Brave Leo adds private AI inference powered by NEAR AI Cloud

October 15, 2026 at 5:49 PMX/TwitterOfficial

Brave's Leo assistant now offers private inference via NEAR AI Cloud: chats using GLM 5.3 Flash run inside hardware enclaves (TEEs) that neither Brave, NEAR AI nor the cloud host can read, and Brave verifies the enclave before sending data.

Private AI inference, now in @brave Leo.

Your chats can stay private, even from Brave. Even from us.

With GLM 5.3 Flash, they run inside secure hardware no one can read, and Brave checks it before your browser sends a word. https://t.co/isIjeu2GkA https://t.co/700l9J7cTw

Original Source

View this content at its original location

View Source