A FIELD GUIDE TO JEV / VOL. 01
Le meilleur de Jev : projets concrets, guides pratiques et idées du web.
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.
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 ↗
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 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 ↗Four official signals. A fresh starting point on each visit.
378 ressources
AI-assisted summaries and translations. Check original sources for context and performance claims.
Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with CodeGraph, and work with Git, Ghostty terminals, and Apple Notes in one app.
github.comCheshiAI/CheshiVoir le projet ↗Source-linked curation
Reduces context usage by 30-55% through Jev-based compaction for OMP agents.
Source-linked curation
Input moderation for Mastra agents on TypeSafe Jev — one file.
github.comCodeAlive-AI/mastra-jev-moderationVoir le projet ↗Source-linked curation
Bounded TypeSafe Jev workflows for coding agents.
github.comdevagrawal09/stanley-codeVoir le projet ↗Source-linked curation
MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.
github.comrashedInt32/jev-mcpVoir le projet ↗Source-linked curation
AI Builder ClubJev-browser enables agents to perform web tasks by automatically opening websites and making click decisions based on screen content.
Source-linked curation
Riley BrownA community project describes an agent system that uses Jev to route requests to appropriate models.
Source-linked curation
A Chrome extension using Jev to filter out AI-generated content from YouTube, caching results for efficiency.
Source-linked curation
Reward-hack radar for coding agents: structural denies + TypeSafe Jev System One sidecar for Claude Code & Cursor hooks.
github.com24601/rh-guardVoir le projet ↗Source-linked curation
Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions.
Source-linked curation
Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model).
github.comopaielsheikh/typesafe-migration-guardVoir le projet ↗Source-linked curation
JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.
github.comkikoncuo/jevfireVoir le projet ↗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
Sawyer HoodJev automates the filling of prompt boxes by selecting appropriate agents, models, or computers for specific tasks.
Source-linked curation
x.comA community post discusses Jev as a faster general classifier/decision-maker, questioning its accuracy in complex scenarios and noting potential benefits in limited solution spaces with low latency requirements.
x.comDay-one notes from a skeptic, in ChineseVoir le projet ↗Source-linked curation
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.
Source-linked curation
Match user goals to MCP catalog (two-stage) via TypeSafe Jev.
github.comndolinschi/mcpmatchVoir le projet ↗Source-linked curation
Outil en ligne de commande pour le modèle Jev de TypeSafe AI. Posez des questions oui/non, à choix multiples et à rubrique à tout texte et obtenez des probabilités calibrées en retour. Les réponses deviennent des codes de sortie pour les shells et CI, du JSON pour les scripts, et des outils MCP pour les agents IA.
github.comshaharia-lab/jev-cliVoir le projet ↗Source-linked curation
A developer project for automatic context clearing in Pi without losing conversation history.
Source-linked curation
Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway.
github.commejiasd3v/pi-jev-routerVoir le projet ↗Source-linked curation
A staged code-review workflow and local dashboard built with TypeSafe Jev.
Source-linked curation
Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM.
github.comprismhq/jev-routerVoir le projet ↗Source-linked curation
A Magic 8 Ball for pull requests: click the ball and it answers "should I approve this?" with one of the 20 classic phrases, chosen by Jev from the PR's real signals in about 200 ms.
github.comacharyaanusha/magic-jevVoir le projet ↗Source-linked curation
RanjanA community project enabling hands-free web navigation by having Jev handle browser actions while Claude manages conversation.
Source-linked curation
Guardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python.
github.comaniruddh-krovvidi/switchboardVoir le projet ↗Source-linked curation
Chrome-devtools-mcp plus one tool: Jev walks the browser to the right spot, then your agent makes a single devtools call there.
github.comrashedInt32/jev-reachVoir le projet ↗Source-linked curation
Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.
github.comcaiovicentino/jev-shieldVoir le projet ↗Source-linked curation
⚡ Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev (System One).
github.commaker-KK/todo-jevVoir le projet ↗Source-linked curation
Tutorial covers API setup and building prototypes with Jev and LLMs.
YouTube · Voir le projetSource-linked curation
Jev controls an Astra planner playing Minecraft in a developer project.
github.comrmalde/minecraft-agentVoir le projet ↗Source-linked curation
Zero-hallucination open-source repo and crate scout powered by TypeSafe AI Jev System One scoring.
github.comAkashPriyadarshii/jev-scoutVoir le projet ↗Source-linked curation
Milind SA system using Jev to interact with computer interfaces without screenshots, relying on local CoreML models and OCR.
