typesafe-ui
Community shadcn-style React components and interactive lab for building TypeSafe AI interfaces.
Overview
TypeSafe UI is an independent community project offering reusable React components and interface patterns for TypeSafe AI apps, built with shadcn/ui (base-nova style), Base UI and Tailwind v4. It is a Turborepo and pnpm workspace with a Next.js component browser, source previews, install and import examples, and an interactive Lab of scenes.
The components live in a private workspace package, not a published npm package, so you port what you need into your own app. The README notes that previews use local fixtures and that a visual live-state indicator is not proof of a real Jev call. No credentials are needed to browse. Commands are run through Turborepo with a pinned pnpm version, and the lab supports dark mode and component search from the keyboard.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | UI components for displaying Choice, Score and Noul answers(inferred) | — |
How it works
- Run the workspace locally with pnpm dev.
- Browse components and Lab scenes.
- Port the needed components into your app.
- Wire them to real Jev responses.
Strengths
- Ready-made UI patterns for typed decisions.
- No credentials needed to explore.
Caveats
- Not a published package; components must be ported.
- Previews use fixtures, not live calls.
- Community project.
Getting started
git clone https://github.com/TypeSafeAI/typesafe-ui.git && pnpm install --frozen-lockfile && pnpm devAt a glance
- Type
- Project
- Status
- beta
- Language
- TypeScript
- Runtime
- Next.js / React
- Has code
- yes
Use cases and integrations
How curated lists describe it
Shadcn-style reusable components and blocks for using TypeSafe AI.
hellogumbo/awesome-jev
Frequently asked questions
Can I npm install it?
No, it is a private workspace package; port the components you need.
Do previews call Jev?
No, they use local fixtures.
Is it official?
No, it is a community project.
Related projects
React components that use Jev judgments to choose which component renders, how lists are ordered and whether affordances show.
ProjectbetaTypeScriptVercel Labs' generative UI framework with an experimental compose path where Jev picks which catalog components and actions to render.
ServicebetaTypeScriptVideo demo app showing Jev use cases with the AI SDK and shadcn/ui, from intent search and model picking to chat moderation.
LibraryprototypeTypeScriptPlayground comparing generative UI via an LLM writing json-render specs with Jev choosing and arranging prepared components.
LibraryprototypeTypeScriptLibrary that composes typed Jev judgments like reactive state in React and backend programs, with automatic batching and reuse.
HookbetaTypeScriptPrompt-first music studio where Jev makes every compositional choice, from plan to each bar pattern, rendered as editable MIDI.
ProjectbetaTypeScript