Danny Beach

People who have extensively used OpenClaw and Hermes: Please give me your most honest assessment of pros and cons between the two below.

@andrewchen Spark rack gang! Still waiting on more parts to finish up mine.

built my openclaw a new home (mac mini + nvidia dgx spark in a 8U mini rack)

@NVIDIAAIDev @NVIDIA_AI_PC Also would recommend this 3D-printed mount if you have one of these 10-inch racks: etsy.com/listing/444558…. The same seller also has a fan mount.

@NVIDIAAIDev @NVIDIA_AI_PC I have mine sitting next to the 4090 build OpenClaw started on, then migrated to the spark once I got it also had to give it a home and still waiting on more rack parts.

Love seeing these new 🦞 homes - share your setup and we'll start posting them.

@AlexFinn Tell your openclaw to add links for keywords/phrases and go to your graph view in obsidian.

OpenClaw's memory out of the box sucks With this simple Obsidian system, it's actually awesome In this video I go over using Obsidian as a memory layer for your AI agent, making it SO much more smarter than it is now If you use OpenClaw or Hermes, you need to watch this:

@TheAhmadOsman This is awesome to watch. I've been following as I have a single 4090 gaming build I was hosting local models on, but bought a Spark so I don't fight for the GPU so often. One stumbling block was getting NVFP4 models working with agents. Can't wait to see your updates.

What do you want to see me running on these 4x DGX Sparks today?

@AlexFinn Just started playing with Hermes last night and already loving it as a local model guy. Now have both hooked up in my discord. Absolutely need a video on how you improved Openclaw/Hermes memory with Obsidian before Hermes figures it out for me.

Hermes Agent is an INCREDIBLE AI agent It's better than OpenClaw in some key ways, but does it replace it? In this video I cover what Hermes agent is, how to use it, workflows that will explode your productivity, and if it's the OpenClaw killer:

🏴‍☠️