Source-linked curation
Application of TypeSafe Jev (noul judgment primitive) on the collusion.wiki corpus: agent vs human page authorship, head-to-head vs local Qwen3.8-Flash-Next.
github.comsypherin/jev-trace-classifierVoir le projet ↗Source-linked curation
ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
github.comtacticocc/JevbridgeVoir le projet ↗Source-linked curation
Reusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev.
github.comRipwords/agent-gate-loopVoir le projet ↗Source-linked curation
Turn your AGENTS.md preferences into a fast, Jev-powered AI linter.
github.comdoeixd/jev-prefVoir le projet ↗Source-linked curation
MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer.
github.comblakestone-x/jev-mcpVoir le projet ↗Source-linked curation
A developer project providing a local MCP server for running pre-made Jev question packs.
Source-linked curation
Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.
github.comAbdelStark/bicameralVoir le projet ↗Source-linked curation
Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident.
github.comBeLazy167/typesafe-modVoir le projet ↗Source-linked curation
Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values.
github.comKesavanKing/jev-browserVoir le projet ↗Source-linked curation
A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.
Source-linked curation
Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.
github.comvinilana/jev-eval-agentVoir le projet ↗Source-linked curation
Detects low-quality content in real-time as users scroll.
Source-linked curation
OskarFramework for running end-to-end tests with agents using Jev.
Source-linked curation
A developer project integrating Jev for judgment tasks within DeepSeek Harness.
github.comHorusJiang/dsh-jev-toolsVoir le projet ↗Source-linked curation
Marcel PociotMarcel Pociot's browser extension that collapses posts based on a Jev judgment.
Source-linked curation
An experiment using Jev to interpret voice commands and trigger tool actions before the user finishes speaking.
Source-linked curation
TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate.
github.comajensenwaud/hermes-jev-pluginVoir le projet ↗Source-linked curation
Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。
github.comDevin-AXIS/jev-dsh-decisionVoir le projet ↗Source-linked curation
Typed, confidence-aware agent skill routing with TypeSafe Jev.
Source-linked curation
Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop.
github.comDevMortimer/pi-wardenVoir le projet ↗Source-linked curation
A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.
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
Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
Source-linked curation
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.
github.comfrostney/clean-code-reviewVoir le projet ↗Source-linked curation
An experiment using Jev for real-time model selection in AI agents, collected for the agents shelf.
Source-linked curation
Andy GaoA project using Jev to enable fast voice-controlled interactions with a Mac computer.
Source-linked curation
Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels.
github.cominanna-malick/jev-dslVoir le projet ↗Source-linked curation
Pre-commit hook: one Jev call judges whether your commit message matches the staged diff, plus debug leftovers, unmentioned work, and a credential check.
github.comvalentynkit/jev-commitVoir le projet ↗Source-linked curation
Grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.
github.comkeltokhy/jgrepVoir le projet ↗Source-linked curation
TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.
github.comphyous/tsai-civ2Voir le projet ↗Source-linked curation
WXT browser extension: Jev-powered page clutter removal with reusable template rules.
Source-linked curation
Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.
github.comlomeshdutta/skill-routerVoir le projet ↗Source-linked curation
Every tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to verify each pending tool call against the session plan, then allows it, asks you, or blocks it. Proof of concept.
github.comgetexcited/stepwardenVoir le projet ↗Source-linked curation
TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent.
github.comsiddicky/omp-typesafeVoir le projet ↗Source-linked curation
Jev-assisted file retrieval and request caching for faster Pi workflows.
Source-linked curation
Windows Codex Skill：通过 npx 或 Git 安装，安全配置 save-token-jev 的 PreCompact/SessionStart Hooks，并提供信任、原生压缩与旧内容隔离验证。
github.com455-dIAO/windows-save-token-jev-setupVoir le projet ↗Source-linked curation
MCP skill router where Jev picks the relevant skills instead of a long agent search.
x.comskillbox + Jev skill routingVoir le projet ↗Source-linked curation
Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozy.
Source-linked curation
Practical, tested recipes for TypeSafe's Jev decision model on OpenRouter: support triage, database indexing, file organizing, tagging, taxonomies, dedupe, PII detection, extraction, search re-ranking and a browser agent.
github.comnexibeo/jev-cookbookVoir 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
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
Agents et navigateurs
Source-linked curation
TRADUIT