I have aPBS server and my friend in a different geographic region has one. I backup to mine and he backs up to his. Mine syncs my backups to a data so l store in his, and his summer backups to a data store in mine. These are our offsite backups.

To be clear, we’re syncing our proxmox VM backups. But Proxmox Backup Server also has a client app, so I also back up my workstation to my PBS and it also syncs to the remote PBS.

It’s important to me to use devices and services that are local only, but I could only find such robot mowers that are beyond my skillset to build. I have no interest in building and 3d printing and flashing firmware, etc. I just want to buy a device and use it, without my privacy being sold. I’m willing to pay, but I guess there’s not enough market for anyone to build/sell that.

Same with vacuums, by the way. I have a dreametech model that’s supported by Valetudo, but the instructions to flash it sounded difficult and risky enough that I just use it as is, with my home map (and whatever other data it gleans) going through Dreametech’s servers and being sold to whomever.

Sad.

Yeah, my thinking was definitely biased to my environment. I selfhost llama.cpp so even if Hivekeep doesn’t require significant resources, whatever LLMs it runs will use my hardware.

agents are activated serially per message, not all firing at once, and the persistent memory is exactly what keeps each context small

It sounds like I need to try it!

This looks interesting, especially the persistent memory. I want to try it out but it seems likely to me that multiple simultaneous agents would require significant hardware. Even if they were serially activated, reloading contexts with each switch would take time. I have a pretty beefy GPU and experience significant (almost ridiculous) slowdown when opencode runs 2 subagents simultaneously.

But perhaps the memory storage/lookup keeps contexts very small?

Anyway, I can’t find any mention in the repo or docs what the suggested minimum hardware is.

I’m glad this conversation is happening.

LuisCore is a X, X X for X X at scale: an X for X, X, and X X across X. The X X is luiscore.com, with X at X and X.

I often feel like that’s what I’m reading, but I assume that enough people understand it that the trend goes on. Like maybe I should just not read articles about tech any more.

I really like the quote “If you can’t explain it to a six-year-old, you don’t really understand it yourself” (possibly by Feynman). I’d like this to be how the works works, but it would mean that most people don’t understand what they’re talking about or they’re intentionally being pretentious and exclusive. But technical things do get made, so it seems more likely that I just don’t understand.