AG-UI.AI — Generative UI Atlas

AG-UI.AI is an independent, bilingual field guide for understanding, choosing, and safely operating a Generative UI stack. It maps interaction protocols, declarative UI specifications, embedded host surfaces, renderers, and integration frameworks without treating different architectural layers as mutually exclusive competitors.

Independent community resource. This project is not affiliated with or endorsed by the maintainers of AG-UI, A2UI, OpenUI, json-render, MCP, CopilotKit, or other technologies it covers.

What ships in the first release

• English and Simplified Chinese routes at /en and /zh
• four-layer ecosystem map and seven core technology profiles
• comparison matrix and deterministic stack selector
• three learning paths and a no-key AG-UI event stream lab
• generated /catalog.json, /search-index.json, /feed.xml, sitemap, robots, canonical and hreflang metadata
• GitHub-first community workflow with source verification and weekly drift checks

Local development

Requires Node.js 22.13 or newer.

npm install
npm run dev

The local site opens at http://localhost:3000. Content is compiled before development and production builds.

Quality gates

npm run content:validate
npm run security:audit
npm test
npm run lint
npm run build
npm run check:bundle
npm run test:render

npm run check:sources inspects declared upstream GitHub repositories and writes a review report. It never edits published content. npm run check:bundle enforces first-party client JavaScript and CSS budgets; Core Web Vitals are measured again against the private deployment before public launch.

Content model

Markdown lives under content/{en,zh}/{technologies,learn,updates}. A bilingual pair must keep the same filename and slug. Raw HTML is not rendered. Each technology profile records its ecosystem layer, maturity, source authority, decision boundaries, composition options, license, official sources, and last verification date.

See CONTRIBUTING.md and EDITORIAL_POLICY.md before changing guidance.

Release evidence and the public-launch decision boundary are tracked in docs/LAUNCH_CHECKLIST.md.

Licensing

• Source code: MIT
• Original editorial content: CC BY 4.0

Third-party names remain the property of their respective owners; see TRADEMARKS.md.