Launches on September 18, 2026

SQL with natural-language predicates, powered by TypeSafe's Jev. Filter, rank, classify and score rows by meaning — batched, cached and cost-guarded.

OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI.

Make room for useful evidence. Inspectable context selection for RAG, with Jev reranking and open benchmark studies.

Typed, calibrated decisions from a local model. No text generated.

TypeSafe's Jev model plays Vampire Survivors on Steam: BepInEx plugin + Python brain + live decision dashboard. Native Linux only.

Route Claude Code's coding decisions through TypeSafe Jev: typed choices with probabilities, enforced at plan approval, questions, and risky commands.

Audit your git diff against YAML coding-standards packs using TypeSafe's Jev model, from a CLI or your AI agent's command/skill.

Sub-second Git pre-commit & pre-push semantic reflex gate powered by TypeSafe AI Jev

Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.

Privacy-first Chrome extension that semantically blocks native ads, sponsored feed cards, and video ads using TypeSafe Jev

Control your Mac by voice. Speech → Jev (TypeSafe AI System One model) typed decisions → macOS actions. Menu-bar Swift app.

An optimized inference engine to turn LLMs into Jev-like machines: optimized for quick, lightweight, and accurate decision-making, classification, and scoring

Jevによるnote記事のAI Slop判定サイト

A Jev based context curator for pi

Connect WordPress to TypeSafe's Jev System One model for structured decisions (choice, score, noul).

Experimental Jev permission gate for Claude Code via OpenRouter, with reproducible latency and cost benchmarks

Jev-powered context curation for Codex. Build compact, traceable handoff context through native plugins and skills.

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.

Ask typed questions of your documents. Get structured signals for agentic workflows, with the page each answer came from.

Calibrated alignment verifier for LLM responses and agent plans — powered by Jev

Pre-registered independent eval of TypeSafe Jev against a nano-class LLM, a frontier LLM, and a supervised encoder (Banking77 + CLINC150 zero-shot)

Browser automation with Jev (TypeSafe) as decision model

Typed model routing for OpenClaw agents, powered by TypeSafe Jev

Context compaction for Hermes sessions that never summarises: every tool call is scored by TypeSafe's Jev model, stale calls are dropped, everything kept stays verbatim.

Experiments on Jev’s probability calibration, uncertainty reporting, and forecast probability preservation.

open-sourced jev-flash-router: an MCP server for TypeSafe's new Jev model. AI coding agents waste hundreds of reasoning tokens just deciding which file to edit, which route to pick, or whether a diff breaks tests. Jev evaluates state and outputs calibrated probabilities. Works with Cursor, Windsurf, & Claude Code

弈瞬：双 Jev 五子棋九宫格输入实验台，逐手查看模型决策，支持真实对局回放与实时对战。

Natural-language MCP tool dispatcher powered entirely by TypeSafe's Jev — no general-purpose LLM. Discovers a simple MCP server's tool signatures at runtime and uses Jev's typed primitives (Choice/Noul) to pick the right tool and extract its arguments straight out of the sentence.

Routes each turn in Claude Code, Codex, Grok and opencode to the cheapest model and reasoning depth that can finish it, using TypeSafe Jev

Options trading bot (backtest + Alpaca paper only) with TypeSafe Jev as the decision core

Hands-on agent memory notebooks and an interactive appbook for context engineering.

TypeSafe AI System One (Jev) task plugin for QuantumNous/new-api — native /v1/systemone, synchronous evaluation, token billing

Verbatim context pruning for the pi coding agent, scored by TypeSafe Jev: stale tool calls and results are dropped or truncated, everything kept stays verbatim.

Automatic Jev context clearing for Pi. Keep the conversation, prune stale tool output, retrieve originals without rerunning commands.

A coding agent and personal assistant with System One reflexes (TypeSafe Jev) on top of the Pi coding agent

Reimagined window switcher for macOS using frontier artificial intelligence. Predicted by TypeSafe's Jev model

Batched natural-language judgments for SQLite, powered by TypeSafe Jev

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

⚡ Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev (System One)

A VGI worker exposing TypeSafe System One questions (choice, noul, score) to DuckDB/SQL as LATERAL-joinable table functions

Zero-memory System-1 decision engine & TypeSafe Jev wire-compatible runtime powered by Mandelbrot wave dynamics (The Zero-VRAM Gauntlet).

Open-source BYOK Chrome extension for personal, reversible X timeline filters.

Private Mac voice diary: local Parakeet transcription, Jev sorting, Notion library

Agent skill that spots bounded-judgment steps, tries a typed decision model (TypeSafe's Jev) first, and documents every attempt

npx skills add raydocs/ego-verified-actions — bounded ego-lite clicks with checkable SUCCESS_MATCH

Jev for Hermes: skill discovery, multi-skill advice, adaptive reasoning effort, model recommendations, typed assessments, session re-ranking, and computer use.

JEV AI Model Demo with FSD

Run jev-browser on a fully local JEV-style decision engine (no cloud API). Warm-browser fork, VRAM guard, measured benchmarks, run traces.

Rubric-based eval harness cheap enough to run on every PR, powered by typesafe-ai/jev

Per-turn router for agent harnesses: one 350ms Jev call picks the model tier, effort, tools and skill, behind a hard deadline with a regex fallback. Claude Agent SDK adapter included.