub24 Sep

  • linkedin-ai-slop

    LinkedIn feed AI-slop detector using TypeSafe Jev API

    pawelmamcarz

    guardrailsgithub24 Sep

  • nextwork-jev-inbox-autopilot

    Build an inbox autopilot in n8n that sorts Gmail with Jev and only acts when it's confident. NextWork project starter.

    Nik-1019

    agent-harnessgithub24 Sep

  • jev-go, has a live demo

    Can you beat Jev at Gomoku, Go or chess? Play TypeSafe's System One decision model on Cloudflare Pages, with every API call shown, a hall of fame and replays.

    beingcognitive

    gamegithub24 Sep

  • jev-skills

    Jev (TypeSafe System One) skill and CLI for coding agents: when to use typed semantic decisions and how to invoke them

    milojarow

    dev-toolgithub24 Sep

  • agent-workflow-typesafe-ai

    jev typesafe-ai implementation to enhance pure deterministic decisions and other modeling

    ngallodev-software

    librarygithub24 Sep

  • laya-server

    A self-hosted API and web interface for Laya’s structured decision models, compatible with the TypeSafe Jev API format.

    1Panel-dev

    dev-toolgithub24 Sep

  • astra-jev-new-vegas

    An experimental Astra + Typesafe Jev Fallout: New Vegas project: read-only game observations, typed decisions, recording, and public commentary.

    0mis

    agent-harnessgithub24 Sep

  • jev-model-router

    Claude Code skill that uses Jev (TypeSafe System One) to route tasks to the best Claude model — Opus, Sonnet, Haiku, or Fable — by capability, cost, and latency.

    griteshs6-boop

    agent-harnessgithub23 Sep

  • tavli, has a live demo

    Tavli (Greek backgammon) played against Jev, TypeSafe's System One decision model. Includes a tutorial on building with typed decision models.

    DimisCodes

    gamegithub23 Sep

  • Trchx

    Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.

    Sajjat4

    agent-harnessgithub23 Sep

  • jev-exam

    用 Jev（TypeSafe System One 决策模型）把上传的学习材料变成可自动判分的自助考试：逐得分点判定、置信门控、错题本与薄弱点。Self-exam generator and point-level grader built on a decision model.

    Simon-zj1

    dev-toolgithub23 Sep

  • jev-echo

    Echo: a 22k-parameter model distilled from TypeSafe's Jev. Same Snake board, ~1,000x faster.

    Adamya05

    gamegithub23 Sep

  • PoC-BetterContext

    JEV x APM progressive-context PoC: TypeSafe System One progressively materializes/dematerializes APM rules and skills

    pangelini777

    demogithub23 Sep

  • ai-decision-engine

    Give your agents typed AI decisions instead of parsing LLM text. Jev (TypeSafe) classifier with confidence-gated routing + regex baseline benchmark.

    sergio-lim

    guardrailsgithub23 Sep

  • jevskillz

    Calibrated TypeSafe Jev confidence checks for every step of coding with Claude Code — brainstorm, research, write, test, verify, triage

    calelamb

    guardrailsgithub23 Sep

  • jev-claw

    Typed model routing for OpenClaw agents, powered by TypeSafe Jev

    trietphan

    librarygithub23 Sep

  • jev_router

    Standalone TypeSafe Jev-based auto-routing for Agent Zero

    twilso24

    agent-harnessgithub23 Sep

  • jevcraft

    Autonomous adaptive Minecraft bot: Jev (TypeSafe System One) decides fast, an LLM plans, designs and talks. mineflayer.

    nthclrd

    agent-harnessgithub23 Sep

  • masroufi

    Expense tracking for Gaza households, built around bank statement exports and their note field. Uses Jev (TypeSafe System One) for typed, confidence-aware transaction categorisation.

    wafaa-alhayek

    othergithub23 Sep

  • Show HN: Sniffslop – browser extension to classify text using Jev

    A browser extension to let you define any question to ask in a webpage. I default it to identify AI written texts. It extract texts element under cursor send to Jev for classification. It comes with all the caveats of Jev. Its classification is in no way an objective truth. Use…

    a_c

    demohn23 Sep

  • typesafe-jev-decision-studio

    Fast, calibrated System One decision platform powered by TypeSafe Jev via OpenRouter

    Romain-Jochum

    agent-harnessgithub23 Sep

  • Jev-api-experiments

    Empirical experiments and API research for TypeSafe's Jev System One model trained using RLCD

    BipinRajC

    demogithub23 Sep

  • n8n-nodes-typesafe-jev

    n8n community node for TypeSafe Jev structured AI decisions

    n3ndor

    librarygithub23 Sep

  • jev-pilot

    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).

    Akramovic1

    dev-toolgithub23 Sep

  • jev-claim-processor

    Insurance claim triage console using TypeSafe AI's Jev model, with rule-based fallback, policy rules, tests and CI/CD

    akhilkoduriak

    guardrailsgithub23 Sep

  • slopmark

    Chrome extension that subtly marks obviously AI-written text on web pages, scored by TypeSafe Jev

    phareim

    othergithub23 Sep

  • gute-kaese, has a live demo

    Type anything. Jev decides in ~0.4s whether it's Gute Käse. A gut call, no explanation.

