NexusCortex Just Beat Opus 4.8 – and It's Open Source
NexusCortex is an experimental cognitive architecture developed in Go, focusing on low-level AI system primitives. It combines various concepts such as sparse representations and online learning to create a prototype cognitive system. The project aims to enhance understanding of memory, retrieval, and inference mechanisms in AI development.
- ▪NexusCortex is not intended to replace advanced language models or claim to be artificial general intelligence.
- ▪The architecture includes components like sensory processing, memory systems, and emotional modulation.
- ▪It features a local dashboard for monitoring cognitive vitals and supports optional GPU acceleration.
Opening excerpt (first ~120 words) tap to expand
NexusCortex Experimental sparse cognitive architecture written in Go. NexusCortex is a research and learning project exploring whether ideas from Sparse Distributed Representations, associative memory, online learning, sparse routing, and local-first compute can be combined into a small cognitive-system prototype. This is not a replacement for frontier LLMs. It is not an AGI claim. The goal is to understand and implement low-level AI system primitives from scratch. What It Implements • Architecture • Quick Start • Dashboard • Benchmarks • Roadmap What It Implements SDR-based attention — popcount similarity and top-K retrieval (sdr_attention.go) Sparse ternary compute — RGBA32 packed weights, 0.25 bytes/param (neurotexture.go, ternary.go) 10 neural region modules — Wernicke, Broca,…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.