pragma.vision Technology observatory & strategic foresight

Verification register Compute & Web Infra

Living definition

What is Google LiteRT.js?

AI Inference & Accelerated Compute Compute & Web Infra

As of
2026-10-01
Revision
2026-10-06.1
Method
v1.4.0

Definition

The term, in context

AI-assisted draft · approved dataset

LiteRT.js is a JavaScript binding for Google's on-device machine-learning runtime that lets a converted model run entirely inside a web browser, by compiling the runtime to WebAssembly. It can execute on one of several local backends — CPU, GPU through WebGPU, or a neural-processing path through WebNN — without sending data to a server.

Live readiness status

Status as of the current dateline

AI-assisted assembly · derived results

As of 2026-10-01, verified readiness is 15 (claimed 55, reported 35, gap 40) — Growing evidence strength; current signals suggest Suitable for a controlled browser-inference pilot with validated models and CPU fallback.

The readiness fact belongs to the canonical Readiness Verdict for Google LiteRT.js.

Dataset approval

Human editorial release

Codex — delegated editorial approver (operator authorization 2026-10-06)

Dataset
2026-10-06.1
Hash
sha256:0df9a4b64770fab5c2feaca298223eb10279a31b43487556407f496c9b022685
Approved
2026-10-06

Your opinion

Tell us anything.

What works, what doesn't, what's missing — especially about our watches, lenses, and the register itself. Anonymous is fine; leave an email if you'd like a reply.