    JonnyFi

    gamegithub23 Sep

  • jev-clipboard

    macOS clipboard history and context-aware Smart Paste powered by TypeSafe Jev.

    Daniel-Goatman

    othergithub23 Sep

  • jev-opus

    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.

    WXK-AI

    dev-toolgithub23 Sep

  • jev-dj-router

    Learning TypeSafe AI's Jev evaluation model fast by building a /play request router for a DJ chatbot

    panchicore

    demogithub23 Sep

  • jevkit-core

    Shared Python infrastructure for the JevKit tools

    keltokhy

    librarygithub23 Sep

  • jev-suite

    Four decision-quality tools on Jev (TypeSafe System One): Jev answers structured questions, deterministic code keeps the final say.

    klauswg

    dev-toolgithub23 Sep

  • obsidian-smart-tagger

    ⚡ High-speed, zero-hallucination System-1 intelligent tagging assistant for Obsidian powered by TypeSafe Jev

    xinye1017

    dev-toolgithub23 Sep

  • clean-code-review, has a live demo

    Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.

    frostney

    dev-toolgithub23 Sep

  • claude-router

    Claude Code plugin that auto-picks the right model for each turn — micro, low, medium, or high tier — using Jev routing.

    alexei-led

    guardrailsgithub23 Sep

  • jev-skill

    Agent skill: decide when and how to integrate TypeSafe's Jev decision model (OpenRouter, TypeSafe, Vercel AI SDK, harness patterns, calibration). Claude Code plugin + npx skills.

    KHAEntertainment

    agent-harnessgithub23 Sep

  • kime-compat

    The compatibility harness for kime. The TypeSafe (Jev) API and SDKs, jev-ultrafast and Laya's own clients and tests, run against kime so that drop in replacement is a number rather than a promise.

    tamnd

    benchmarkgithub23 Sep

  • jev-mcp-server

    MCP server for Jev (TypeSafe System One): the three official question types — choice, score, noul — plus batch classify. Calibrated probabilities, ~0.5s, <$0.001/call.

    wangkuangkuang

    agent-harnessgithub23 Sep

  • jev-effort-router

    Per-turn model AND reasoning-effort routing for Hermes Agent on Ollama:Cloud, decided by TypeSafe Jev (a System One decision model, not an LLM). Rewrites the outgoing provider request itself via llm_request middleware. Ollama:Cloud only.

    AlphaPerseii3000

    guardrailsgithub23 Sep

  • dsh-jev-plugin

    Ask Jev (TypeSafe System One) typed questions from DeepSeek Harness: batch judgements with probabilities, configured per user in Settings.

    RaulLazaro

    benchmarkgithub23 Sep

  • magnum-opus

    Adaptive reasoning effort for Claude Opus 5.5 in Oh My Pi, decided per generation by a TypeSafe System One model.

    mja00

    agent-harnessgithub23 Sep

  • typesafe-tutorial

    Notebooks built while learning TypeSafe AI's System One model Jev

    rickysullivan

    demogithub23 Sep

  • jev-tmmluplus-eval

    Evaluate TypeSafe AI's Jev (System One Model) on TMMLU+ v1.1 — four-way choice via the API's own response schema, 100% parse rate by construction

    lianghsun

    benchmarkgithub23 Sep

  • stuntd

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

    bladedevoff

    dev-toolgithub23 Sep

  • jev-snake

    Snake autoplay powered by TypeSafe Jev (System One)

    lalitsonawane

    gamegithub23 Sep

  • jev-mcp, has a live demo

    MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

    rashedInt32

    dev-toolgithub23 Sep

  • jev-chat-moderator, has a live demo

    Playground: TypeSafe AI's Jev moderating a simulated live-stream chat in real time (ES/EN)

    vstrofago

    demogithub23 Sep

  • agent-one, has a live demo

    A browser agent that books a flight from one sentence. TypeSafe Jev makes every bounded decision; a small text model only writes strings; code does the clicking. 12.88s end to end, 4s of it thinking.

    saikumardeepak1

    demogithub23 Sep

  • jev-browser

    Browser use using Typesafe's Jev model

    jkudish

    agent-harnessgithub23 Sep

  • I built a linter/skill that ensures requests to jev are structured correctly

    i built wellposed as a plugin&#x2F;skill which works with any agent (https:&#x2F;&#x2F;github.com&#x2F;suraj-phanindra&#x2F;wellposed) to ensure your agent understands how to choose the right kind of jev request and format it correctly not just for syntax but for completeness an…

    suraj_phanindra

    dev-toolhn22 Sep

  • n8n-nodes-jev-router

    n8n community node for TypeSafe AI's Jev System One decision model

    guptadivyanshu765

    guardrailsgithub22 Sep

  • jev-mcp

    MCP server for TypeSafe Jev (System One): one typed evaluate tool over streamable HTTP

    darthzen

    dev-toolgithub22 Sep

  • resolve

    Automated resolution infrastructure API for long-tail prediction markets (Cloudflare Workers + Supabase + TypeSafe Jev)

    rafaemush

    othergithub22 Sep

  • jev-router

    Per-turn model and reasoning-effort routing for Hermes Agent, decided by TypeSafe Jev (a System One decision model, not an LLM).

