@0xSero He wants to run true multi agent like in a corporate structure - I'm worrying parallel processing would take the wind out of the sails of this?
i have a question to you: i tried qwen.3.5-35 with llama.cpp and it's blazing fast when i use their chat tool (the one on 1143) - however using it on openclaw is a nightmare - i have to wait a minute to get a hello back. Is this something i can expect with Hermes, or is it loading less bloat for local models?
Crypto analysis in 2024: The dog has a hat
Crypto analysis in 2026: Strait of Hormuz, auto-translate from Farsi, tracking military movements via OSINT, oil futures backwardation