LocalMode UI - Local-First AI Components

What is LocalMode UI - Local-First AI Components

LocalMode UI is an open-source, shadcn-style registry of copy-owned, composable AI UI components for the browser. It includes 100+ React components and 36 installable blocks that run real models on-device. The project is local-first and privacy-first: inference runs entirely in the browser, data never leaves the device, and no server or API key is required. It is MIT-licensed and free to use.

How to use LocalMode UI - Local-First AI Components

1. Configure the @localmode namespace in your components.json file.
2. Install a component using the shadcn CLI, for example: npx shadcn@latest add @localmode/ui/conversation/message.
3. Components are copy-owned and inherit your existing shadcn/ui theme.
4. For full experiences, install blocks that run real models on-device via WebGPU or WebAssembly.

Features of LocalMode UI - Local-First AI Components

• 100+ copy-owned React components across categories like Conversation, Local-First, Audio, Results, Input Controls, Media & Vision, Data & Documents, Artifacts, Security & Privacy, and DevTools.
• 36 installable blocks that run real models entirely in the browser, including Chat, RAG Chat, Object Detector, Voice Notes, Image Search, and PII Redactor.
• Local-first and privacy-first: inference runs in the browser, data never leaves the device, and no server or API key is needed.
• Works offline after the initial model download; the site is also an installable PWA.
• Browser support: WebGPU-capable browsers (Chrome and Edge 113+, Safari 26+) get GPU-accelerated inference; other modern browsers fall back to WebAssembly.
• Free and open source under the MIT license.

Use Cases of LocalMode UI - Local-First AI Components

• Build private, offline AI-powered web applications with on-device chat, RAG, object detection, voice transcription, image search, and PII redaction.
• Create custom AI interfaces using composable components that integrate with your existing shadcn/ui theme.
• Deploy AI features without backend infrastructure or API costs, ensuring user data stays on the device.

Pricing

LocalMode UI is free and open source (MIT license). There are no paid plans or tiers.

FAQ

Does LocalMode UI work offline? Yes. After the initial model download, inference runs entirely in the browser with no network requests, and data never leaves your device. The site is also an installable PWA, so its shell works offline.

Do I need an API key or a server? No. Blocks run real models on-device via WebGPU or WebAssembly. There is no server and no API key, and installation is client-only.

How do I install a component? Configure the @localmode namespace in your components.json, then run npx shadcn@latest add @localmode/ui/<name>. Components are copy-owned and inherit your shadcn/ui theme.

Which browsers are supported? WebGPU-capable browsers (Chrome and Edge 113+, Safari 26+) get GPU-accelerated inference; other modern browsers fall back to WebAssembly.

Is it free and open source? Yes. LocalMode UI is MIT-licensed and free to use.