    AlphaPerseii3000

    agent-harnessgithub22 Sep

  • jev-guardrails

    Comparing LLM-as-judge vs TypeSafe Jev for agent guardrails: same rules, same agent, measured on cost, latency, calibration and coverage.

    deepansh-saxena

    benchmarkgithub22 Sep

  • TurboSlop

    Machine-made, human-judged. Jev decides the design, an LLM writes the copy, an image model illustrates it — and code ships the page in about a second for a tenth of a cent. Typed decisions with calibrated confidence, not vibes.

    mojomast

    demogithub22 Sep

  • TibiaJevBot

    An autonomous game-playing decision engine for Tibia (Open Tibia / OTServ) powered by TypeSafe AI's Jev System One model.

    GabrielBigardi

    agent-harnessgithub22 Sep

  • karnak

    Jev picks Claude Code's reasoning effort before every step. Low for routine, high when recovering.

    kjmagnan1s

    dev-toolgithub22 Sep

  • dsh-wsl-jev

    DeepSeek Harness WSL plugin: TypeSafe Jev / OpenRouter System One (jev_ask / check / rank)

    173787247

    agent-harnessgithub22 Sep

  • skillfeed

    Skill-ranked tech feed powered by TypeSafe Jev (System One) — not autoregressive generation

    iikareem

    othergithub22 Sep

  • llav

    Typed semantic decisions from a local open model, served over an HTTP API shaped like TypeSafe's System One API

    wistrand

    librarygithub22 Sep

  • jevelry

    A runtime for Jev, TypeSafe's System One model: jevels in, verdicts out

    backant-io

    guardrailsgithub22 Sep

  • werr, has a live demo

    Zero-memory System-1 decision engine & TypeSafe Jev wire-compatible runtime powered by Mandelbrot wave dynamics (JevBench #1).

    pCwOrM

    librarygithub22 Sep

  • foreman, has a live demo

    Software factory foreman based on TypeSafe's Jev model

    thruwire

    agent-harnessgithub22 Sep

  • llm-typesafe

    LLM plugin for accessing Jev and other TypeSafe AI models

    simonw

    librarygithub22 Sep

  • HearthstoneLegendArriver

    基于 TypeSafe Jev 1.13 多维决策矩阵与游戏内内存发包的《炉石传说》酒馆战棋全自动无感助手

    fusei1008

    agent-harnessgithub22 Sep

  • jev-gateway, has a live demo

    TypeSafe Jev API gateway with official SDK compatibility and a simple ask endpoint, built for Vercel.

    FreeJolan

    agent-harnessgithub22 Sep

  • laya-server

    Run Laya behind the TypeSafe System One API: a local, drop-in endpoint for Jev clients. Docker (CPU, CUDA, ROCm) or native Windows on a Radeon.

    noahbclarkson

    agent-harnessgithub22 Sep

  • mcp-jev

    Minimal MCP wrapper for TypeSafe Jev. Structured yes/no, choice, and score decisions. Docker-ready. Unofficial project.

    Chrishow2

    librarygithub22 Sep

  • pi-smart-router

    A Pi coding-agent extension that routes each prompt to the best backend model — cheap, fast, balanced, or powerful — using local heuristics, with optional TypeSafe Jev classification.

    jordilopez

    guardrailsgithub22 Sep

  • jevseek

    DeepSeek proposes the next token, TypeSafe's Jev chooses it: a decision model used as a sampler

    blingdivinity

    librarygithub22 Sep

  • jevlery

    A runtime for Jev, TypeSafe's System One model: jevels in, verdicts out

    backant-io

    agent-harnessgithub22 Sep

  • pi-ext-model-router

    pi.dev extension to select models using TypeSafe Jev

    phamhongviet

    librarygithub22 Sep

  • hermes-jev-adaptive-effort

    Cache-safe adaptive reasoning effort for Hermes, selected by TypeSafe Jev through OpenRouter

    kirkins

    agent-harnessgithub22 Sep

  • Prompt-Router

    Prompt-Router: lightning-fast LLM gateway with a telemetry dashboard for coding agents (Goose, Cursor, Claude Code, VS Code) and enterprise pipelines. Why pay frontier prices for trivial lookups? TypeSafe Jev System One sorts each prompt in under 120ms and sends it to the right…

    robinwintertaylor

    agent-harnessgithub22 Sep

  • jev-linkedin-slop-filter

    Slams a BAIT, CORP or BRAG stamp onto LinkedIn engagement-bait, judged live by Jev (TypeSafe System One).

