Catalog, page 5

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.

Classifies each outbound agent email with Jev before it reaches Resend, blocking abusive bulk outreach at the API boundary.

Hunch maps an accessibility snapshot to the next browser operation with Jev, then verifies outcomes in code and hands uncertain or irreversible steps to an LLM.

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

jevals turns agent checks into typed questions so the same evaluation definitions can run on saved traces and as runtime guardrails with Jev-style decision models.

A custom Jev harness uses context-sensitive hints and chained decisions to pronounce Chinese characters.

Jev helps find the exact moment answering a health question across more than 3,000 hours of video.

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

An open-source Alexa-like assistant calls Jev before its LLM to identify device-control requests, choose the device and action, and switch hardware immediately.

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

A harness supplies real-time strategy game state to Jev and lets Jev make the gameplay decisions. The author says they have worked with Jev for more than 35 hours.

A free Jev-powered magic 8 ball at real8ball.com.

A Chrome extension uses Jev to choose the best existing prompt, template or workflow for the user’s goal even when their search terms do not match saved titles, text or tags.

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.

A client workflow uses Jev to label emails by priority and other signals; the author says a demo is live on their site.

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.

Rebuilt a survey-research workflow with Jev for 200 samples and 12 questions per survey; author reports it ran 2x faster and cost 85% less than Gemini 3.5 Flash-Lite.

Debarpan Jha

@DebarpanJha

Jev is INSANE. I built a LinkedIn Post Copilot to score posts, explain the results, and suggest improvements using structured analysis. No API key? It scores offline using a deterministic local heuristic. https://t.co/ys32qPwDaZ #Jev #AI #Buildinpublic @typesafeai

Pranav Barthwal

@pranavbarthwal_

unlocked a new jev usecase today a publisher, secretly, ran our ad tag on their 🌽 sites none mapped on our dashboard now jev will check at runtime > tag loaded on a related domain / subdomain / mapped domain? allow. > phishy corn site? blocked.

Luong NGUYEN

@luongnv89

So instead of chasing which posts I should pay attention to, I am using Jev (combine with my original Algo) to have this floating panel Now I can quickly find which posts are most relate to my interest, and probably save ton of time because of dump scrolling, but hey, dump

Gajanan

@gajananrx

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

Li Yibai

@yibaili530

Added a Chrome extension to my X research tool! You can now save posts straight from X into the workspace and see the relevance score. Really useful little upgrade!

Robin Roy

@_RobinRoy

what if your imessage had an elo bar? powered by @typesafeai jev astra makes the choices, jev scores them. repo below.

Rishi Raj Jain

@rishi_raj_jain_

I turned Jev into a Flappy Bird player and I won against it (sorraay @typesafeai). Can you beat it? Let's see your score: https://t.co/ktQrUYvPHb Tech: - Results stored in @neondatabase Postgres - @nextjs App Router 16 with @DrizzleORM, @shadcn and @tailwindcss - pdx1 region

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

Rishi Raj Jain

@rishi_raj_jain_

Had Jev (@typesafeai) read every comment on the most-discussed threads on Hacker News (@hackernews) and give a verdict ⚖️ → https://t.co/WzAWif9Ekj • Every comment judged by Jev: stance (support / critical / neutral), a substance score, a 0..1 quotability, and whether it

Rishi Raj Jain

@rishi_raj_jain_

Built content-aware PII redaction in Postgres with @neondatabase and @typesafeai's Jev where redaction on support messages is not on entire column bluntly, but only on meaningful bits: https://t.co/sOSG4tXCot 🎉 • Jev reads each message and tags the personal bits: names,

Anish Ghimire

@anishghimire862

Kueon allows you to set your goals for conversation mentions and then shows you only the conversations relevant to your product and the ones that match your goals. A step ahead in reducing the noise. Join Kueon today 👉 https://t.co/Ect4IcbyxS

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.

Vishesh Baghel

@VisheshBaghell

I recently got access to jev from and built this, because I hated the hacker news front page. everyone gets the same stories in the same order. someone else already decided what matters, and it is never quite what matters to me so: six sliders. technical depth, drama, practical

Bilal Khan

@Bk23544

JEV is crazy!!! I got access, so naturally I had to try it with the Three.js Grassworks demo. I built an AI Scene Director that takes a simple prompt and changes a whole set of scene and grass parameters to customize the environment based on your instructions. And it’s FAST.

David Madurzak

@davidmadurzak

Can you play mspacman with @typesafeai Well kind of. You need about 70ms of latency to play properly, in the video I had an average of ~650ms. The game was paused waiting for a response and then the footage you see is with the pauses removed. I also had to give some hints on

Mike Kelly

@NicerInPerson

Turns out Jev is very good at quickly crawling through an LLM wiki to find relevant content. 10x cheaper and 40x faster than a frontier worker model like Sonnet. So I built a cli tool your agents can use: s1m - High efficiency knowledge recall from an LLM wiki, powered by Jev

Shubh Srivastava

@idleshubh

JEV is INSANE. 4,000+ people applied for internship at @tryAlanAI. So we built an in house review console to find evidence of real work at scale. Every square is a real SDE intern application > 3,518 applications checked in 4:54 > 20 surfaced for human review > Estimated Jev

TypeSafe launched Jev mid-September 2026. It makes decisions, cannot write a single sentence, and is 20 to 200x faster and 40 to 400x cheaper than frontier models according to…

TypeSafe AI (Jev) decisions for Pi: batched Choice/Score/Noul evaluation tool, terminal playground, and a typed API other extensions build on. ... Install `pi-typesafe` from npm…

LLMs Are Built to Write. Jev Is Built to Decide. | by Dr. Fadi Shaar | AI Mindset | Sep, 2026 | Medium ... # LLMs Are Built to Write. Jev Is Built to Decide. ... Inside Jev,…

The simplest way to write decision workflows in Python, backed by TypeSafe's Jev model ... classifier, decision, jev, routing, transpiler, triage, typesafe ... ## Description…

Jev: a decision-model experiment (TH) ... # Jev: a decision-model experiment (TH) ... 1. ### Jev ฉลาดพอไหม? - บททดสอบความสามารถของโมเดล "ตัดสินใจ" (ตอนที่ 1) ... Jev คืออะไร?…