Launches on September 21, 2026

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

Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway

Pi extension: TypeSafe Jev routes among checked models without becoming a chat model.

pi extension that rates each prompt with TypeSafe's jev decision model and reports the gaps.

Reproducible long-workflow benchmarks for Pi Sieve, with Astra and Luna comparisons.

Play chess against Jev with live TypeSafe inputs, choices, and probabilities

Comprehensive poker game theory knowledge base, instruction-tuning dataset, and TypeSafe AI (Jev) evaluation benchmark for Limit & No-Limit Texas Hold'em.

Sub-120ms smart LLM gateway & real-time optics dashboard using TypeSafe Jev System One. Defeats cache thrashing on coding agents (Goose, Cursor, VS Code) with Break-Even Cache Affinity and 0.60 Confidence-Gated Safety.

Question classification experiment using TypeSafe AI Jev for QA/RAG routing.

Compare question formulations with held-out evaluation, bounded experiments and DecisionPack export.

An inspectable action guard for LLM-driven Reachy Mini apps.

Typed Jev decision primitives for Reachy Mini applications.

Iibrary for Jev

Godot 4.7 addon for guarded finite NPC decisions, a playable market and replay checks.

Training demonstration of Jev in a dispatch services command center scenario.

ASCII music visualiser art-directed by TypeSafe's Jev: the room's sound becomes words, Jev picks the picture, the browser rolls it from Jev's odds

Write a rule. Change the physics. A Portuguese open-source game powered by TypeSafe Jev.

will update soon

Go client for the TypeSafe System One API (Jev) — the first piece of sael, a content-safety classifier for an AI request relay

Can a non-generative model (Jev) double-check an AI scribe's note against the encounter transcript? Working mock-up, psychiatry encounter, colour-coded draft with click-to-source and omission flags.

Pub/sub that routes messages by what they mean. Subscribers describe their interests in plain language; each message is judged once against all of them with Jev.

Monitor semantic conditions with exact-input caching, hysteresis and source/evaluator plugins.

Should I use JEV?

Experimental TypeSafe Jev controller for slither.io via Vercel AI Gateway

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

A Sonos command-line tool for humans and AI agents

A spam classifier - using system-one -> system-two architecture.

Email triage app built around Spark CLI and TypeSafe Jev. Early development: TanStack Start, React and TypeScript

Reigns-style card game with Luna and Jev.

Open-source, Jev-compatible System One API: typed decisions (Noul, Choice, Score) from next-token probabilities in one forward pass. Works with typesafe-sdk. Free hosted at sifty.dev.

Typed, calibrated decisions for Rust: a backend-agnostic client for System One models (TypeSafe AI's Jev), with cost-matrix decisions, caching, recording and calibration.

System One Model API for Laya compatible with TypeSafe Jev

Created using system One

Small, reproducible comparison between two approaches to single-choice decision making evaluated on BBH Logical Deduction

Hybrid System 1 (TypeSafe Jev decisions) + System 2 (Claude Fable) demo with confidence-gated routing and cost/accuracy benchmarks.

Small, standard-library-only Go library for typed decisions with Jev and other System One models.

🧭 Turn noisy tool output into compact, typed next-step JSON for AI coding agents with Jev.

Bounded Jev Activities and deterministic Workflow examples for Temporal.

THE CLAW. Ask for the night you want. TypeSafe Jev weighs every prize in the pit.

Support ticket triage: TypeSafe Jev judgments plus an explicit policy layer for priority and team routing, with a Next.js triage workbench.

A small RAG web app that visualizes every step of the retrieval-augmented generation pipeline

Twenty Questions played by two AI models: gpt-oss-120b guesses, TypeSafe's Jev answers. Cloudflare Worker, zero dependencies.

Large typed decision model evaluation benchmark and novel calibration standard (`calibration.json`) for any typed decision inference system, covering 275 distinct use-cases and 27,598 individual decisions for Jev-like open typed decision models.

Jev AI

Spring Boot API gateway using TypeSafe AI for confidence-based request routing.

Jev AI

Stress test of TypeSafe AI's jev-1.13 System One model: limits, vagueness, calibration, adversarial, new patterns, LLM bake-off

TypeSafe System One (Jev) 的 Go SDK — 类型化判断与概率,代码掌控工作流

Jev AI

A live, graphical dojo for TypeSafe's Jev (System One) typed decision model — routing, a Tetris-playing agent, parallel swarms, and an honest Jev-vs-Claude gauntlet.