json-render: The Generative UI Framework for Dynamic Interfaces
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
json-render is a powerful Generative UI framework that allows developers to create dynamic, personalized user interfaces from natural language prompts. It ensures reliability by constraining AI-generated output to predefined components and actions, offering a predictable and safe way to build cross-platform UIs.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
json-render is an innovative Generative UI framework developed by Vercel Labs. It empowers developers to build dynamic and personalized user interfaces by leveraging AI to generate UI specifications from natural language prompts. The framework ensures reliability and predictability by allowing developers to define a catalog of components and actions, effectively setting guardrails for the AI's output. This approach combines the flexibility of AI generation with the control and safety of structured UI development.
Installation
Getting started with json-render is straightforward. You can install the core package along with specific renderers for your chosen framework:
# for React
npm install @json-render/core @json-render/react
# for React with pre-built shadcn/ui components
npm install @json-render/shadcn
# or for React Native
npm install @json-render/core @json-render/react-native
# or for Vue
npm install @json-render/core @json-render/vue
# or for Svelte
npm install @json-render/core @json-render/svelte
# or for SolidJS
npm install @json-render/core @json-render/solid
# for full Next.js apps
npm install @json-render/core @json-render/react @json-render/next
# for 3D scenes
npm install @json-render/core @json-render/react-three-fiber @react-three/fiber @react-three/drei three
# for terminal UIs
npm install @json-render/core @json-render/ink ink react
# for PDF documents
npm install @json-render/core @json-render/react-pdf
# for HTML email
npm install @json-render/core @json-render/react-email @react-email/components @react-email/render
# for video
npm install @json-render/core @json-render/remotion
Examples
json-render boasts extensive cross-platform support, allowing you to render AI-generated UI specifications across a wide array of environments. Here are some of the supported renderers:
- Web Frameworks: React, Vue, Svelte, SolidJS, with pre-built shadcn/ui components available.
- Mobile: React Native for native mobile applications.
- Full-stack: Next.js for building complete applications with routes, layouts, and SSR.
- 3D Scenes: React Three Fiber for creating immersive 3D experiences, including Gaussian Splatting.
- Video: Remotion for generating dynamic videos.
- Documents: React PDF for creating PDF documents from UI specs.
- Email: React Email for generating HTML/plain-text emails.
- Images: Render to SVG/PNG output for OG images or social cards.
- Terminal UIs: Ink for interactive command-line interfaces.
The framework's core idea involves defining a component catalog, implementing these components, and then rendering AI-generated JSON specifications. For instance, a basic React setup looks like this:
import { defineRegistry, Renderer } from "@json-render/react";
// ... catalog definition ...
const spec = {
root: "card-1",
elements: {
"card-1": {
type: "Card",
props: { title: "Hello" },
children: ["button-1"],
},
"button-1": {
type: "Button",
props: { label: "Click me" },
children: [],
},
},
};
// defineRegistry creates a type-safe component registry
const { registry } = defineRegistry(catalog, { components });
<Renderer spec={spec} registry={registry} />;
Why Use json-render?
json-render stands out as a Generative UI framework due to several key advantages:
- Guardrailed: AI can only utilize components defined in your custom catalog, ensuring controlled and safe output.
- Predictable: The JSON output consistently matches your predefined schema, guaranteeing reliable results every time.
- Fast: It supports streaming, allowing UIs to render progressively as the AI model responds, leading to a faster user experience.
- Cross-Platform: Build UIs for web (React, Vue, Svelte, Solid), mobile (React Native), video, PDF, email, 3D, and even terminal interfaces from the same component catalog.
- Batteries Included: Comes with 36 pre-built shadcn/ui components, ready for immediate use in web projects.
Links
- GitHub Repository: https://github.com/vercel-labs/json-render
- Docs & Playground: http://json-render.localhost:1355
- Example Dashboard: http://dashboard-demo.json-render.localhost:1355
- React Email Example: http://react-email-demo.json-render.localhost:1355
- Remotion Video Example: http://remotion-demo.json-render.localhost:1355
Related repositories
Similar repositories that may be relevant next.

Mercury Agent: A Soul-Driven AI with Hardened Permissions and Multi-Channel Access
August 12, 2026
Mercury Agent is a sophisticated, soul-driven AI agent designed for continuous 24/7 operation, offering robust permission-hardened tools, intelligent token budgeting, and versatile multi-channel access. It remembers what matters, asks for permission before acting, and runs seamlessly from the CLI, Telegram, or a web dashboard. With 31 built-in tools, Kanban boards, and a SQLite-backed Second Brain memory, Mercury provides a comprehensive and secure AI assistant experience.

Pi Agent Harness: An AI Agent Toolkit for LLMs and Coding
August 10, 2026
Pi Agent Harness is a comprehensive AI agent toolkit designed for building and deploying intelligent agents. It features a unified API for various Large Language Models, a robust agent runtime with tool calling, and an interactive coding agent CLI. This project provides a modular and extensible foundation for developing advanced AI applications.

background-agents: An Open-Source System for Background Coding Agents
August 10, 2026
background-agents is an open-source system designed for running background coding agents. It enables developers to automate tasks, collaborate in real-time, and integrate with various platforms like GitHub, Slack, and Linear. With support for multiple AI models and full development environments, it streamlines development workflows and enhances productivity.

Clowder AI: Orchestrating AI Teams for Collaborative Development
August 10, 2026
Clowder AI is an innovative platform designed to transform isolated AI agents into cohesive, collaborative teams. It emphasizes persistent identity, cross-model review, and shared memory, enabling AI models like Claude, GPT, and Gemini to work together seamlessly. This platform empowers users to orchestrate AI workflows, fostering a new paradigm for AI-driven development and co-creation.
Source repository
Open the original repository on GitHub.