GitHub

Swift client for TypeSafe Jev typed judgments instead of generated text.

Research notes and an interactive Cloudflare Worker demo for Jev, TypeSafe AI's structured decision model

LangChain and deepagents skill router where Jev ranks installed SKILL.md files and decides whether and which skills to load for each turn.

Jev checks configurable Pi agent rules for risk, output redaction, repeated failures, and missing verification at selected workflow stages.

Six live, side-by-side demos of TypeSafe's Jev — a "System One" model that returns typed, probabilistic decisions (70–500 ms, $0.042 per 1M input tokens, output free) instead of generated text.

Random Jev-compatible baseline that emits Noul, Choice, and Score probabilities for mocks, lower-bound comparisons, and router evaluation.

Left-pad strings with TypeSafe AI's Jev. For reasons.

Jev shadcn-block generator.

An unofficial local visualizer for Jev (TypeSafe): a live view of every call your code makes. Not affiliated with TypeSafe AI.

A Clash Royale bot with no trained policy: Jev (TypeSafe System One) makes every decision from the live game state.

Laya (open source, local) vs TypeSafe Jev (API): two AI models race in Snake and fight in a Mortal-Kombat-style arena. Every move is a real model decision.

🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.

Laya vs Jev: local MLX and hosted AI decisions playing T-Rex side by side, with live metrics and replay recording.

Jev uses one typed Choice question to select each narrative action from the options available at a Detroit: Become Human decision node.

Classify your inbox with Jev (TypeSafe's System One model) — tag, move, flag, and notify, all config-driven.

AI Music (MIDI) generator powered by Jev.

Don’t know how to answer the message on WeChat? macOS floating chat assistant: identifies message intent and communication risks, GPT generates a variety of words, Jev evaluates candidates, and fills in WeChat with one click. I will help you think about it and send it to you to order..

Self-hosted AI email classifier for Gmail powered by Jev. Create custom labels, organize your inbox, and filter spam with confidence and cost controls.

The experimental Jev path scores completed context payloads so users can review and approve what remains available to the agent.

Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with CodeGraph, and work with Git, Ghostty terminals, and Apple Notes in one app.

Read-only trading journal and review harness: Jev typed judgments, agent integration, and a reproducible finance benchmark. No orders, no advice.

The jev.ask runtime global lets sandboxed TypeScript programs request calibrated Jev Noul, Choice, and Score answers.

Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev.

Live SEO audit for any website from one homepage URL, judged by Jev. PDF, XLSX and Markdown reports.

Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.

An input that becomes what you mean: one text box that morphs into the right UI as you type. Powered by TypeSafe Jev, works offline.

A tool calling chat bot built with Jev and no LLM.

Jev ranks command-palette entries against a plain-language query so the intended terminal action appears first.

A small extension that demos the combination of Jev x WebMCP.

Jev Chat Assistant for Windows - PC version of WeChat intent judgment and DeepSeek suggested reply.

An on-demand crypto market intelligence and decision-support terminal powered by TypeSafe AI's System One model (Jev).

Crush Favorability Monitor: Use Jev to analyze the emotions, intentions and reply performance of WeChat chats. Deploy locally, use your own API Key..

Jev compares items against a ranking prompt across repeated batches so SiftRank can produce a converged relevance order.

Jev classifies incoming WeChat or QQ messages by intent and risk before the app presents reply guidance.

A very fast document classifier/splitter using Jev.

At each debugger pause, Jev chooses the next debugging action from the stack, locals, nearby source, output, and prior attempts.

Filter any live Twitch chat with Jev: a bring-your-own-key Chrome extension.

Chrome extension that cleans up your LinkedIn feed: hides engagement bait, self-promo and off-topic posts using Jev, TypeSafe AI's typed classification model — and explains every decision.

Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.

⚡ Millisecond-level Viral Hook Telemetry & Co-pilot for Social Media (Chrome Extension + JEV System 1).