Tools & apps

syumai

@__syumai

I built a CLI wrapper that gives you semantic "Did you mean?" suggestions when you mistype a subcommand, powered by Jev. git record → suggests: git commit npm add → suggests: npm install Not just typo-distance matching — it understands what you meant.

Jeff Coggshall

@voxmenthe

New code-search tool for agents! (and humans) Naive BM25 + Jev didn't work well enough for the code searches I and my agents were doing, so I built a better one: `code-search-jev`. It works like this: starts with four lexical channels (code, prose, symbol names, paths) to build

Chirag

@chirag

Saw someone comment here that you can make any local model speak TypeSafe Jev's /v1/systemone - so I built it. llamacpp-jev: typed questions → probabilities, text + vision, in front of an unmodified llama-server.

Wahab Khan

@chaosengineerr

got tired of reply guys.. so i built a chrome extension that stamps them jev by @typesafeai reads every reply and hides the low effort ones want it? thinking of open sourcing it

jem 💜🩵🩷

@sheherenow_

jemo 4: someone was like "jev is cool, I wonder what other old ideas are worth reevaluating?" so i guess i made a 1980s Expert System that runs on lisp + jev??? ¯\_(ツ)_/¯

Luis

@luisf_mc

“Where was that tweet I read yesterday?” I built Seen with Jev from @typesafeai to find it. Press ⇧⌘Space. Type what you remember. Open the saved screen. It works across Mac apps and displays. Jev ranks the results using your own TypeSafe or Vercel AI Gateway key. Local

Jarod Reyes

@jreyesdev

I just built a demo that uses @typesafeai JEV and @sanity_io and it's incredible. No LLM in the query path. The "agent" skips retrieval entirely when it can, and when it can't, it's one-way (no roundtrips). The prose was already written at ingest, so the agent selects an answer

Kevin Ly

@kevinlysocial

I Built a Live AI Director With Jev I’m presenting. AI is choosing whether you see me, my screen, or both. I built a little live director using Jev. My voice is transcribed locally, then Jev uses those words to choose the view while I talk. It switches between the views, but

Kane Snyder

@tenfingers

I built an open source voice control plugin for @OmarchyLinux using Whisper and Jev from @typesafeai. Its called Voicebind. I love keybindings in Omarchy and use voice control as a second option. Its nice to have both. @dhh 🙏 You can use a phrase to enable listening

mathews

@chriscmathew

Context compaction shouldn't eat the error you're trying to fix I built fast-jev-codex: Jev scores tool history, then the plugin restores verbatim context after Codex compacts. Open source. Bring your own Jev key.

Chris Nicholas

@ctnicholasdev

I've built an open-source workflow builder for Jev! Experiment using a UI—classify inputs using choices, scores, booleans; wire results into other prompts; and return a set of custom outputs. Below I've set up a support system that can help with various queries. Features ↓

DJ RIO | REALITY

@djrio_vr

Jevのテストとして、とりあえずXで自分が見たくないなぁって投稿を判定して非表示にするChrome拡張機能を作ってみました。 リアルタイムに投稿内容を判定しているけど、めちゃくちゃ速い＆安いです。ベンリ！ github: https://t.co/E6oG8wyRS5

void

@sakevoid

i built a safety hook that screens every shell command before claude code is allowed to run it. the idea is simple: before execution, jev looks at the command and answers one question: "should this command be stopped?" then deterministic code decides what happens next. low

A plugin asks Jev to choose the Codex model and reasoning effort before a run, with user-set model caps and approval required for Astra.

A Python/Strands workflow has agents inspect a GitHub pull request, then compares an LLM judge with Jev for severity and relevance before Python applies the final inclusion rules.

An Elixir client supports TypeSafe and OpenRouter with yes/no decisions, choices, scores and multiple questions per request.

Tom Frazier

slopmop.lol

↗

A free Chrome extension asks Jev about signs of low-value writing in LinkedIn posts, then lets readers hide, highlight, inspect, or override its judgments.

