Skip to content

What is exo?

exo is free, open-source software from Exo Labs that connects your devices into one AI cluster. It splits large models across machines so you can run models bigger than any single device holds, and with RDMA over Thunderbolt 5 it can make them run faster as you add devices.

exo is one of the most popular local AI projects on GitHub, with more than 48,000 stars as of October 2026.

Devices running exo find each other automatically. exo measures each device’s memory and each link’s speed, then decides how to split the model.

It uses Apple’s MLX for inference and serves OpenAI, Claude Messages and Ollama compatible APIs plus a built-in dashboard for chat and cluster management.

Exo Labs also runs local.ai, which helps you see which models fit which hardware.

Sources

  1. exo on GitHub (README)
  2. local.ai: which models fit your hardware

Updated

Planning local AI for your team?

Tell us about your models, users and hardware. Exo Labs helps teams size, build and run private AI clusters.

Talk to Exo Labs →Download exoCheck your hardware on local.ai ↗