Launches on September 18, 2026

A bounded Jev risk check for Claude Code: eight risk axes, one request, one optional reinspection.

TUI Sandbox for Typesafe Jev API

Practical guide to using TypeSafe Jev with Herdr and Claude, Codex, Hermes, and browser agents.

Standalone TypeSafe Jev code-review CLI: typed decisions over a local git diff.

Recursive semantic file search using TypeSafe Jev and fzf

Real-time Tetris versus Jev, a TypeSafe decision model — spins, garbage, B2B chains, and decisions prefetched a piece ahead

Turn any word into probability distributions over taste, material, scent, and shape. Powered by Jev.

Local evaluation workbench for TypeSafe Jev

JevCode — Jev (TypeSafe System One) 技术解决方案与最佳实践 · https://www.jevcode.ai

Ask typed questions about a text and branch on the answer. A shell front end for TypeSafe's Jev.

Map a codebase into units and let Jev (TypeSafe AI) hand an AI coding agent the ten files that matter for a task

Open-source projects that provably call Jev, TypeSafe AI's System One model. Every entry links to the line of code that proves it. Refreshed daily.

TypeSafe AI's first model Jev takes on an entire city's traffic

Drive a real browser or a real LangGraph agent through one declared user journey, and report what actually happened. A page saying 'success' is never accepted as proof.

Every email accounted for. Every expected shipment answered for.

A small detective escape room built with TypeSafe Jev, React, and Express.

Local stand-ins for TypeSafe Jev's System One interface: typed calibrated decisions from small models, with a routing benchmark and a distilled 19 ms encoder

Long inputs for TypeSafe AI's Jev decision model. An experiment.

A beautifully minimal Magic 8 Ball powered by Jev from TypeSafe. Twenty classic answers, one fast AI judgment.

Ask the map anything. Every place answers with a probability. OpenStreetMap + Mapillary + TypeSafe Jev + Cactus Needle.

Node client for decision models such as Typesafe Jev

Hermes Agent skill whose north-star gate is judged by Jev (TypeSafe System One): turn an intention into a checkable finish line, generate the run prompt, and let Jev rank what is still unproven.

A gate for your agent's expensive steps, powered by TypeSafe Jev (System One). Offline-first, OpenRouter or direct, MIT.

Optional typed TypeSafe AI Jev decisions for OpenClaw, with SecretRef credentials and strict API validation.

open-Jev LM arm: Qwen2.5-0.5B + LoRA reproducing a hosted decision model's judgment at 92.9% on hand-labelled gold - trained overnight on a 6-vCPU CPU-only host, $0/call. Paper, corpora, harnesses, receipts.

Find the AI agent runs that broke because their environment did: missing keys, tools, files, permissions, network, or context. Powered by TypeSafe Jev.

Jev-powered context compaction for Pi. Keep critical instructions and tool history, prune the noise, and fall back gracefully.

Jev decides what to keep. Compaction never rewrites the transcript.

Semantic PR gate: .jev.yml rules as TypeSafe Jev questions. Not a review bot.

X 时间线清洁工 · FeedSieve(MIT) 衍生 · 带实测标定的 AI 判定层：误杀 0.7%，还能抓词库认不出的 47%

X（旧Twitter）のタイムラインから誹謗中傷を取り除く Chrome 拡張。判定を TypeSafe の System One モデル Jev で行う。

Static shell script analysis with Jev.

Semantic firewall for LLM agents: tool calls gated by TypeSafe Jev (System One decision model via OpenRouter) + deterministic policy. PoC with corpus, stability eval, baseline, results.

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.

Jev on Indonesia's SNBT 2025 university entrance test: 159 questions, seven subtests, audited answer keys.

Recorded comparison of Jev, Terra, and Opus on 100 synthetic security-triage cases, five passes each, with a static inspectable dashboard

Zero-dependency Go SDK for TypeSafe's System One API (Jev). Typed questions in, calibrated probabilities out with static analyzers that catch bad question design at build time, a decision layer, batching and caching. Not affiliated with TypeSafe AI.

Unofficial Go SDK for TypeSafe AI's System One API (Jev).

A Claude Code hook that asks whether the decision you are writing needs a model at all. Includes a measured 149-row comparison of TypeSafe Jev against Claude Haiku 4.5.

MCP server exposing TypeSafe (Jev/System One) to the fleet: judge, rerank, systemone

Unofficial C++23 client for the TypeSafe AI API.

Go SDK for TypeSafe AI.

Unofficial async Rust SDK for the TypeSafe AI System One API: typed questions via #[derive(QuestionSet)], a port of typesafe-sdk-python.

typesafe-sdk-js and typesafe-sdk-python port for swift

C# Library to use the Typesafe APIs, Direct conversion from Python/JS libraries

Classify C/C++ snippets via TypeSafe Jev through OpenRouter.

Hide what you'd rather not see: a Chrome extension demo where natural-language rules are judged by TypeSafe's Jev

Chrome extension that stamps every X post with a type badge — alpha, shitpost, AI slop, bait — judged by Jev from Typesafe

Typed state, explicit transitions, one narrow model judgment, and a human approval gate — a rebuildable agent workflow using and testing Jev.

Apply OS — Personal career decision engine powered by TypeSafe AI (Jev). Ranks job postings, drafts applications, and automates the pipeline with typed, calibrated decisions. Agency-ready build spec included.