Liquid AI's LocalCowork Runs a 24B-Parameter Agent on a MacBook — No API Calls Required

An open-source AI agent with 67 tools, 385ms tool selection, and 80% accuracy runs entirely on-device. Liquid AI is making the case that the next generation of agents doesn't need the cloud.

Liquid AI released LocalCowork, an open-source AI agent built on its LFM2-24B-A2B hybrid architecture that runs entirely on a MacBook without any network calls. As @liquidai detailed, the agent handles 67 tools with an average tool selection latency of 385 milliseconds and 80% tool accuracy — numbers that would have been respectable for a cloud-hosted agent a year ago.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Proin pharetra nonummy pede. Mauris et orci. Aenean nec lorem. In porttitor. Donec laoreet nonummy augue. Suspendisse dui purus, scelerisque at, vulputate vitae, pretium mattis, nunc. Mauris eget neque at sem venenatis eleifend. Ut nonummy. Fusce aliquet pede non pede. Suspendisse dapibus lorem pellentesque magna integer malesuada.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief