DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to use Exo: what you can do with it

What is Exo? exo connects your devices into one AI cluster so you can run models larger than any single device could hold, and run them faster as you add devices. Devices on the same network discover each other automatically, exo splits the model with topology-aware auto parallel and tensor parallelism on an MLX backend, and supports RDMA over Thunderbolt 5. Each device exposes a dashboard and an API compatible with OpenAI Chat Completions, Claude Messages, OpenAI Responses and Ollama.

How do I use it? Install the macOS app from EXO-latest.dmg or with brew install --cask exo; then open EXO and allow Local Network access so it can find your other devices; install EXO on the other Mac, put both on the same Wi-Fi or Ethernet network or connect them with a Thunderbolt cable, and make sure both run the same version. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

3 use cases

Quick start with Exo

  1. Check you have what it needs: For the macOS app: a Mac with Apple silicon and macOS Sequoia 15.1 or later; RDMA over Thunderbolt needs macOS Tahoe 26.2 or later; From source: macOS or Linux with Xcode (on Mac), uv, node and rust.
  2. Open exo-explore/exo on GitHub and read the README and license.
  3. Install the macOS app from EXO-latest.dmg or with brew install --cask exo
  4. Open EXO and allow Local Network access so it can find your other devices
  5. Install EXO on the other Mac, put both on the same Wi-Fi or Ethernet network or connect them with a Thunderbolt cable, and make sure both run the same version
  6. Watch the new Mac appear in the dashboard within a few seconds

These steps come from our top use case, Pool several Macs to run a model none could run alone, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for exo-explore/exo

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Best AI repos for Software and DevOps

About this repo

  • Who it is forMac owners and home lab builders who want to pool several machines to run large open models locally.
  • Why it is hot48k stars, talked about in 2 AI sources we track
  • LanguagePython
  • Sourcegithub.com/exo-explore/exo ยท Back to Hot repos

Requirements

  • For the macOS app: a Mac with Apple silicon and macOS Sequoia 15.1 or later
  • RDMA over Thunderbolt needs macOS Tahoe 26.2 or later
  • From source: macOS or Linux with Xcode (on Mac), uv, node and rust
  • Every device on the same network and the same exo version

Add this badge to your README

Maintain Exo? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/exo-explore/exo.svg)](https://dedupedai.com/use-cases/exo-explore-exo/?utm_source=github&utm_medium=badge&utm_campaign=exo-explore-exo)

HTML 

<a href="https://dedupedai.com/use-cases/exo-explore-exo/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=exo-explore-exo"><img src="https://dedupedai.com/badge/exo-explore/exo.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Exo

What is Exo?

exo connects your devices into one AI cluster so you can run models larger than any single device could hold, and run them faster as you add devices. Devices on the same network discover each other automatically, exo splits the model with topology-aware auto parallel and tensor parallelism on an MLX backend, and supports RDMA over Thunderbolt 5. Each device exposes a dashboard and an API compatible with OpenAI Chat Completions, Claude Messages, OpenAI Responses and Ollama. It is an open-source project on GitHub: https://github.com/exo-explore/exo.

How do I use Exo?

Install the macOS app from EXO-latest.dmg or with brew install --cask exo; then open EXO and allow Local Network access so it can find your other devices; install EXO on the other Mac, put both on the same Wi-Fi or Ethernet network or connect them with a Thunderbolt cable, and make sure both run the same version. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Exo for?

Mac owners and home lab builders who want to pool several machines to run large open models locally.

What can I do with Exo?

3 use cases so far, for example: Pool several Macs to run a model none could run alone; Use your existing AI tools with a local Exo cluster; Run a test cluster next to your main one. Each has steps and a copy-paste agent prompt.

What do I need to run Exo?

For the macOS app: a Mac with Apple silicon and macOS Sequoia 15.1 or later; RDMA over Thunderbolt needs macOS Tahoe 26.2 or later; From source: macOS or Linux with Xcode (on Mac), uv, node and rust; Every device on the same network and the same exo version.

What are alternatives to Exo?

Other hot AI repos in Software and DevOps: ECC, Thinkrail, Superpowers, Deep Infer, Instructor.

Is Exo safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.