

Yes and no. I use llama server to run my own local models, and then open ice to monitor it. From there a lot of open source services host MCP servers which then can help integrate. I then use it to auto write the documentation on the layout so next time when I say “go to the ZigBee controller and tell me…” It knows first go to the docs, it remembers where it is and any useful commands, then continues on.








I’ve been doing that, I use kubernetes, so kagent. Sammy at first but it calmed down. It’s neat to have it auto triage something that went down or failed, parse the logs, look at the hardware and health and then tell me when it’s time.
GPUs are sparse but I run on a 3090, VRAM is king. If you have one for a server it’s not horrible to spin up an llm