A filter extension uses Jev to screen the author’s own social feeds.

baoer_signal_grep uses Jev as an optional judging layer over local code search.

A free, open-source local gateway visualizes the decisions from Jev after the author moved most pseudo-deterministic flows to it.

Open-source Chrome extension for X and LinkedIn. Jev scores whether each post is AI slop; posts above the user-set threshold are blurred, with a reveal button for mistakes.

The developer says Miraviel uses Jev to help run an immersive roleplay app with infinite memory, one-minute character setup, and imports from SillyTavern, Janitor and Character.AI.

Gajanan

@gajananrx

@icantcodefyi Check this out I built this using JEV it rates how stupid your startup idea is

Rishi Raj Jain

@rishi_raj_jain_

Jev at dating: https://t.co/1JfzVmD4Ak 💔 Anonymously paste your chat / screenshot and save yourself!? 💀 - Judged by Jev (by @typesafeai) - Securely stored in @neondatabase - OCR with Tesseract.js - Built with @claudeai - Deployed to @vercel

Saif

@saifcodes_exe

Launching FyleContext. 1/5 Upload PDFs, docs and URLs once. Claude (or any MCP client) searches them and cites the exact page. TypeSafe Jev scores every passage before it reaches your model. Nothing relevant? It says so instead of guessing. Link in comments.

Zade

@zadescoxp

I built a trading agent with the all new @typesafeai Jev. You can try it here : https://t.co/im4bydkUTh. Just put your own API key and start playing or clone it from https://t.co/wIYgpRWv0w and test it locally. To my surprise the agent was able to take a trade of 2.405 $ETH and

for a short video, four segments, each tagged with type, duration, and text. The `noul` confidence scores are real Jev API results for the original Traditional Chinese text (an…

Jev is a model that answers typed questions instead of generating text: yes/no, pick-one, or a score on a scale, each returned as a calibrated probability. You can get the same…

Roan

@RohOnChain

i built a 24/7 HFT trading bot with Jev and wrote an 8-page research paper on EXACTLY how to build a millisecond speed high-frequency trading system with Jev, along with COMPLETE CODEBASE here is how you set it up: 1. split your system in two, deterministic code owns the math

Pass two hands that shortlist to Jev, TypeSafe's decision model, in a single batched call. Jev isn't a chat model, it's what they call a System One model: it doesn't generate…

A semantic lint is a rule you can state in a sentence but cannot express in a regular linter. Jev turns each rule into a yes/no question over one diff hunk and returns a…

Jev is TypeSafe AI's model for that narrower job. You give it the relevant text and define the possible kinds of answer. It returns typed values and probability distributions…

SuperQode is our terminal-first harness for coding agents. You bring a model or an agent. SuperQode owns the loop: tools, permissions, YAML exec-policy, Git Guard, session…

codila

@0xCodila

Jev is the "Internet" moment for the AI industry It tells your agents and LLMs what to do next, in milliseconds and at almost zero cost If you set it up correctly, you will have the AI engineer’s stack for 2028 In this article, I show you how

Two public sources now say Jev beats GPT-5.6 Luna. Vercel's CEO says so for the safety reviewer in fx, a Vercel tool whose default auto mode runs that reviewer on every command.…

TypeSafe released Jev on 2026-09-15. It is a decision-only model: you give it yes/no propositions and it returns a probability instead of text. I put it in front of Pi's `bash`,…

# Exploring Jev for AI-Driven QA with agent-device ... TypeSafe recently released Jev, a model for making fast, structured decisions. The company reports response times of 70 to…

Jev handles narrow, typed decisions over unstructured data through TypeSafe's System One API. Your code supplies the relevant state and one or more questions with constrained…

That's where Jev comes in. From Parts 1-2 we know it's a fast, cheap "decision model": give it options and a question, and it returns one answer plus a confidence score - no long…