Launches on September 18, 2026

Arcade

A small app to test Jev

Live-stream encoder settings from telemetry and history: TypeSafe's Jev decision model inside a deterministic safety envelope. Deno, Node, edge runtimes.

LLM vs TypeSafe Jev vs a confidence-gated hybrid: who picks better links in a wiki race?

Bare-bones OpenRouter + TypeSafe Jev classifier: route legal prompts to Texas statute databases

Cline Plugin to add a new computer run tool runs by the typesafe/jev model

Crawls a site with Cloudflare Browser Rendering, triages with typesafe/jev, confirms with vision, files deduped GitHub Issues

A source-linked venture diligence workspace powered by TypeSafe Jev

Voice-driven UI command layer in the Jev style: speak mixer commands ("mute singer", "set reverb 25%") and the UI moves instantly. Jev-shaped decision interface (typed decision + confidence + threshold escalation), $0 local implementation now, TypeSafe Jev slottable later.

TypeSafe Jev (System One decision model) as a native jev_decide tool plugin for DeepSeek Harness

Dual-Process AI: A design pattern combining System 1 (Jev/TypeSafe AI) with System 2 (Gemini) — inspired by Kahneman's Thinking, Fast and Slow

Semantic ORDER BY for DuckDB, backed by TypeSafe AI's Jev model. Ships with independent calibration numbers.

what is this?

Semantic validation for Zod schemas, powered by TypeSafe Jev. Validate meaning, not just structure.

TypeSafe System One (Jev) evaluated on synthetic FHIR clinical scenarios, with Claude as System Two

A small native launcher for macOS. Option+Space opens a dark HUD.

Browser extension that blocks distracting websites using TypeSafe: Jev

Flock-camera-aware privacy navigation: see ALPR cameras near you and get driving routes ranked by camera exposure (TypeSafe Jev ranking + heuristic fallback). Paste your own key, find clean routes.

GitHub Action for agent-written PRs: one comment that says what the PR really does, which hunks need a human, why, and what to verify. About a cent per PR, on TypeSafe Jev.

Scores public job postings against my resume using TypeSafe's jev via the Vercel AI Gateway. Daily Vercel cron.

TypeSafe/Jev decision signals for Hermes: turn classification, conservative tool shaping, approvals, and coding verification.

A wall of a hundred invented people who react while you type, on TypeSafe AI's Jev

A chatbot that cannot write: TypeSafe Jev ranks a checked-in bank of replies.

Result-based TypeSafe System One client library and jev command-line interface.

Typed judgment CLI for the Jev model (TypeSafe System One): state + questions in, calibrated answers and exit codes out

TypeSafe's Jev decision model in Claude Code. Ask in plain language, get a typed answer with a calibrated probability.

TypeSafe Jev plays live 2048. It doesn’t see pixels or write text, it only picks the swipe.

Public Jev / TypeSafe academy — zero-to-hero walkthrough for Brandon Theriot

An independent, evidence-first field guide to Jev (TypeSafe AI's System One model) — for people and for coding agents. Not affiliated with TypeSafe AI.

JevBot: TypeSafe Jev support bot. Choice+Score+Noul in, canned reply/escalate/block out. Not a chatbot.

Jev chess experiments: independent decisions vs tactical and Stockfish assistance, with full traces and video replays

Testing out Jev / System One model for a health use case

JevCode: TypeSafe Jev diff merge gate. merge / comment / block in code.

Score every Cognigy conversation against rubrics you write, using TypeSafe Jev instead of an LLM. CLI, local web UI, and an agent skill.

Context compaction for agent harnesses: a decision model scores transcript spans and tombstones the ones that stop mattering. Includes an MCP restore server.

A visual control room for typed AI evaluations, structured decision-making, and confidence-aware policy gating using Vercel AI SDK and TypeSafe Jev.

Read-only TypeSafe Jev feasibility test rig for comparing structured Curation Engine classification decisions with existing LLM audit results.

把决策模型（typesafe/jev-1.13，经 OpenRouter 的 decisions 端点调用）封装成业务决策工具：注册表驱动，带置信度门控与硬约束。非官方项目。

A ~/Downloads folder that sorts itself: one Jev decision per file, launchd WatchPaths, no daemon

A liquid magic eight ball powered by TypeSafe Jev decisions through OpenRouter

tinkering and experiments with jev and typesafe ai

An example repository for exploring Jev - the System One model

Uses Typesafe AI Jev to Provide A Tweet Fact Checker

Six calibrated gates for Claude Code, judged by TypeSafe Jev: rules, scope, intent, done, claims, and commit honesty. Each one escalates, none ever approves.

A small local HTTP service for TypeSafe AI's Jev through Vercel

Hunting label errors in popular text-classification datasets with TypeSafe Jev

Harness for TypeSafe's Jev decision model: typed questions over datasets via OpenRouter, JSONL answers, summary reports.

TypeSafe jev でエージェントの応答を審査し、形式的な完了を Stop hook で差し戻す Claude Code / Codex plugin

Early-access test of TypeSafe's Jev on 24 Norwegian hearing responses, next to DeepSeek V4.1 Flash

Two TypeSafe Jevs duel in NES Joust.