Dev Radar
Support
LiveUpdated 2026-10-30 20:22 UTC

exo

exo — Run frontier AI locally. Contribute to exo-explore/exo development by creating an…

exo is Run frontier AI locally. Contribute to exo-explore/exo development by creating an account on GitHub.. It is ranked #305 on the Dev Radar, in AI dev tools, first seen 26 days ago and shared in 3 posts (12k views).

Visit github.com

GitHub - exo-explore/exo: Run frontier AI locally. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation exo Public Notifications You must be signed in to change notification settings Fork 3.6k ( 3.6k ) Star 47.9k ( 47.9k ) You must be signed in to star a repository About Run frontier AI locally. Resources…

What people said about exo on X

手头那些吃灰的设备,先别急着嫌它们没用——exo 这个开源项目,能把它们攒成一个 AI 计算集群,GitHub 上 star 已经 4 万多,显卡堆到肉疼的日子可以先缓一缓。 它思路挺野:把所有设备的算力捏成一块虚拟 GPU。 1️⃣ iPhone、iPad、Mac、树莓派,只要挂在同一个局域网里就能用,不挑设备 2️⃣ 不用手动配,节点自动发现,p2p 直连,推理全在本地跑,数据不出门 3️⃣ 它盯着每台机器的实时性能和网络状况,自己决定模型怎么切,尽量把整体速度拉满 最狠的是有人拿 4 台 M3 Ultra Mac Studio,真把 DeepSeek v3.1 671B 这种巨无霸跑起来了,接上 RDMA over…

— @bkdgiffug, 1 days ago · 76 likes · see the post

家里有两三台 Mac,想在本地跑个大点的模型,单台的内存总是差一截。 exo 能把这些设备连成一个 AI 集群,一台装不下的模型,拆开分给几台一起跑,已狂揽 4.8 万多 Star。 设备之间会自动发现,不用手动配置,它会看每台机器的内存和网速,自己决定模型怎么切。 GitHub:http://github.com/exo-explore/exo 设备越多跑得越快,官方给的数据是 2 台提速 1.8 倍,4 台提速 3.2 倍。 README 里放了 4 台 Mac Studio 一起跑 6710 亿参数 DeepSeek v3.1 的实测,几台机器摆在一起跑模型,画面挺有冲击力。 Mac 上有现成的…

— @GitHub_Daily, 9 days ago · 40 likes · see the post

旧设备别急着吃灰,组个 AI 集群还能继续发挥价值。 开源项目 exo,可以把局域网里的多台设备连起来协同运行 AI 模型,不必一上来就砸钱买高端显卡。 ⚡ 设备协同:支持 Mac、iPhone、iPad、树莓派等设备 🔗 自动组网:自动发现节点,根据设备状态分配模型任务 🔒 本地推理:模型在自己的设备上运行,减少对云端服务的依赖 项目还展示过多台高性能 Mac 协同运行超大模型的案例。不过,实际速度取决于设备配置、内存和网络条件,普通旧设备不一定能跑动大模型。 想折腾本地 AI 集群的,可以研究一下。 🔗 GitHub:https://github.com/exo-explore/exo

— @bkdgiffug, 13 days ago · 1 likes · see the post

Alternatives to exo

exo in numbers

FAQ

What is exo?

Run frontier AI locally. Contribute to exo-explore/exo development by creating an account on GitHub. It was first shared on X 26 days ago and is ranked #305 on the Dev Radar.

Is exo free?

It is open source.

Who shared exo?

2 accounts on X, including @bkdgiffug, @GitHub_Daily, in 3 posts totalling 12k views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:22 UTC. Full method.