Kev lets you run small AI models on your own computer to sort requests, choose between…
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Kev lets you run small AI models on your own computer to sort requests, choose between options, and rate things like urgency. Built by Jared Palmer on Qwen3.5, it comes in three sizes: 0.8B, 4B, and 9B parameters. The repo includes model weights, training code, evaluation data, and a web playground. Give it a customer message, for example, and ask: → Which team should handle this? → Does it need urgent human attention? → How frustrated is the customer? Kev answers these questions in one request. Each question shares the original message but can't read the other questions. It returns probab
Posted by Sandhya (1.3k followers) 1 h ago · 3 likes · 194 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- PSA: new case study unlocked 🔓 — @mynameisyahia
- in case you were wondering this is how i prompt — @hraness
- 🔥太全面了吧！别再问Jev 到底能干啥了！全网 68 个实战案例 + 自带 Skill，直接喂给你的 Agent！ — @NFT_Chen
- One agent is useful. Coordinating the work around it is the hard part. — @DanKornas
- Spent the weekend deep-diving into WorkSwarm's source code and honestly, the… — @HeyZoyaKhan
- Introducing the fastest AI icon search on the web 😱. — @haxzie_
- "RRSI: Regularized Recursive Self-Improvement of Agent Harnesses" — @askalphaxiv
- AI coding agents can write code. Proving the work is complete is the harder part. — @DanKornas
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 22.2k posts from 5k X accounts over the last 21 days, 2.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 07:44 UTC. Full method.