MacPaw partners with Liquid AI for on-device AI inference in its app store

Ukrainian software company MacPaw has announced a partnership with Liquid AI to power its products with AI models that run locally on devices. The company eventually plans to make the underlying technology available to third-party developers.

MacPaw is currently developing an AI assistant called Eney, unveiled last year. As part of the new effort, it wants to build a locally hosted version of the assistant. Liquid AI will develop an on-device inference system named Elix and a local memory system for this purpose.

Liquid AI co-founder and CEO Ramin Hasani said the company selects a hardware-tailored architecture before training its models. He argued this approach delivers the most efficient version of intelligence that runs directly on the device, with benefits including privacy and security.

MacPaw CEO Oleksandr Kosovan noted that locally hosted AI models will also give users the ability to run assistants and agentic workflows offline. He added that the platform will also give developers access to other cloud models, such as those from Google, making it a one-stop shop.

Apple already offers its own local models to developers, but Hasani said Liquid AI’s models focus on performance across different capabilities. The company is also building a customization stack around its models, allowing them to improve over time with user input.

MacPaw plans to focus more on AI apps for its subscription-based SetApp store, which has more than 150,000 paying users. Once the local processing architecture is finalized, MacPaw wants to open it up so developers can use on-device inference in their apps.

The company is also experimenting with credit-based pricing for the store. In this model, users can perform a certain number of AI operations based on the credits they hold and the complexity of the task.