    Arpit-Khandelwal

    guardrailsgithub22 Sep

  • Show HN: Jevopt: Making intelligent compiler optimisation decisions with Jev

    Can Jev optimise the size of compiled binaries better than clang -Oz? Turns out it can (sometimes)! Introducing jevopt: making intelligent compiler optimisation decisions with Jev. I used Jev to make intelligent inlining decisions at each LLVM IR call-site. Here’s why and how I…

    ramneet_singh

    dev-toolhn22 Sep

  • elmridge-ai-town

    three.js AI town simulation: day/night economy, jobs, citizens — MCP server for AI control + TypeSafe Jev (System One) decision layer on OpenRouter

    nikkoxgonzales

    gamegithub22 Sep

  • jevgram

    Can Jev (TypeSafe System One) do what Pangram does? 7,139 texts from RAID, HC3 and MAGE, one typed question each, $0.97.

    sksq96

    benchmarkgithub22 Sep

  • pi-jev-multi-provider

    Pi Jev System One integration with TypeSafe Direct and Vercel AI Gateway transports

    0x1f

    librarygithub22 Sep

  • jevDemo

    AI-native Android UI test runner using TypeSafe/Jev + Appium

    ChubbyOtter

    demogithub22 Sep

  • jev-mcp

    Unofficial stdio MCP client for TypeSafe Jev. Bring your own API key.

    jfrader

    dev-toolgithub22 Sep

  • openjev-mcp

    MCP server exposing TypeSafe's Jev through the public OpenJEV API. Send one shared context and several independent questions; get typed judgments and probabilities back — choice, score, or yes/no — not prose. Built for DeepSeek Harness; runs unchanged in any MCP client.

    markylaredo

    dev-toolgithub22 Sep

  • commander-oracle

    Buy/Hold/Sell outlook for new Magic: The Gathering cards, driven by Commander demand. Price history + EDHREC + TypeSafe Jev judgments.

    kitapplegate

    data-pipelinegithub22 Sep

  • jev-voice

    Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.

    kevinbadi

    demogithub22 Sep

  • jev-qq-assist

    基于 Jev 的 QQ 聊天决策辅助 · On-device QQ chat decision assistant built on Jev typed-decision idea

    1104480426-hash

    demogithub22 Sep

  • decisions-judge-mcp

    Typed decisions for AI agents as an MCP tool: yes/no probability (noul), choice, and score in one fast request. Backed by the TypeSafe System One model.

    clouatre-labs

    dev-toolgithub21 Sep

  • spark-jev-email-triage

    Email triage app built around Spark CLI and TypeSafe Jev. Early development: TanStack Start, React and TypeScript; email integration is not implemented yet.

    WesleySmits

    othergithub21 Sep

  • jev-browse

    Browser automation with Jev (TypeSafe) as decision model

    0x7067

    agent-harnessgithub21 Sep

  • jevsume

    ATS-friendly resume review powered by Jev (TypeSafe System One). The frontend extracts resume text the way a parser would, then a Cloudflare Worker runs typed JEV questions and composes a JevScore.

    unownone

    dev-toolgithub21 Sep

  • jev

    CLI and MCP server for TypeSafe's Jev model, built for scripts, agents, and automation.

    gnapse

    dev-toolgithub21 Sep

  • tink-route

    Dynamic, confidence-aware Agent Skill routing with TypeSafe Jev and Tink

    jon-devlapaz

    agent-harnessgithub21 Sep

  • jev-the-janitor

    A janitor for markdown vaults powered by TypeSafe Jev: Jev votes on each note, your code files it, you review the low-confidence pile.

    kylehovance-ai

    data-pipelinegithub21 Sep

  • judgevet

    Typed client, CLI and MCP server for TypeSafe's Jev (System One) judgment model

    Alberto-Codes

    librarygithub21 Sep

  • jev-judge

    Jev CLI for the jev-judge Claude/Codex skill. Wraps the official @typesafe-ai/sdk.

    nickwinder

    dev-toolgithub21 Sep

  • jev-codex-router

    Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.

    0xNatoshi

    agent-harnessgithub21 Sep

  • jev-minesweeper

    Minesweeper played by TypeSafe's Jev System One model: one P(mine) per hidden cell per move, code owns the policy.

    dbssman

    gamegithub21 Sep

  • ticket-rerank

    FastAPI service that reranks support tickets by urgency using TypeSafe (Jev / System One)

    Obrais-cloud

    data-pipelinegithub21 Sep

  • HA-Jev

    Ask your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automations, and a conversation agent for Assist.

    AboveColin

    librarygithub21 Sep

  • typesafe-mcp

    MCP server exposing TypeSafe (Jev/System One) to the fleet: judge, rerank, systemone

    Obrais-cloud

    agent-harnessgithub21 Sep

  • hermes-slash-router

    Unified Hermes Agent + Desktop plugin: TypeSafe Jev routes misspelled, shortened, and meaning-based slash commands to real ones. Advisory memory, fresh Jev decision every time.

    raitoxlol

    guardrailsgithub21 Sep

  • clash-jev, has a live demo

    A Clash Royale bot with no trained policy: Jev (TypeSafe System One) makes every decision from the live game state

    Atikpui007

    gamegithub21 Sep

  • JevPalette, has a live demo

    TypeSafe JEV Color Guesser with Closed Beta Gate & Vercel deployment

    diluteoxygen

    gamegithub21 Sep

  • jev-is-not-odd

    A probabilistic, AI-powered utility to determine if a number is not odd (or not even) using TypeSafe's Jev model and the Vercel AI SDK.

