MacPaw is bringing on-device AI to its Mac assistant, Eney. The company partnered with Liquid AI to build a local intelligence stack designed to run on your Mac, not in the cloud.
The partnership pairs Liquid AI’s foundation models with MacPaw’s own inference and memory technology. Eney will be the first product to get the upgrade, and results are expected later this year.
MacPaw’s on-device AI stack, explained
AI assistants are everywhere these days (hello, Siri AI), but most still rely on sending your data to someone else’s servers. MacPaw, like Apple, is betting there’s a better way.
By partnering with Liquid AI to build purpose-trained models that run directly on your Mac, the company wants Eney to be faster, more private and smart enough to remember how you work without constantly sending your data to the cloud.
MacPaw describes Eney, which the Ukraine-based developer introduced last year, as an “OS extension for Macs.” It lives on your desktop and helps you get things done through simple, conversational commands. Eney’s features are powered by built-in commands and a variety of integrations, including native MacPaw apps and third-party software.
MacPaw and Liquid AI are jointly building the technology from the ground up. Liquid AI is fine-tuning the foundation models for Eney’s specific tasks that will run locally through Elix — MacPaw’s inference engine. But cloud models will still be available for jobs better suited for them.
An approach similar to Apple’s
Image: Liquid AI
MacPaw is also building Mnemos, a memory layer for Eney. This will enable the assistant to remember context across sessions. The idea is that Eney will become more useful the longer you use it.
“After almost two decades of building software for the Mac, MacPaw is evolving its standalone products into a connected ecosystem, with AI as a core technology we build and own,” said Oleksandr Kosovan, CEO and founder of MacPaw, in a press release about the partnership with Liquid AI. “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.”
Apple uses a similar approach, handling as many tasks on-device as possible and handing off more complicated queries to Private Cloud Compute.
Eney has been moving in this very direction for a while. MacPaw shifted the assistant to a local model last December. That move kept reasoning and conversation history on the device itself whenever possible.
But with this new partnership, Liquid AI will be supplying purpose-built models rather than MacPaw bolting on a generic third-party option.
Liquid AI isn’t new to this kind of work. Its models already power on-device features for Mercedes-Benz, Insilico Medicine and Shopify.
What comes next for Setapp developers
Apple already allows developers to build with their own on-device models. Liquid AI CEO Ramin Hasani told TechCrunch that Liquid AI’s approach is different.
He said it focuses on task-specific performance and has a customization layer that helps the model improve from user input.
MacPaw’s ambitions don’t stop at bringing on-device AI to Eney. Once the stack is proven, the company plans to open it up to developers on Setapp, its Mac app subscription app service with more than 150,000 paying users. Setapp gives subscribers access to more than 270 Mac apps, starting at $14.99 a month.
If Setapp apps eventually tap into on-device AI directly, it would let Eney understand more of what’s happening in those apps.
MacPaw is also testing credit-based pricing for AI features on Setapp, with usage metered by task complexity. Kosovan said the platform will also offer access to other cloud models in the future.
MacPaw and Liquid AI did not disclose pricing or a date for the wider developer rollout. For now, the partnership’s first real test will be Eney later this year.
Anurag Chawake is a tech-focused writer specializing in smartphones, apps and consumer technology. His interest in computers began during the Windows 98 era, eventually leading him to explore everything from operating systems to mobile devices and PC hardware. Anurag previously contributed to The Indian Express, covering Apple, Android, gaming and the broader technology landscape.
