JSON Render React

AI-generated UI from natural language using @json-render. Describe a UI and watch it stream in progressively with shadcn components.

Loading preview…

Problems solved

Technical challenges this implementation handles out of the box.

Products and workflows this pattern is designed to support.

Requirements, wiring steps, and what this pattern adds to your project.

Pick how you want to pull this pattern in — then wire env vars and routes the same way.

1
Install from the preview toolbar
Copy the install command above and run it in your project — Pro patterns include a short-lived token.
2
Add environment variables to .env.local
AI_GATEWAY_API_KEY, UPSTASH_REDIS_REST_URL, UPSTASH_REDIS_REST_TOKEN
3
Point client fetches at your API routes
Replace preview `/view/.../api/...` paths with `/api/...` in the installed files.
4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions for your product — Copy for AI in the toolbar helps seed that work.
5
Run your dev server and open the pattern route
Install dependencies if needed, then start the app and verify responses.

AI SDK APIs

streamTextgateway

Providers

OpenAI

External services

Upstash

10 files

13 total

npm packages

@json-render/core@json-render/react@json-render/shadcnUpstashAISDKlucide-reactNext.jsReactZod

Registry components

buttonemptyinputscroll-area

lib/catalog.ts
Catalog and registry definitions. Uses defineCatalog with shadcn component subset and defineRegistry for React implementations. Exports catalog (for API prompt) and registry (for Renderer).
generate/route.ts
API route for Generate mode. Uses streamText with catalog.prompt() as system prompt, returns toTextStreamResponse() for JSONL-only stream. Includes rate limiting.