Four open-source repos for generative UI built with Jev
Behind a motion video said to leak from Disney designers are four open-source projects that use Jev to select components rather than generate UI, including Shapeshift and Vercel's json-render.
Disney cartoon designers accidentally leaked this motion video repos and its f*ckin crazy They are building this with Jev. A tiny AI model that doesn’t write. It just picks the right component in milliseconds. 4 repos to steal from: > Shapeshift - one input that morphs into the right UI as you type: event card, checklist, timer, color picker, poll. One Jev call answers 14 questions in parallel. Runs offline without an account bun install && bun dev -> http://github.com/anishfn/shapeshift > json-render by Vercel Labs - generative UI from your own component catalog. Its experimental Jev mode picks which components and actions the screen should contain Try it: http://json-render.dev/playground -> "Jev (Experimental)" -> http://github.com/vercel-labs/json-render > unclutter by Kitze - a browser extension where Jev decides element by element what's clutter and wipes it off the page -> http://github.com/kitze/unclutter > jev-canvas - draw on a tldraw canvas with your voice and a pointing finger. Jev decides the action, the target and where it goes -> http://github.com/gaborishka/jev-canvas Here's why it works: Jev never generates your UI. It only chooses from components you already built. Your design system stays intact, and the model can't hallucinate a broken button. The designer's job is shifting from drawing every screen to building the pieces and letting the interface pick. More Jev projects: http://github.com/yibie/awesome-jev Save this for your next redesign.
This post quotes another post: x.com/thegreatest_sv/status/2102802378378621355