Launches on September 18, 2026

Jev as a message gate to determine if agents should respond

Fast JEV compaction extension for pi

Reversible context pruning for Pi, powered by TypeSafe Jev. Keep useful context without deleting session history.

Pi extension that uses Jev task classification (via OpenRouter) to route each run to explicitly configured models with fail-open policy. Public Preview.

Jev test bench — Texas Hold'em edition: live-fire testing of TypeSafe's Jev evaluation model through a React poker game (Vercel AI Gateway). MIT.

Agente de trading para o mercado BTC Up/Down de 5 minutos da Polymarket: modelo em código, Jev (TypeSafe System One) como portão, ordens maker, calibração e shadows em paper

A nutrition label for privacy policies. Plain-language answers, confidence scores, and source excerpts powered by Jev.

Semantic linter for AI coding agents and CI code review. Detects silent failures, weakened tests, scope creep, unnecessary abstractions, and other semantic code smells.

TypeSafe Jev demonstration for new analyzation — experimenting with Jev for fast analysis of news and tickers

Makes S1-model 'measurement' (and the collapse that follows it) a Ruby primitive.

8 AI snakes, 1 human, 1 arena. Every snake is driven live by TypeSafe's Jev, making all decisions in real time

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

Open auto mode for AI agents — a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook

Alert triage as a UNIX filter: JSONL security alerts in, typed decisions out. Runs on TypeSafe Jev or a local model; policy routing stays in code.

화재 피난자 개인별 판단 엔진 — 타입 안전 판독(Bonsai 2 27B / TypeSafe Jev) + 소셜포스 이동, FDS-GPU 화재장 위에서 역할·구조·경로 결정 · Meteor Simulation

Chrome extension that reads every cookie banner and popup like a person and clicks the honest button. Judged by TypeSafe's Jev. BYOK, no backend.

MCP server: screen PubMed titles/abstracts against a query or clinical question with TypeSafe Jev

Give your AI agent a CLI companion who has access to TypeSafe AI's Jev.

Worked out examples of applying TypeSafe AI Decision (Jev) models with Pinecone.

Ask Jev whether a sleeping agent's wakeup is worth a full LLM turn before you resume it. A fail-open wake gate for long-running agents on Workers, Durable Objects and Node.

15-min BTC JAP — Jev Agent Protocol for Kalshi BTC 15m YES/NO

MCP server for TypeSafe's System One API (Jev): typed choice/noul/score judgments with calibrated probabilities and confidence

Jev-powered Judgment layer for Claude Code. Stops paying reasoning prices for if-statements: a PreToolUse hook scores every tool call against a YAML policy you own — allow / deny in ~100 ms, no LLM in the loop. TypeSafe Jev now, local models next. Dry-run by default, calibration table published.

TypeSafe Jev-scored context recovery for Cursor CLI (agent). Capture tool I/O, score keep/drop, re-inject after native compact.

Tetris arcade jogado pelo Jev da TypeSafe AI, com decisões em JSON, antecipação de jogadas e custo por partida.

Safe-controls Chrome feed filter (v3.3.0) with TypeSafe Jev judgments, temporal topic mutes, repeat grouping, API usage panel with thrift mode, author pickers, transactional cosmetic picker with Undo, persist-first recovery, and six supported platforms including Wykop (beta). Zero runtime dependencies.

For OpenClaw users, Gavel is a new plugin and skill that connects to OpenRouter so you can use the power of Jev. Route bugs, triage failures, and gate PRs in 200ms for $0.00002. OpenClaw plugin for TypeSafe Jev structured decisions.

Eval framework library to evaluate AI hallucinations, correctness, and instruction following, powered by Jev AI.

Lossless context compaction for Hermes Agent via the TypeSafe/Jev API — deletes or truncates stale tool calls instead of summarising. Python port of tamaratran/fast-jev-compaction.

Plain-English pull request checks powered by Jev. One condition, a minimum confidence, one check.

Measure what Jev can actually do before you build on it. Graded findings, ruled-out candidates, and recipes with stop-conditions. 0 promotions — on purpose.

AI-powered pre-commit auditor backed by TypeSafe System One (Jev) — blocks secrets, vulns & low-quality code in ~300ms. 79-case test corpus at 100% accuracy.

Daily demo applying TypeSafe's Jev model to Spain's official gazette (BOE).

Computer Use Agent developed with Jev

Independent API-only calibration audit of TypeSafe AI's Jev decision model

Experiment: using TypeSafe Jev as a chatbot by choosing replies one letter or word at a time

JSON-in, typed-decisions-out CLI for the TypeSafe System One API

Can a TypeSafe Jev prior read from a README on day one predict which new agent-skill repos gain stars? Zero-shot Jev ≈ a text model trained on ~150 labels; best used as a feature. Prospective test running.

Benchmark TypeSafe Jev against any OpenRouter model on your own data.

TypeSafe's Jev vs gpt-5.4-mini and gpt-5.6-luna on four public classification sets: cases, per-item answers, scoring, charts

Smart, dynamic AI filtering for X and YouTube feeds using Jev

JevHarness: TypeSafe Jev agent tool-call gate. execute / confirm / reject in code.

Jev for Hermes Agent: cheap typed decisions via TypeSafe Jev on OpenRouter. Routes turns, gates risky commands, compacts tool history, triages mail.

Ask Jev by TypeSafe AI whether a number is odd. TypeScript, real token usage, and latency benchmarks.

이름으로 나이대를 맞히는 React 웹 (TypeSafe Jev)

Experiments on TypeSafe Jev (System One decision model) via OpenRouter: repeatability, perturbation, and LLM baseline comparison

jev picks what a coding agent gets to see of large tool results: core library, pi extension and Claude Code plugin

Fake autoregressive language model powered by TypeSafe Jev

Reproducible riichi mahjong benchmark for Jev, GPT, Mortal, and hybrid agents using MJAI and RiichiEnv.

TypeSafe Jev plays Super Mario Bros.