A FIELD GUIDE TO JEV / VOL. 01
Le meilleur de Jev : projets concrets, guides pratiques et idées du web.
TypeSafe AI@typesafeaiOFFICIALTypeSafe announces public access to Jev without a waiting list. The official console is the starting point for trying typed decisions in your own application.
x.comJev opens to everyoneVoir le projet ↗TypeSafe AI@typesafeaiOFFICIALTypeSafe’s official launch announcement introduces the lab and points builders to Jev. It includes Diogo Almeida’s launch film and original introduction.
Diogo Almeida@CompleteSkepticLAUNCH POSTDiogo Almeida introduces Jev, TypeSafe’s structured decision model. Watch the launch film and explore the original thread for the model’s approach, examples and author-reported performance.
TypeSafe AI@typesafeaiOFFICIALTypeSafe highlights Jev’s typed-output approach: applications provide state and questions, then act on probabilities, choices or scores. The linked announcement also covers the Venice API integration.
x.comAnswers your code can useVoir le projet ↗Four official signals. A fresh starting point on each visit.
714 ressources
AI-assisted summaries and translations. Check original sources for context and performance claims.
发明 RLHF 的人，这次做了个不会说话的模型：Jev 独立研究报告。52 页 PDF + 50 条中文实测复现包 + 143 条可回溯数据表.
github.comHackSing/jev-reportVoir le projet ↗Source-linked curation
Ruby client for typesafe.ai.
github.comjoshmn/typesafe-sdkVoir le projet ↗Source-linked curation
Hunch is a GitHub tool for code review that applies rules written in plain English to analyze and improve code quality.
Source-linked curation
Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers.
github.commateonunez/jodVoir le projet ↗Source-linked curation
用 TypeSafe Jev 推荐已安装 Skill / Bounded installed-skill recommendations with TypeSafe Jev. Python CLI, Codex skill, bilingual docs and live examples.
github.comwin4r/jev-skill-suggesterVoir le projet ↗Source-linked curation
A GitHub project developing a screen overlay to identify manipulative interface patterns.
github.comzohaib-md/UXRayVoir le projet ↗Source-linked curation
A developer project for automatic context clearing in Pi without losing conversation history.
Source-linked curation
One-pass option scoring with a local Gemma 3 4B on Apple silicon via MLX, inspired by jevlike, with a Doom demo.
github.comdaseinlabs/open-jevVoir le projet ↗Source-linked curation
An agent system that makes one Jev decision per computational step.
Source-linked curation
TypeScript browser agent for ego lite: Jev Ultrafast indexed actions, TypeSafe Jev decisions, persistent observe/act CLI. No Chrome or Playwright.
github.comromaluev/jev-egoVoir le projet ↗Source-linked curation
PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.
github.comanpicasso/hermes-jev-approvalsVoir le projet ↗Source-linked curation
A project comparing Jev's performance against chat models in analyzing Fed press conferences.
Source-linked curation
A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.
github.compithings/advocaatVoir le projet ↗Source-linked curation
Pydantic AI capabilities made stronger with Jev: small runnable demos, one file each.
github.comadtyavrdhn/pydantic-jev-examplesVoir le projet ↗Source-linked curation
Per-call GPT model routing for Codex: Jev chooses model and effort, a local Responses proxy keeps the tool loop intact, then independent verification and Router Compass check whether the task still passed.
github.comminiLV/Jev-Auto-RouterVoir le projet ↗Source-linked curation
Go client for TypeSafe's System One API and its model Jev: typed judgments and calibrated probabilities instead of generated text.
github.comGaurav-Gosain/jev-goVoir le projet ↗Source-linked curation
Let Jev (TypeSafeAI) solve 2048.
github.comKyleKreuter/jev2048Voir le projet ↗Source-linked curation
Arbiter provides a tool to serve custom decision models through a Jev-shaped API, allowing developers to create tailored decision-making systems.
github.com0xBakeer/arbiterVoir le projet ↗Source-linked curation
Screen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring.
github.comgtaras7/typesafe-jevVoir le projet ↗Source-linked curation
在 X 的时间线上，给每条帖子标出它想让你干什么。判断来自 Jev，一个只返回概率、不生成文本的模型。
github.commanifoldor/xtagsVoir le projet ↗Source-linked curation
River shooter game in Python, inspired by Atari's River Raid, played by a TypeSafe AI pilot.
github.comashaazami/river-run-typesafeVoir le projet ↗Source-linked curation
A deterministic model routing system for coding agents with a skill for Codex.
Source-linked curation
Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.
github.com0xArx/jevegisVoir le projet ↗Source-linked curation
JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.
github.comfstandhartinger/jevbenchVoir le projet ↗Source-linked curation
FUn little experiment with Typesafe AI Jev Model playing chess against stockfish :).
github.comDimesio/typesafe-chessVoir le projet ↗Source-linked curation
Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes.
github.comButochnikov/laravel-typesafe-jevVoir le projet ↗Source-linked curation
Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code.
github.comsorrycc/typesafe-snakeVoir le projet ↗Source-linked curation
I kept watching coding agents burn context on decisions that aren't hard - triage 400 tickets, tag 600 files, route to one of six teams. jev-mode moves those verdicts to a typed-judgment model. I A/B'd it: 78% fewer tokens, 16x less work-attributable input, accuracy 96.1% vs 93.7%. Python, no deps, MIT.
github.comddfeyes/jev-modeVoir le projet ↗Source-linked curation
GitHub Action for issue triage that abstains: label, spam, needs-info and duplicate in one call, each applied only above a threshold you set, and nothing at all below it.
github.comemreozyoruk/hushVoir le projet ↗Source-linked curation
A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.
github.comolanotolu/jevbetterVoir le projet ↗Source-linked curation
Unofficial go sdk for typesafe ai.
github.comatharvamhaske/typesafe-sdk-goVoir le projet ↗Source-linked curation
A flexible and configurable CLI model router using TypeSafe Jev.
github.commarcus/frostVoir le projet ↗Source-linked curation
A developer project where Jev assists in browsing by selecting actions, with an LLM planning and citing sources.
