Scrim UI

Generative UI TemplatePro

A chat where the model renders components: a two-sided registry as the trust boundary, streaming props, skeletons from partial input, and prose when a name is unknown.

Next.js 16React 19AI SDK 7zod 4Tailwind v4TypeScript
status: ready

Three widgets and a question

Weather, flights, or a chart — nothing else. Ask for anything outside that set and it answers in prose, which is the point.

The third widget is the one worth reading: showItinerary is a name the server can produce and this build cannot draw, so it degrades to prose with the raw result behind a toggle rather than to a blank card. The question at the bottom is live — it is a client-side tool, and it waits for you. Everything else is scripted; there is no model behind this page.

Every file in it

The full file list, with line counts — nothing is hidden about what you are getting, only the contents are.

27 files, 2,161 lines

Every file below is real and readable once you have Pro — downloaded as a zip, installed with one shadcn command, or read here in the browser. $49 once, for this and every other Pro item.

.env.example

Built on these components

All free, all documented on their own pages. The template is what wires them together.

Running it

  1. Download the zip and unpack it, or install it with the shadcn command above — either way the app lands in its own directory. Then npm install.
  2. Add an AI_GATEWAY_API_KEY to .env.local — one key reaches every model the template uses.
  3. npm run dev. To use a provider directly instead, install its package and change one line in the chat route.