rathermercurial.eth

It's an existing hermes/agent memory plugin that offers a lightweight, searchable alternative to memory.md (and is smaller then a typical self-hosted memory engine like Hindsight or Honcho) github.com/mnemosyne-oss/mnemosyne Here's a great vid from @wanderloots.eth on the topic: youtu.be/R1TNGOZAOZs?si=RfyrDkgtGLfaStoZ Discoverability for good hermes tools is very unsolved :( Like with how many agents use lcm-x and other good context engines, yet Nous does fuck all to help users find them. And many builders have a negative view of community plugin directories as being mostly-slop.

Yes, and I believe it's a trademarked commercial application. Here's the oss version:

RIP Dolores Huerta

Not trippin. AMD makes a separate "AI Engine" (the part that's supposed to run the models) which is a separate wafer from your GPU's. amd.com/en/products/processors/laptop/ryzen/ai-300-series/amd-ryzen-ai-max-385.html My main reason for mentioning it is that my setup is solar-assisted also, and I also setup my Ai mini-pc (minisforum um890) in gpu-only mode when I got it. It was running at 1/3 speed and using 3x power than it should have on paper. Anyway not a performance nitpick so much as "I've got one of those new tools too, and I think you're holding it the wrong way"... Like you said, unified systems are new and there's a lot of misconceptions to unlearn (like skeumorphically selecting a gpu-only runtime even when we paid the extra $ for an AI CPU)