Launches on September 26, 2026

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).

Reads the open reports on a Mastodon server with a moderator's own read-only token and prints them as a queue sorted by severity, using TypeSafe's Jev model. It never takes a moderation action.

Flink SQL ML_PREDICT provider for TypeSafe Jev semantic decisions

Realistic 100-Fly Drosophila Sword Colosseum powered by 139k Biological Connectome Dynamics & TypeSafe JEV System One AI

Community TypeSafe Jev semantic decision integration for formbricks

Gev: a System One decision model on Gemma 4 E4B, trained on a Mac

Hall Monitor: supervision and evidence-backed receipts for IBM Bob 2.0 (IBM Bob 2.0 Hackathon)

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

First survey and analysis of Jev's application ecosystem. 首个 Jev 应用生态综述与分析论文

local jev equivalent designed for llama.cpp and qwen 3.8 27B

A 90s home-shopping TV for eBay, where every knob is a question for Jev

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

Chrome履歴から目的に合うページを選び、Jevで操作して役立ったURLだけをプロジェクトごとに記録するCLI

Jev vs a Sonnet 5 RLM on BrowseComp-Plus (1K docs): a Jev screen in front of one Sonnet call matched RLM accuracy at 38% of the cost and 1/7 of the time.

What is JEV? A simple explanation of its architecture, reasoning, and how it works.

Read-only research prototypes for prediction-market contract logic, resolution scenarios and crypto exposure

Turns free-text smartphone reviews into Flipkart-style per-topic star ratings using Jev (via the TypeSafe SDK).

I built this project to test JEV, the new model recently launched by TypeSafe, by using it to turn free-text smartphone reviews into Daraz-style per-topic star ratings.

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

Claude Code plugin: Jev (TypeSafe) checks Claude's plan against your request before it builds, and its final summary before it stops; gaps go back to Claude until Jev passes it.

Official JEV Gateway & Reverse Proxy for Cursor, Claude Code, and autonomous AI agents. Sub-25ms deterministic tool execution layer.

AI chat moderation for Minecraft (Paper/Folia) and Hytale servers, powered by TypeSafe's Jev model. Works with the TypeSafe API or Cloudflare AI Gateway.

Jev ???? Harness ?? - ????????

Typed JSON payloads from natural language via TypeSafe Jev — Express middleware, no generative LLM, no MCP middleware

Jev decision model: TypeScript examples, HR Suite web app and webinar lessons

Running Jev (TypeSafe System One) from a NixOS flake: packaging, CLI, sops key storage

JevOnAir monitors livestreams in real time, transcribes speech, detects market-moving statements with Jev, and turns them into structured simulated trade signals.

A quality gate for AI-generated requirements, powered by Jev (TypeSafe System One). Routes each requirement to PASS / REVIEW / BLOCK with calibrated probabilities. Real benchmark vs LLM: 0 false blocks, 9x cheaper.

Turn an investment idea into an evidence-backed stock list: Jev reads ~20k global companies and checks official annual reports. 主题选股 / 产业链 / 年报证据 — runs locally via your AI agent.

Demo site for the Jev SVG classification project

Chrome extension: group, hide, or close tabs by theme, scored by TypeSafe's Jev model

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

Run only the tests your change touched: import graph + ownership rules first, Jev decides the ambiguous rest, fail-safe to the full suite. Replay benchmark with real ground truth.

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.

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

Trading with Jev

Meaning search for fzf: rank any piped text by what it means, using Jev. Unofficial, not affiliated with TypeSafe.

Community TypeSafe Jev semantic decision integration for kestra

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

☕ A bilingual tool to learn and communicate in multiple languages

Semantic SQL predicates for MariaDB powered by TypeSafe Jev

Community TypeSafe Jev semantic decision integration for meilisearch

Models interpret, rules decide: a fail-closed neuro-symbolic router in which language models only understand the text and a state machine carries out what the rules allow.

Apache NiFi processor for TypeSafe Jev semantic routing with uncertainty lane

A pixel-art Ouija board possessed by Jev, an AI model that can't write: it only picks, so it answers by choosing words.

usanya (Kiswahili: to collect, to gather) — invoice-first international collections for Kenyan SME exporters. Buyers pay in USD by card/Apple Pay/Google Pay (or in KES/UGX/TZS by mobile money); exporters settle to M-Pesa or bank in KES with total fee/FX transparency. AI paperwork by TypeSafe Jev. Money rails by Payaza. UI strictly shadcn/ui.

Minimal production Pi extension bootstrap for TypeSafe Jev and future Grail reviews

Semantic SQL predicates for Apache Pinot powered by TypeSafe Jev

Community TypeSafe Jev semantic decision integration for pulsar

Speak to Mac. On-box Laya picks the app. No cloud LLM.