Comment by remote3body

The 'spent 100 hours configuring' part hits home. That fragmentation is exactly why we started building Olares (https://github.com/beclab/Olares).

It’s basically an open-source OS layer that standardizes the local AI stack—Kubernetes (K3s) for orchestration, standardized model serving, and GPU scheduling. The goal is to stop fiddling with Python environments/drivers and just treat local agents like standardized containers. It runs on Mac Minis or dedicated hardware.