    ItzSupra13

    demogithub21 Sep

  • jev-table-tennis

    Table tennis vs. TypeSafe's Jev (System One). Every paddle move on the right is a live model decision — no local prediction, just a lookup table and a servo.

    LiuHao-1443

    demogithub21 Sep

  • local-jev

    A local, offline System One server compatible with TypeSafe's Jev API. It answers typed yes/no, category and score questions with small open models.

    amithgc

    dev-toolgithub21 Sep

  • jev-toolkit

    MCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server (jev mcp) serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana.

    jbt95

    agent-harnessgithub21 Sep

  • jev-factorio-agent

    Jev picks what, code owns how - a System One Factorio agent driven by TypeSafe's Jev on FLE

    CompleteDotTech

    agent-harnessgithub21 Sep

  • fotocopiatrice, has a live demo

    Emendamenti alla manovra letti uno per uno: fotocopie, firmatari, esiti. Dati Camera dei deputati, analisi TypeSafe Jev.

    bnistor4

    data-pipelinegithub21 Sep

  • jev-vs-llm-ticket-router

    Benchmark: TypeSafe Jev vs traditional LLM on support-ticket routing accuracy, latency, and cost

    SarathChandraBellam

    benchmarkgithub21 Sep

  • jev-mcp

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

    tphakala

    dev-toolgithub21 Sep

  • jev-fastloop

    Cheap fail-open semantic edge layer for Jev (TypeSafe System One): decision service + confidence policy + decision logging + blind eval harness + skill router over 1,000+ skills. Stdlib-only Python.

    SupremeDreamZ

    guardrailsgithub21 Sep

  • harness-drift-detector

    Fast drift hotspotting for coding-agent harness transcripts, scored with TypeSafe System One judgments behind a provider port

    SongTonyLi

    benchmarkgithub21 Sep

  • open-spark-jev

    Open-source, local decision models inspired by TypeSafe’s Jev and System One - built on Qwen3 for NVIDIA DGX Spark.

    abhishek085

    othergithub21 Sep

  • jev-mcp-spring

    Java/Spring Boot MCP server for TypeSafe Jev

    Ashfaqbs

    librarygithub21 Sep

  • jev-spec, has a live demo

    ⚡ Specification-Driven Semantic Verification Engine for AI Code & Specs powered by TypeSafe AI Jev

    nozomi-koborinai

    dev-toolgithub21 Sep

  • jev-ecosystem-sim

    A 2D grid-island ecosystem where each animal is a Jev (TypeSafe) agent; the food chain emerges from calibrated typed decisions. Pure-stdlib Python + browser UI.

    emipasca

    gamegithub21 Sep

  • hermes-and-jev-play-minecraft

    Hermes Agent plans, Jev (TypeSafe) picks bounded actions, Mineflayer executes: Minecraft with no screenshots or keypresses from a model. Includes the reproduction of rmalde/minecraft-agent's Ender Dragon run.

    teknium1

    demogithub21 Sep

  • snake-jev

    Un Snake en canvas que se juega solo: el modelo Jev de TypeSafe elige cada movimiento y el código tiene la última palabra.

    paulovillarroel

    gamegithub21 Sep

  • filit

    Tiny open-source smart paste for macOS, powered by TypeSafe / Jev

    AR-1106

    othergithub21 Sep

  • jev-decision-maker

    omp plugin: JEV (TypeSafe System One) picks the next coding step from agent-supplied candidates

    hoaphm

    dev-toolgithub20 Sep

  • jev-resume-disqualifier

    Jev Resume Disqualifier: Sub-25ms automated resume knockout engine powered by TypeSafe Jev System One decision intelligence. Eliminates 80% of unqualified applicants with deterministic date math & EEOC-safe rejection notices.

    AiPersonacademy

    data-pipelinegithub20 Sep

  • jev-judge-mcp

    MCP server exposing TypeSafe's Jev as a judge tool: typed judgments with calibrated probabilities, for any MCP client.

    gecm0

    dev-toolgithub20 Sep

  • rjif

    jif: calibrated if-statements in R via TypeSafe Jev — judgment-based control flow with reliability curves for biostatistics

    doublerobust

    librarygithub20 Sep

  • home-assistant-typesafe

    Home Assistant conversation integration powered by the Jev / TypeSafe AI API for fast, structured intent routing and device control

    allenporter

    agent-harnessgithub20 Sep

  • typesafe-jev-mcp, has a live demo

    MCP server exposing TypeSafe's Jev model as a typed evaluate tool — structured answers with probabilities, not prose.

    anasbekheit

    librarygithub20 Sep

  • jev-crypto-scout

    Crypto screening: quant signals in code (CoinGecko), news judgment via Jev (TypeSafe System One) — sentiment/catalyst/confirmed, not a trading bot

    yasdelayu

    data-pipelinegithub20 Sep

  • jev-router.nvim

    An intent router for Neovim that classifies AI commands with Jev (TypeSafe's System One model) via the OpenRouter Decisions API, then routes execution to the matching handler.

