vercel-labs/json-render

The Generative UI framework

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 59 minutes ago
Added to GitGenius on September 1st, 2026
Created on January 14th, 2026
Open Issues & Pull Requests: 98 (+0)
GitHub issues: Enabled
Number of forks: 875
Total Stargazers: 16,106 (+0)
Total Subscribers: 56 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 11.0 hours
Mean response time: 7.2 days
90th percentile: 22.7 days
Tracked items: 56

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 98% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 85% of tracked open issues have had no activity in three months, so the open count overstates what is actively being worked. Only 10% of issues opened in the past year have been closed. Three people close 70% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 62
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 164 days
Stale 30+ days: 57
Stale 90+ days: 51

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • ci/cd (1)
  • dependencies (1)
  • documentation (1)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

json-render is a Generative UI framework that enables AI to generate dynamic, personalized user interfaces from natural language prompts while maintaining strict safety constraints through predefined component catalogs.

The tool solves the problem of reliably generating UIs from AI models without sacrificing predictability or safety. Rather than allowing AI to generate arbitrary code or markup, json-render constrains generation to a developer-defined catalog of components and actions. The AI produces JSON specifications that match your schema, which are then rendered across different platforms. The framework supports progressive rendering, allowing interfaces to display as the model streams its response rather than waiting for completion.

json-render suits projects where you need AI-driven interface generation but require guarantees about what components will appear and how they will behave. It works across React, Vue, Svelte, and Solid on the web, as well as React Native for mobile applications, all from a single component catalog. The framework includes thirty-six pre-built shadcn/ui components ready to use immediately, reducing setup time for common UI patterns. This approach is particularly valuable when you want to offer generative capabilities without the unpredictability of unconstrained AI output.

The project maintains active engagement with its user base, with nearly all open issues originating from adopters rather than the core team, indicating substantial real-world usage. Maintainers respond to new issues and pull requests within a day. Development activity concentrates on continuous integration and documentation work, suggesting the team prioritizes reliability and user guidance as the project matures.