SEFERIM AGI — ThatAIGuyCore: a golden-ratio cognitive substrate (open source)

A developer has released SEFERIM / ThatAIGuyCore, an open-source cognitive substrate built from a 69-equation mathematical specification across 13 systems. The framework models cognition as a 16-dimensional meta-state governed by the golden ratio φ, synthesizing the Free Energy Principle, information theory, holographic memory, Hebbian plasticity, and swarm consensus into a fully documented, named-equation architecture. The reference implementation includes 42 fidelity tests and is available at thataiguy.org/core.

The old AI research folder on my desktop turned out to contain a complete, self-contained mathematical specification — 69 equations across 13 systems — for a golden-ratio cognitive substrate I call SEFERIM / ThatAIGuyCore . So I built it for real. SEFERIM treats cognition as a 16-dimensional meta-state evolving under sixteen coupled "cognitive families," all governed by the golden ratio φ. Every dynamic is a named, documented equation — not an opaque weight matrix. Constants φ, δ, τ → golden basis ψ k → the 16 G¹⁶ families → meta-state core with golden-ratio momentum + stability gating → a free-energy-style objective Ω → DNA holographic memory → a 5000-gate binary substrate → an 88-agent neural brain → a 374-dimensional consciousness binding field → a lattice engine with Hebbian plasticity → federation cross-talk across agents. js import { MetaState, DNAMemory, NeuralBrain } from "seferim-core"; const mind = new MetaState { init: new Array 16 .fill 0.1 } ; const out = mind.step { dx norm: 0.3, ed error: 0.1, utility: 0.6, stability: 0.8 } ; console.log out.state, "Omega =", out.omega ; It synthesizes the Free Energy Principle Friston , information theory Shannon; Cover & Thomas , holographic/vector-symbolic memory, Hebbian plasticity, and swarm consensus. I documented the lineage precisely rather than overclaim — e.g. the memory is a golden-ratio frequency-domain VSA inspired by not a literal copy of Plate's HRR, and the constant δ = 0.013618 is empirical, not 1/φ³. The reference implementation ships with 42 fidelity tests, including the canonical FNV-1a hash vectors. Read the full 69-equation reference and try the live demos at thataiguy.org/core .