    Mawfyy

    guardrailsgithub20 Sep

  • cartas-ciberseguridad-jev, has a live demo

    Puntuar currículums de ciberseguridad con JEV, el modelo System One de TypeSafe, sobre Cloudflare Workers. Clasificación contra NICE, ECSF y SFIA, con cada número trazable hasta la pregunta que lo produjo.

    noelserdna

    data-pipelinegithub20 Sep

  • jevlergy

    Evaluating TypeSafe's System One model Jev through camera-based food allergen estimation (Flutter, iOS/Android)

    daisuke7

    demogithub20 Sep

  • dsh-plugin-jev

    TypeSafe Jev (System One decision model) as a native jev_decide tool plugin for DeepSeek Harness

    kaijia323

    librarygithub20 Sep

  • jev-outlook-organizer

    Self-hosted Outlook organization with TypeSafe Jev, custom categories, scoped Microsoft 365 access, and guided setup

    Taveren7

    othergithub20 Sep

  • laya-jev-compatible-server

    A TypeSafe Jev-compatible HTTP server (POST /v1/systemone)

    exfly

    librarygithub20 Sep

  • jev-agent-toolkit

    Jev-first portable Agent Skill and optional MCP bridge for Claude Code, Codex, Cursor and compatible agents.

    reiswaffel78

    librarygithub20 Sep

  • openfront-agent

    A local OpenFront agent using TypeSafe Jev for bounded gameplay decisions.

    mogottsch

    agent-harnessgithub20 Sep

  • pi-jev

    Claude-style auto-mode classifier for Pi, powered by TypeSafe Jev

    JohnsonRan

    agent-harnessgithub20 Sep

  • gentle-shell-jev

    Public Gentle Shell fork exploring an optional TypeSafe/JEV context-anticipation integration

    jorgehara

    librarygithub20 Sep

  • rev

    Fast, prefill-only decision model. Typed questions in, calibrated probabilities out, single forward pass with TypeSafe System One API. inspired from jev

    jaswanthsanjay88

    librarygithub20 Sep

  • oido-systemone

    Local, drop-in server for TypeSafe's System One API (POST /v1/systemone). Runs MiniCPM5-2B or Qwen3.5-4B in-process via Kronk/llama.cpp, on GPU or CPU. One Go binary, no Docker. Yes/no, choice an score answers from a single forward pass. Swagger, Prometheus metrics, rate limitin…

    Djancyp

    agent-harnessgithub20 Sep

  • alp-pr-review

    ALP-linje: PR-review med Jev-routing (TypeSafe System One) og automerge bag port

    pksorensen

    demogithub20 Sep

  • typesafe-jev

    sahibinden ilanlarini tarayicida yakalayip TypeSafe (Jev) ile eleyen yerel arac — emlak ve vasita icin ayri soru setleri, karar akisi gosterimi

    ismailakdag

    data-pipelinegithub20 Sep

  • jev-codex-bridge

    Model and reasoning routing for Codex Desktop and CLI, with a Windows service and validated updates

    ansidium

    dev-toolgithub20 Sep

  • diff-risk-sentinel

    Risk triage for large git diffs (CRAP + TypeSafe Jev) and a repository-wide dead-code scan for Python and JS/TS

    heliowap

    dev-toolgithub20 Sep

  • jev-pacman

    Pac-Man decision environment for TypeSafe's Jev (System One) model

    Schweik7

    benchmarkgithub20 Sep

  • omause

    Silent Omarchy voice control powered by TypeSafe Jev: voice command in, visible Omarchy action out.

    devfros

    librarygithub20 Sep

  • jev-llm, has a live demo

    An LLM built without a language model — using TypeSafe Jev's non-generative AI for contextual response selection. Zero hallucination. Zero prompt injection.

    akash-kamat

    demogithub20 Sep

  • jevskill

    Teach your coding agent to stop burning context. Jev (System One) decisions for 325ms + 0.000013 USD: classify, route, triage, and cut huge logs before they hit your LLM. Saves 74-96% of harness context. Portable Skill for Claude Code, Codex, DSH.

    lazniak

    guardrailsgithub20 Sep

  • jev-dev-kit

    Framework for agents on TypeSafe Jev: turns candidates into valid Jev questions and answers into validated choices; loop, cross-checks, fallbacks and traces built in. No network code.

    chy4pro

    agent-harnessgithub20 Sep

  • jevcore

    TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

    PerryLink

    librarygithub20 Sep

  • OpenJev

    Open-weight System One model (Jev-compatible): calibrated noul / choice / score decisions in one forward pass, no text generation. Works with TypeSafe's typesafe-sdk unchanged.

    GitHub30

    librarygithub20 Sep

  • jev-voice-control

    Control your Mac by voice. Speech → Jev (TypeSafe AI System One model) typed decisions → macOS actions. Menu-bar Swift app.

    chris-wozniczek

    othergithub20 Sep

  • jev-usecases

    Jev (TypeSafe AI's System One decision model) use-case catalog: real-world builds, cost math, design patterns, and a reality check on vendor claims.

    vamsikrishna2421

    demogithub20 Sep

  • jev-cms

    On-demand Jev (TypeSafe System One) question catalog for CMS-style content — classify, gate, and judge your own content by id.

