Native Shell
Native Shell: AI-generated UI, native in your app, on every platform. Apps on iOS, Android, macOS, Windows and Linux, GPUI apps and web pages load signed, sandboxed TSX modules at run time and draw th
Generative UI cards for your chatbot, installed with the shadcn CLI.
Developer toolsTypeScript · JavaScriptGitHub @jefferypippittOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
UI cards for your chatbot
Taken from the repository README
Loading the full README.
Read the full README ↗genuicn is a shadcn registry of generative UI cards that render inside a chatbot. The chat uses json-render, so the model writes a small spec that names a card and its props, and the card fetches its own live data.
These cards are ready to install:
The other cards in the docs sidebar are planned. To add the chat and cards to your own Next.js app, follow the Installation page at /docs/installation.
Some cards call services that ask for credit, and some call endpoints that have no public API. The Installation page lists which cards these are. Check each service's terms before you ship.
This repo is the docs site and the registry source. We use pnpm.
pnpm install
pnpm dev
Then open http://localhost:3000. The docs playgrounds replay recorded chats along with the data each card loaded, so browsing the site calls neither the model nor the quote and weather services.
To try /api/chat locally, copy .env.example to .env.local and add an AI_GATEWAY_API_KEY from the Vercel dashboard under AI Gateway, API Keys.
pnpm registry:build runs shadcn build, which writes the installable items in registry.json to public/r/. pnpm build runs it before next build.pnpm record <name> "<prompt>" sends one prompt to the running dev server and saves the reply to content/recordings/<name>.json for a docs playground, together with the data each card in the reply loaded. It needs pnpm dev running and the key in .env.local.pnpm record:data [name...] refreshes the card data in every recording, or in the ones named, without calling the model. It needs pnpm dev running. Run it before a deploy to bring the playground numbers up to date.pnpm check and pnpm fix run Ultracite.The changelog lives in content/changelog/, one file per month. The format is in content/changelog/README.md.