I am not sure anyone knows what a harness is at this point. I've heard 17 different definitions of it at this point. It's almost like a buzzword in search of a problem.
If you use cloud models.. the harness is what runs in your computer
AI companies would love if everything ran in their cloud, but arguably there are latency reasons or other reasons to run at least some stuff in your own computer
the agent harness is the REPL. The evaluation + loop.
I don’t even know what an agent means, let alone harness.
Author here. My definition is: you take an agent, remove the model and you’re left with the harness.
Tools, memories, sandboxing, steering, etc