hebbian

Raise a neural network as a pet - a transparent cognitive sandbox where a digital squid learns, grows, and rewires itself via Hebbian learning & Neurogenesis

LLM infrastructure cost reduction via NUMA-aware weight banking: 147 t/s (8.8x stock llama.cpp) on refurbished enterprise POWER8. Self-hosted inference, no cloud APIs. Part of the Proof of Physical AI stack.

Meta-Learning through Hebbian Plasticity in Random Networks: https://arxiv.org/abs/2007.02686

ShaprAI — Agent Sharpener by Elyan Labs. Sharpen raw models into principled, self-governing Elyan-class agents. Requires beacon-skill, grazer-skill, atlas, RustChain.

Pytorch implementation of Hebbian learning algorithms to train deep convolutional neural networks.

Code for paper NeurIPS AMHN 2023

Pytorch implementation of Hebbian learning algorithms to train deep convolutional neural networks.

In this project, I used Hebbian, Perceptron, Adaline, MultiClassPerceptron and MultiClassAdaline neural networks to implement X and O character recognition.

In this project, I used Hebbian, Perceptron and Adaline neural networks to implement AND gate, and OR gate.

Create and Evolve AI animal robots

Evolve Robotic Animats in a Simulation of Nature

Local-first personal knowledge graph with Hebbian TTL decay, rendered as a living constellation.

AeloRu (Adaptive Elastic Learning with Orthogonal Robust Units) enables real-time, continuous learning on resource-constrained devices. Drop-in memory module for LLMs.

A hippocampus for Claude Code — surprise-aware memory MCP server. Pure Rust, SHODH-compatible schema, Apache-2.0/MIT.

hebbian learning for sequential generation

A framework for systems that learn from experience without backprop: local Hebbian and neuromodulatory learning, persistent memory, a safety kernel. Rust core, Python API.