No API calls. No server costs. Complete privacy. EdgeMind runs powerful AI models directly in your browser using WebAssembly and ONNX Runtime.
Optimized quantized models that run entirely on-device
666M parameters
Embeddings
STT + TTS
No per-token billing. No API calls for inference. Run locally.
Data never leaves your device. No server-side processing.
Works without internet after initial model download.
No network round-trips. Instant responses.
Optimized quantized ONNX models fit in memory.
Browser, Node.js, React Native, edge runtime.
Install the SDK and start building AI-powered applications with just a few lines of code.
npm install @edgemind/jsconst client = new EdgeMind();
const { content } = await client.llm.chat({ messages: [...] });import { EdgeMind } from '@edgemind/js'
const client = new EdgeMind();
await client.models.load('taskwizer-llm');
const { content } = await client.llm.chat({
messages: [{ role: 'user', content: 'Hello!' }]
});