    EmilianoVeron

    benchmarkgithub20 Sep

  • jev-mail

    Autonomous 24/7 Zero-Inbox triage for Gmail powered by TypeSafe Jev System One

    vynnlee

    agent-harnessgithub20 Sep

  • remember-me

    Agent memory that decides what to hydrate — local topology recall + TypeSafe Jev gates (not another dump-everything store).

    leonininder

    agent-harnessgithub20 Sep

  • jev-resume-screening

    TypeSafe Jev (System One) 简历-JD 匹配度初筛：判据模板 + 正/负/陷阱三类样本测试档案，判据 v1→v3 迭代全程可复现 / Resume-JD screening with TypeSafe Jev: atomic questions, calibrated criteria v1→v3, full reproducible test archive

    nanami-0713

    benchmarkgithub20 Sep

  • jevkit-py

    jevkit for Python: static linter and shared record format for building on TypeSafe's Jev (System One) model. Unofficial.

    pjdurden

    librarygithub20 Sep

  • JevPip

    GMOのFX/BTC市場データに対応したローカル市場研究ターミナル。ライブチャート、ペーパートレード、バックテスト、安全監督、TypeSafe Jev連携。安全機構を整えたうえで実売買対応予定。

    yo4e

    othergithub20 Sep

  • jevtail

    Nothing to read: a message only when your app is actually broken, with what kind of problem it is. Log and alert triage powered by TypeSafe Jev.

    jevtail

    dev-toolgithub20 Sep

  • jsort

    sort by meaning: order lines along a plain-English dimension, from pairwise comparisons judged by TypeSafe's Jev model

    keltokhy

    librarygithub20 Sep

  • jevkit-js

    jevkit for JavaScript/TypeScript: static linter and shared record format for building on TypeSafe's Jev (System One) model. Unofficial.

    pjdurden

    librarygithub20 Sep

  • hermes-jev

    Typed System One decisions, ranking, verification, and an opt-in Hermes tool gate using TypeSafe Jev.

    keeltrace

    guardrailsgithub19 Sep

  • larp-detector

    Real-time LinkedIn LARP detector — names the persona being performed as you scroll. Chrome MV3 extension powered by Jev (TypeSafe System One).

    sxeptical

    othergithub19 Sep

  • easynest_v2

    Industrial 2D irregular nesting engine with Superposition concurrency and TypeSafe Jev System One AI intelligence

    ghiffarsabda

    librarygithub19 Sep

  • yuru-poll

    Loose polling: free-text comments become fractional votes via TypeSafe Jev (System One)

    hiroyannnn

    data-pipelinegithub19 Sep

  • jevcode, has a live demo

    JevCode — Jev (TypeSafe System One) 技术解决方案与最佳实践 · https://www.jevcode.ai

    miounet11

    othergithub19 Sep

  • story-arc

    Visualize a character's journey through a story using TypeSafe System One

    amali-s

    demogithub19 Sep

  • chartroom

    A local second brain built on GBrain, with TypeSafe Jev for search ranking and page connections.

    MayberryDT

    othergithub19 Sep

  • judgement

    A Go CLI for TypeSafe Jev judgments, with JSON input/output and optional caching

    2389-research

    dev-toolgithub19 Sep

  • dealscout

    Jev-powered deal search engine with a chat frontend — semantic matching + offer eligibility by TypeSafe's Jev, all the money in plain code.

    shivprime94

    othergithub19 Sep

  • typesafe-ai-php

    TypeSafe AI PHP SDK

    sanmai

    librarygithub19 Sep

  • jev-mail-classifier

    Classify your inbox with Jev (TypeSafe's System One model) — tag, move, flag, and notify, all config-driven.

    parth-kp

    data-pipelinegithub19 Sep

  • jeffrey

    A coding agent CLI where Jev (TypeSafe System One) decides what to do next and a configurable LLM does the work.

    thomasbrueggemann

    agent-harnessgithub19 Sep

  • jev-testbed

    Jev (TypeSafe System One) 테스트베드 — 클라우드 API와 로컬 셀프호스팅(jeff/GLiFormer) 양쪽 실행 예제 및 실측 결과

    hulryung

    benchmarkgithub19 Sep

  • hermes-plugin-jev

    Jev (TypeSafe AI) System One decision engine plugin for Hermes Agent, backed by Agnes AI Flash.

    Mrmimee

    agent-harnessgithub19 Sep

  • x-jev-classifier

    Chrome extension that stamps every X post with a type badge — alpha, shitpost, AI slop, bait — judged by Jev from Typesafe

    rolottr

    othergithub19 Sep

  • fable-jev

    ⚡ Sub-100ms cognitive reflexes for autonomous coding agents. Powered by TypeSafe AI's Jev & get-fable.

    imMamdouhaboammar

    agent-harnessgithub19 Sep

  • typo3-webcon-jev

    Typed decisions from TypeSafe AI's Jev model inside TYPO3: a decision editor and playground in the backend, powermail_cond operators, and submission routing

    dirnbauer

    dev-toolgithub19 Sep

  • jev-use

    Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — ~200 ms, ~$0.00004 per judgment

    shitianfang

    agent-harnessgithub19 Sep

  • jev-voice

    Multi-dimensional writing voice profiler powered by Jev (TypeSafe AI)

    vcjdeboer

    librarygithub19 Sep

  • jev_bitcoin_backtest

    A reproducible backtest of whether TypeSafe Jev can forecast BTC/USD and produce a tradable edge after fees, slippage, and holdout validation.

