Loading pattern preview
BlocksArtifacts
JSON Render Three.js
JSON Render Three.js
AI-generated 3D scenes using @json-render/react-three-fiber. Describe environments, meshes, and lighting to stream live Three.js renders you can orbit immediately.
Use this when users describe a 3D scene in plain language and need it streamed as a live React Three Fiber render they can orbit right away.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Turn natural language into orbitable Three.js scenes
- Stream JSON specs into React Three Fiber without reloads
- Compose meshes, lights, cameras, and controls from a catalog
Use cases
Products and workflows this pattern is designed to support.
- 3D concept explorers
- Product hero stage builders
- Immersive storytelling demos
- Rapid prototyping for motion shoots
Compare with
Similar patterns, and when each one is the better fit.
JSON Render ReactUse this when you want to define your own small component catalog and render streamed JSON specs with the base @json-render React renderer.
JSON Render Data TableUse this when you are building a prompt-driven data grid with search, filter, pagination, and bulk action toolbars generated from a json-render spec.
JSON Render ShadcnUse this when prompts should render only from a fixed catalog of shadcn components provided by the @json-render/shadcn package.
JSON Render RemotionUse this when you are prototyping prompt-to-video features, such as intro or slideshow drafts, and want output that plays in Remotion.
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: AI_GATEWAY_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
AI_GATEWAY_API_KEYGet key
Capabilities
AI SDK APIs
streamTextgatewayProviders
Claude
External services
Upstash
Files added
10 files
app/page.tsxapp/layout.tsxapp/api/json-render-threejs/route.tscomponents/json-render-demo.tsxcomponents/empty-state.tsxlib/catalog.tslib/registry.tsxlib/rate-limit.tslib/request-utils.tsREADME.md
Dependencies
17 total
npm packages
14AISDK@json-render/core@json-render/react@json-render/react-three-fiber@react-three/drei@react-three/fiberUpstashlucide-reactNext.jsReactsonnerthreeZodmotion
Registry components
buttonemptyinput
Critical files
3 files
lib/catalog.tsDefines the Three.js component catalog using threeComponentDefinitions for meshes, lights, helpers, Text3D, and camera controls.
lib/registry.tsxMaps json-render component names to their React Three Fiber implementations so ThreeCanvas can render streamed specs.
json-render-threejs/route.tsStreaming API endpoint that rate limits requests, enriches catalog.prompt() with 3D-specific guidance, and calls streamText via gateway("anthropic/claude-sonnet-4.6").
Requirements
- Complexity
- Advanced
- Setup time
- ~7 minutes
- Node
- 24+
- Memory
- 512MB
Upstash Redis
