On-device embeddings

Ternlight

An embedding model in 7 MB.
Runs on your CPU. No API.

Drop it in, embed text in milliseconds, and never call a server.

Use it

Three lines to semantic search

Ships as a single npm package. No model download step, no server.

$npm install @ternlight/base

example.js

import { embed, similar } from '@ternlight/base';

similar('I want my money back', docs, { topK: 3 });
// → ranked matches · ~5 ms · zero network

Pick a model, index React's docs in your browser, then query them: no server, no API.

Choose a model & index

Same API. Pick a tier, then index.