Latest addition
Source check
Recent activityA FIELD GUIDE TO JEV / VOL. 01
Лучшее о Jev: реальные проекты, практические руководства и идеи со всего интернета.
THE OFFICIAL SIGNAL 4 HIGHLIGHTS
Diogo Almeida@CompleteSkepticLAUNCH POSTДиогу Алмейда представляет Jev, структурированную модель принятия решений TypeSafe. Посмотрите фильм о запуске и изучите оригинальный тред для подхода модели, примеров и отчетов автора о производительности.
TypeSafe AI@typesafeaiOFFICIALОфициальное объявление запуска TypeSafe знакомит с лабораторией и направляет разработчиков к Jev. Включает фильм о запуске Диогу Алмейды и оригинальное введение.
TypeSafe AI@typesafeaiOFFICIALTypeSafe объявляет о публичном доступе к Jev без списка ожидания. Официальный консоль — это отправная точка для тестирования типизированных решений в собственном приложении.
x.comJev открыт для всехПодробнее о проекте ↗TypeSafe AI@typesafeaiOFFICIALTypeSafe подчеркивает подход Jev с типизированным выводом: приложения предоставляют состояние и вопросы, затем действуют на основе вероятностей, выборов или оценок. Связанное объявление также касается интеграции API Venice.
x.comОтветы, которые может использовать кодПодробнее о проекте ↗Start with the Launch Post. Explore four official signals.
286 материалов
AI-assisted summaries and translations. Check original sources for context and performance claims.
Плагин Claude Code, который заменяет резюме компакции решениями Jev: каждая инструкция и результат оцениваются за один быстрый запрос, устаревшие данные удаляются или обрезаются, все остальное сохраняется без изменений.
EnglishSource-linked curation
Ультраскоростной агент для браузера: Jev выбирает операцию и элемент DOM за один запрос; небольшой ОЯ пишет текст только при необходимости ввода.
EnglishSource-linked curation
Proof of concept MCP for Typesafe's new Jev AI model.
EnglishSource-linked curation
Agent Skill: send closed coding-agent judgments to TypeSafe Jev.
EnglishSource-linked curation
Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions.
EnglishSource-linked curation
MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client.
EnglishSource-linked curation
A deterministic model routing system for coding agents with a skill for Codex.
EnglishSource-linked curation
A developer project that uses Jev as a sensor to control access to agent tools, enhancing security and functionality.
EnglishSource-linked curation
Typesafe's jev as a "fuzzy linter". give your code an ocular patdown.
EnglishSource-linked curation
A developer project demonstrates Jev's rapid response to browser tasks, with decisions made in approximately 100 milliseconds.
EnglishSource-linked curation
An agent project that enforces policies by judging Claude Code tool calls.
EnglishSource-linked curation
A developer project for automatic context clearing in Pi without losing conversation history.
EnglishSource-linked curation
A moderation system for Mastra agents that processes inputs in a single file.
EnglishSource-linked curation
Fast Rust CLI for TypeSafe Jev: typed decisions, offline linting before you pay.
EnglishSource-linked curation
Go CLI and single-binary MCP server exposing TypeSafe judgments to Claude Desktop, Claude Code, and Codex.
EnglishSource-linked curation
An agent project aimed at reducing token usage for coding agents via an MCP server.
EnglishSource-linked curation
A developer project where Jev assists in browsing by selecting actions, with an LLM planning and citing sources.
EnglishSource-linked curation
Agent skill: design judgment-assisted systems with TypeSafe Jev (System One). Maps Choice/Score/Noul onto decision theory, reranking, and routing. Composition algebra, question design, validation gates. MIT.
EnglishSource-linked curation
An agent system that makes one Jev decision per computational step.
EnglishSource-linked curation
Data extraction for systematic reviews, quoted from the papers. Ask a trial report and its supplements your extraction form or a RoB 2, ROBINS-I, QUADAS-2 or TIDieR template; Jev points at the lines, every answer is a verbatim quote with its page, you check it and export the table. Files stay in your browser.
EnglishSource-linked curation
Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.
EnglishSource-linked curation
A developer project for the agents shelf featuring a local MCP gateway with Jev tool discovery and a dashboard.
EnglishSource-linked curation
Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it.
EnglishSource-linked curation
A developer project using Jev for plain-language MCP tool calls without an LLM.
EnglishSource-linked curation
Scans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it.
EnglishSource-linked curation
Использование компьютера за $0.0002 за шаг: сканируйте экран, классифицируйте следующее действие с помощью TypeSafe, нажмите. macOS.
