YB AI

A local, free, private AI. Your own Muse, on your own machine.

Open YB AI — it runs on your device, free, no account

What it is

YB AI runs on your own device. Four small open models do the work — Qwen3, Qwen2.5-Coder and two Llama 3.2 models — picked per task by a router. No mandatory cloud, no per-prompt cost, no account needed to use it. The brain is one intelligence, one identity: Younesse.

Chat, building, documents, translation, memory, goals, Gmail and settings are all sections inside the one YB AI app — never separate destinations.

Status — 17 November 2026

This page shows only public status. No inbox, no account data, no private content of any kind lives here. What is not yet proven is listed as not yet proven.

How it is built

Spec v3.19 (442 pages) is the contract. Every phase is tested before it ships, and a capability is only claimed after it survives a live test against the machine as it is. The code lives in a private repository; the Founder governs releases.

Last updated 17 November 2026. This page is generated from the project's own record, so it changes when the record changes.