MacPaw partners with Liquid AI on on-device Mac AI

MacPaw and Liquid AI announced a strategic, long-term partnership on August 5, 2026. The two companies will co-develop a technology stack for running AI locally on macOS.

Liquid AI, an MIT spin-out, will build and fine-tune its Liquid Foundation Models (LFMs) specifically for macOS assistant tasks. Those models will be paired with two MacPaw technologies: Elix, its on-device inference layer, and Mnemos, a memory layer that lets an assistant keep context across interactions. The first product to use the stack is Eney, MacPaw's AI assistant for macOS. According to the companies, its core work will run locally on Apple silicon, and cloud models will stay available for tasks where they are the better tool. Results were expected "later this year."

The companies say no Mac product has previously combined on-device intelligence, persistent memory and native macOS task execution. They give no benchmarks, model sizes or hardware requirements to back that up.

"We believe intelligence should live where people work: private by design, fast by default, and be able to reach the cloud when that's the better tool," said MacPaw CEO Oleksandr Kosovan. Liquid AI CEO Ramin Hasani said the deal "will bring efficient, private, on-device LFMs to millions of Mac users."

The models, inference framework and memory layer are meant as shared infrastructure. Once they ship in Eney, they "could eventually" be offered to Mac developers through Setapp, MacPaw's software marketplace, though no timeline was given. The announcement does not disclose financial terms. Liquid AI says its models are already used by Mercedes-Benz, Insilico Medicine and Shopify.