PediatricsAI Boilerplate

SvelteKit plus Capacitor boilerplate for a pediatric pre-visit summary app with a future on-device AI path.

Included

• SvelteKit + TypeScript app shell
• Capacitor Android project in android/
• Static adapter setup so the web app can be bundled into Capacitor
• Capacitor plugin bridge named PediatricsAiEdgeAi
• Mixed Java/Kotlin Android scaffold for a future LiteRT runtime
• Gemma 4 E2B LiteRT model config and download script

Commands

npm run dev
npm run check
npm run test
npm run model:plan
npm run model:download:android
npm run mobile:sync
npm run mobile:open:android

Key Entry Points

• src/routes/+page.svelte: starter mobile shell UI
• src/lib/features/edge-ai/: TypeScript bridge contracts, runtime helpers, and store
• scripts/download-gemma.mjs: Gemma model downloader for Android or web assets
• android/app/src/main/java/com/pediatricsai/previsit/MainActivity.java: Capacitor plugin registration
• android/app/src/main/java/com/pediatricsai/previsit/edgeai/: Java/Kotlin native bridge boilerplate

Gemma Model Setup

• Repo: litert-community/gemma-4-E2B-it-litert-lm
• Android file: gemma-4-E2B-it.litertlm
• Web file: gemma-4-E2B-it-web.task
• Local token source: HF_TOKEN in your shell or .env.local

Example:

export HF_TOKEN=your_huggingface_token
npm run model:download:android

The download target is ignored by git and lands in android/app/src/main/assets/models/.

Next Integration Step

When you send the main workings and UI, the next pass can wire:

• the pediatric summary workflow
• retrieval and RAG orchestration
• real LiteRT model loading
• Gemma prompt formatting and response parsing

sv

Everything you need to build a Svelte project, powered by sv.

Creating a project

If you're seeing this, you've probably already done this step. Congrats!

# create a new project
npx sv create my-app

To recreate this project with the same configuration:

# recreate this project
npx sv@0.15.1 create --template minimal --types ts --add prettier eslint vitest="usages:unit" sveltekit-adapter="adapter:auto" --install npm .

Developing

Once you've created a project and installed dependencies with npm install (or pnpm install or yarn), start a development server:

npm run dev

# or start the server and open the app in a new browser tab
npm run dev -- --open

Building

To create a production version of your app:

npm run build

You can preview the production build with npm run preview.

To deploy your app, you may need to install an adapter for your target environment.