EnglishSource-linked curation
Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.
github.comgodspede/construct-auto-classifierПодробнее о проекте ↗EnglishSource-linked curation
Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration.
github.comkomikat/psearchПодробнее о проекте ↗EnglishSource-linked curation
A local computer-use fast path for Codex and Waku, designed for developers.
github.comEronmmer/jev-cuaПодробнее о проекте ↗EnglishSource-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-browserПодробнее о проекте ↗EnglishSource-linked curation
Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.
github.comshitianfang/jev-useПодробнее о проекте ↗EnglishSource-linked curation
JevNoiseGate filters unwanted notifications and SMS on Android. Rather than matching keywords, an LLM decides what's noise — and only what it explicitly flags is blocked. Verification codes are matched on-device and never uploaded; anything uncertain passes through.
github.comufec/jev-block-android-adПодробнее о проекте ↗EnglishSource-linked curation
Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model).
github.comopaielsheikh/typesafe-migration-guardПодробнее о проекте ↗EnglishSource-linked curation
Predict another skill's next closed decision with TypeSafe Jev — without running that skill.
github.comDanielKillenberger/jev-predict-skillПодробнее о проекте ↗EnglishSource-linked curation
A Jev browser agent implemented in Go, connected to a real Chrome browser for agent-based tasks.
github.comphanngoc/browser-aiПодробнее о проекте ↗EnglishSource-linked curation
Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.
github.comAbdelStark/heist-oneПодробнее о проекте ↗EnglishSource-linked curation
A developer project providing a local MCP server for running pre-made Jev question packs.
EnglishSource-linked curation
5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
EnglishSource-linked curation
A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.
EnglishSource-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.
EnglishSource-linked curation
WXT browser extension: Jev-powered page clutter removal with reusable template rules.
EnglishSource-linked curation
MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code.
EnglishSource-linked curation
Jev (System One decision model) plugin suite for DeepSeek Harness (dsh).
github.comzhangxaochen/dsh-jevПодробнее о проекте ↗EnglishSource-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-suggesterПодробнее о проекте ↗EnglishSource-linked curation
Code quality and test coverage for coding agents: Jev scores each source file so the agent knows what to fix first.
github.comsupercorp-ai/supercovПодробнее о проекте ↗EnglishSource-linked curation
Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic.
github.comZahrannnn/zcode-jevПодробнее о проекте ↗EnglishSource-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/stepwardenПодробнее о проекте ↗EnglishSource-linked curation
⚡ Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev (System One).
github.commaker-KK/todo-jevПодробнее о проекте ↗EnglishSource-linked curation
Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.
github.comleonaaardob/fast-dev-compactionПодробнее о проекте ↗EnglishSource-linked curation
Reversible context pruning for Pi, powered by TypeSafe Jev. Keep useful context without deleting session history.
github.comkevinpita/pi-jev-contextПодробнее о проекте ↗EnglishSource-linked curation
100% free ₹0 agent-first SEO & GEO CLI suite and MCP server in Rust replacing Semrush and OpenSEO via DuckDuckGo and TypeSafe Jev System One.
EnglishSource-linked curation
Interactive TypeScript coding CLI with typed routing, decision programs, and validated formal trees driven by Jev.
github.comrhighs/jev-codeПодробнее о проекте ↗EnglishSource-linked curation
Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell.
EnglishSource-linked curation
Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.
github.comNobleSpartan6/ottoПодробнее о проекте ↗EnglishSource-linked curation
Typed, confidence-aware agent skill routing with TypeSafe Jev.
EnglishSource-linked curation
Route to the cheapest model in claude code for your task using jev-router.
EnglishSource-linked curation
Jev controls an Astra planner playing Minecraft in a developer project.
github.comrmalde/minecraft-agentПодробнее о проекте ↗EnglishSource-linked curation
jev-use (voice). A developer project implementing voice control for macOS with Jev as a fallback option.
github.comcoco-research/jev-useПодробнее о проекте ↗EnglishSource-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-wardenПодробнее о проекте ↗EnglishSource-linked curation
Pi extension: verbatim context compaction with TypeSafe Jev decisions.
github.comjoelhooks/pi-fast-jev-compactionПодробнее о проекте ↗EnglishSource-linked curation
Aside agents decide with TypeSafe Jev (System One: Choice/Score/Noul). Not a Cua binding — Jev is the model, Aside is the browser runtime.
github.comhimomohi/aside-jevПодробнее о проекте ↗EnglishSource-linked curation
A staged code-review workflow and local dashboard built with TypeSafe Jev.
EnglishSource-linked curation
Context curator for Pi agent using Jev technology.
EnglishSource-linked curation
Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.
github.comAbdelStark/bicameralПодробнее о проекте ↗EnglishSource-linked curation
Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence.
github.comCorieW/JevTestПодробнее о проекте ↗EnglishSource-linked curation
Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
EnglishSource-linked curation
Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev).
EnglishSource-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-reviewПодробнее о проекте ↗EnglishSource-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-classifierПодробнее о проекте ↗EnglishSource-linked curation
A developer project for agent classification and selective reading using an agent plugin and MCP tool.
EnglishSource-linked curation
Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation.
github.comthiago-ss/jev-reviewПодробнее о проекте ↗EnglishSource-linked curation
Playjev uses Jev for browser automation with decision-making capabilities.
github.comfiledcom/playjevПодробнее о проекте ↗EnglishSource-linked curation
Предложить ссылку
한국어
日本語
Español
Français
Deutsch
简体中文
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
4 HIGHLIGHTS
ПЕРЕВОД
4 clicks / 7d
Agents & browsers
Source-linked curation