Made a little village that you can join 😄
It grows as more people move in, and new things unlock at each milestone
(still WIP, btw 😄)
https://t.co/u6px34T43I
Apple had an app on the App Store last night that turns your Mac into a private AI server. A few hours later it was gone.
Harbor runs open-weight models on Apple silicon and pools memory across Macs over Thunderbolt 5. No command line.
The translation in my X tools runs a small open model (GLM 4.7 Flash) on Cloudflare. That's the kind of job I'd happily move to a Mac on my desk, if I trusted my home internet to stay up 😅
Apple is working on a new app called Harbor
Harbor turns your Mac into a private AI inference server. Run open-weight models locally on Apple silicon—your data never leaves your hardware, and nothing reaches the cloud. Connect multiple Mac computers over Thunderbolt 5 to pool unified memory, enabling large models and higher concurrency that a single computer can handle alone.
Set up in minutes, not hours Harbor automatically detects your devices over Thunderbolt 5 to form a cluster. Plug in, start, and you’re running—no manual configuration, no command line, no infrastructure expertise required.
Download and run models directly Browse, download, and load open-weight models from within the app. Harbor handles model management so you can focus on the work, not the setup.
Cluster for scale Connect two or more Thunderbolt 5-capable Mac computers and Harbor pools their unified memory into a single inference resource. Run models that exceed any single computer’s capacity, or serve more concurrent requests across your cluster.
Harbor is currently in a private preview under the Claris brand.
A tale in 2 parts:
- User downloads app and starts trial
- They find a bug and send me an email!
- I fix the bug
- They purchase the app
I freaking love this!
All my side projects are on a subdomain 😄 Except for those that I'm now deploying on Cloudflare
https://t.co/jbtWKjOyXE
https://t.co/THgIotY9KR
https://t.co/Zw6ENHiHwB
https://t.co/65iNSGclQH
https://t.co/EyF09PBzLu
https://t.co/gUVRWwsTCP
https://t.co/XNPfYrsHKV
https://t.co/RYHBEG2BfB
and too many more 😂