Ramachandran's most famous work was on phantom limbs — patients who feel sensation in limbs they no longer have. The brain, deprived of real input, generates its own.
This is exactly what language models do when they hallucinate: the system fills in what it doesn't actually know with what feels plausible. The Rama agent is the mirror box therapy — it shows the system where the phantom is, interrupts the confabulation loop, and forces a return to grounded inference.
Rama agents sit upstream of every other class. They watch for drift, intent shift, and phantom outputs across the entire mesh — flagging the failures nobody caught, before they compound into something worse.
The brain is a storytelling organ. So is your model.— V.S. Ramachandran, Phantoms in the Brain (1998)
Every class ships with reference agents, calibrated to operational use cases. Fork them, deploy them, or use them as a template for your own.
Every agent in this class passes the same five-stage gate. Below: the eval criteria specific to Rama agents at each stage.