    egrm07

    benchmarkgithub19 Sep

  • fast-jev-compaction

    Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.

    tamaratran

    dev-toolgithub19 Sep

  • jev-mine-sweeping

    用 TypeSafe Jev（System One）驱动扫雷自动通关：HTML 扫雷页每走一步实时问模型，并把它的选项、概率、代码已证明的事实全部可视化。Play Minesweeper with TypeSafe Jev (System One): an HTML game that asks the model every move and visualises its options, probabilities and the facts the code proved.

    sxinyuhoo

    demogithub19 Sep

  • pi-jev-typesafe

    TypeSafe Jev (System One judgments) for Pi: zero-dependency jev_ask tool with question linting, model discovery, and budget caps

    nardinmarcus

    librarygithub19 Sep

  • jev-skill

    Agent skill for TypeSafe Jev (System One) typed judgments

    toorop

    librarygithub19 Sep

  • omp-jev-decision

    omp extension: a read-tier `decision` tool backed by TypeSafe System One (Jev) — typed choice/noul/score questions over any state, answered with probabilities and token cost

    iAziz786

    librarygithub19 Sep

  • systemone-lite

    Toy local System One–style decision API (Jev-shaped). Not affiliated with TypeSafe.

    fritzprix

    librarygithub19 Sep

  • canvas-quiz-ai-solver

    High-performance Canvas LMS quiz assistant & scraper designed for TypeSafe AI System One decision primitives

    Bigthap

    othergithub19 Sep

  • n8n-nodes-jev, has a live demo

    Helper n8n community node for Jev by TypeSafe. Classify, route, and score text with questions you define, and get a probability for every answer so unsure items can go to review.

    vibe-with-me-tools

    data-pipelinegithub19 Sep

  • pi-jev-skill-suggestion

    Pi extension that removes the inlined skill list and asks TypeSafe Jev which skill to load

    iamdin

    dev-toolgithub19 Sep

  • jev-projects

    7 projects built with TypeSafe Jev — dev tools and games

    Faiziahmad

    demogithub19 Sep

  • jev-panerelay

    Ultra-fast browser automation using TypeSafe Jev via Panerelay and OpenRouter.

    hdkiller

    agent-harnessgithub19 Sep

  • trading-bot-jev

    Crypto trading bot on Binance testnet using TypeSafe (Jev) to judge news

    Spykoninho

    demogithub19 Sep

  • jev-feed-filter

    Smart, dynamic AI filtering for X and YouTube feeds using Jev

    makefinks

    guardrailsgithub19 Sep

  • fast-jev-compaction-alt

    Continuous, verbatim context compaction for LLM agents using TypeSafe's Jev model.

    cassiomc1

    agent-harnessgithub19 Sep

  • jev-control-room, has a live demo

    A visual control room for typed AI evaluations, structured decision-making, and confidence-aware policy gating using Vercel AI SDK and TypeSafe Jev.

    thisisjorge

    guardrailsgithub19 Sep

  • jev-playground

    Playground for TypeSafe AI's Jev decision model: provider-agnostic AI SDK scripts, jev-filter CLI, GitHub pruner

    realdubb

    demogithub19 Sep

  • Jevs-Garage

    A garage full of tiny experiments for building critical systems with System One & Jev 🔧🧠⚡

    JGalego

    demogithub19 Sep

  • Show HN: Sokit – a LangChain like harness for Jev (or other System 1 models)

    Full disclosure, it was coded with AI, I don&#x27;t claim otherwise. But I wanted to test out tool calls and iterative problem solving using Jev and needed a simple library&#x2F;framework&#x2F;harness to do that. SOKIT (System One Knowledge, Instructions and Tools) is the result…

    phantomCupcake

    agent-harnesshn19 Sep

  • skillranker

    Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.

    Dicklesworthstone

    agent-harnessgithub19 Sep

  • jev-search, has a live demo

    Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.

    superagents-lab

    dev-toolgithub19 Sep

  • jev4j

    Java 21 client for Jev, TypeSafe's structured decision model

    kcb-swe-gh

    librarygithub19 Sep

  • typesafe-sdk-swift

    typesafe-sdk-js and typesafe-sdk-python port for swift

    marandaneto

    librarygithub19 Sep

  • verdict

    ocaml sdk for typesafe.ai's jev model

    jonesmelton

    librarygithub19 Sep

  • ibmi-jev

    Ask your Db2 for i tables questions. A Db2 for i SQL SDK powered by TypeSafe's Jev.

    ajshedivy

    librarygithub19 Sep

  • typesafe-sdk-go

    Idiomatic, strongly-typed Go client SDK for the TypeSafe AI System One API (v0.6.0)

    orcawhisperer

    librarygithub19 Sep

  • typesafeai-dotnet-sdk, has a live demo

    Community .NET SDK for the TypeSafe AI System One API — typed noul, choice, and score questions with structured, confidence-scored answers. Not affiliated with TypeSafe AI.

    saibimajdi

    librarygithub19 Sep