Source-linked curation
An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.
github.comaltryne/jevifyVoir le projet ↗Source-linked curation
DiffJury — TypeSafe Jev PR risk router + code review coach.
github.comraihankhan-rk/diffjuryVoir le projet ↗Source-linked curation
A developer project using Jev for plain-language MCP tool calls without an LLM.
Source-linked curation
Agent Skill: send closed coding-agent judgments to TypeSafe Jev.
Source-linked curation
Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.
github.comqkal/CannyVoir le projet ↗Source-linked curation
Selective list behind a 10-star bar, with hands-on reviews at mrjev.com recording what each tool sends and where.
github.comMrJev/awesome-jevVoir le projet ↗Source-linked curation
Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev.
github.comsamdotmak/jev-recallVoir le projet ↗Source-linked curation
Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.
github.comNobleSpartan6/ottoVoir le projet ↗Source-linked curation
Benchmarks and a playground for TypeSafe's Jev (System One) model: chess, and who-is-the-player-talking-to for speech-to-text game NPCs.
github.comwondertwins/jev-benchmarkVoir le projet ↗Source-linked curation
Wikipedia link races with direct Jev ranking and a live terminal display.
github.comkomikat/jev-bfsVoir le projet ↗Source-linked curation
Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.
github.comAboveColin/jevclientVoir le projet ↗Source-linked curation
A reproduction of Jev that turns any Qwen model into a fast decision model, serving the same /v1/systemone schema (Choice, Score, Noul) with no training and no generated answer text.
github.comzhengxuyu/litjevVoir le projet ↗Source-linked curation
A code search tool for agents to find behavior patterns instead of text strings.
github.comnassim-arifette/jevgrepVoir le projet ↗Source-linked curation
Context curator for Pi agent using Jev technology.
Source-linked curation
A GitHub project implements a web search tool where Jev selects sources for plain-language queries.
github.commukiwu/jev-search-mcpVoir le projet ↗Source-linked curation
Jev play Tetris in real-time against other AI models.
Source-linked curation
A GitHub project routing tasks by selecting model tier, tools, skill, and effort.
Source-linked curation
A GitHub project enabling voice-controlled Mac automation without vision models.
github.comsavka777/jev-useVoir le projet ↗Source-linked curation
Chrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post.
github.comRafalWilinski/vibecheckVoir le projet ↗Source-linked curation
Independent calibration test of TypeSafe's Jev on a task it cannot have seen: 900 rule-generated support tickets (choice / score / boolean) plus 3 public benchmarks via Vercel AI Gateway. Raw responses, ECE with noise floor, temperature refit, per-type sign of miscalibration. Reproducible for ~$0.06.
github.comscienthoon/jev-ood-calibrationVoir le projet ↗Source-linked curation
Match user goals to MCP catalog (two-stage) via TypeSafe Jev.
github.comndolinschi/mcpmatchVoir le projet ↗Source-linked curation
Real-time Discord moderation bot: Jev evaluates messages and metadata in parallel to catch phishing, spam, and social engineering with a progressive escalation ladder.
Source-linked curation
A developer project using Jev to score sales calls, collected for the creative shelf.
github.comZeroGold/call-coach-aiVoir le projet ↗Source-linked curation
Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.
github.comrorshopping/jev-on-a-laptopVoir le projet ↗Source-linked curation
Jev-Tool-Runner is a GitHub project where Jev selects developer tools and Codex generates code based on those selections.
Source-linked curation
A self-hosted skills library with optional Jev recommendations.
Source-linked curation
TypeSafe Jev as the pi coding agent's quiet decision layer.
github.comHyunjunJeon/pi-quiet-askVoir le projet ↗Source-linked curation
Unofficial typed async Rust client for the TypeSafe System One API.
github.comJedimEmO/typesafe-clientVoir le projet ↗Source-linked curation
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.
github.comAbdelStark/jev-benchmarksVoir le projet ↗Source-linked curation
CartShield — SMB checkout fraud disposition via TypeSafe Jev.
github.comndolinschi/cartshieldVoir le projet ↗Source-linked curation
Can a System One model steer music? Jev picks the plan (enums only); code renders sheet, audio and MIDI.
Source-linked curation
ACME live support-call scoring demo with TypeSafe AI, Effect, SQLite, React, Vite, and Turborepo.
github.combrandonbryant12/transcript-scorecardVoir le projet ↗Source-linked curation
Shady Town: social-deduction party game for the living room TV, moderated by TypeSafe Jev.
github.comtpaulshippy/shady-townVoir le projet ↗Source-linked curation
Safety checks for Hermes and other AI agents before they act, ask for approval, or verify a change.
github.combojansandhaus/jev-decisionsVoir le projet ↗Source-linked curation
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.
Source-linked curation
A Mac voice diary tool that uses Jev for sorting and integrates with Notion.
Source-linked curation
Typed decisions with TypeSafe's Jev, the first System One model.
github.comvalentynkit/awesome-jev-typesafeVoir le projet ↗Source-linked curation
Offline Obsidian search with optional Jev reranking of results, requiring user approval before reranking.
Source-linked curation
A developer project using Jev to play Pokémon Red by typing each turn.
Source-linked curation
Proposer un lien
English
한국어
日本語
Español
Deutsch
简体中文
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
Recherche et données
Source-linked curation
Outils et applis
Agents et navigateurs
Création et croissance
Jeux et temps réel
Marchés et expériences
Décisions et routage