associative-memory

A swarm of autonomous AI minds, unified and steered by a single consciousness - the Veil. Runs on any language model.

Reference implementation of "An Algorithm for Routing Vectors in Sequences" (Heinsen, 2022) and "An Algorithm for Routing Capsules in All Domains" (Heinsen, 2019), for composing deep neural networks.

Implementation of deep implicit attention in PyTorch

Holistic system for storage and transformation of information based on associative model of data. Целостная система для хранения и обработки информации, основанная на ассоциативной модели данных.

Physics-inspired transformer modules based on mean-field dynamics of vector-spin models in JAX

Cognitive Computing with Associative Memory

Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing (Technical Report)

This repository contains the official code for Energy Transformer---an efficient Energy-based Transformer variant for graph classification

A TypeScript-based MCP server implementing a memory system inspired by neurodivergent cognitive styles. It organizes thoughts into five districts (knowledge domains), ranks search results using BM25 semantic ranking, and stores memories as a persistent knowledge graph with bidirectional connections.

High-performance Holographic Memory System (HMS) for Node.js, powered by Rust. This library implements Vector Symbolic Architectures (VSA) using Binary Spatter Code (BSC) to enable semantic search, analogical reasoning, and associative memory at scale.

Experimental self-growing local AI brain in Rust — learns facts into neural weights, never forgets, runs on your laptop CPU. No cloud. No GPU. No ML framework.

A computational foundation for AGI, based on hyperdimensional computing and framed in set theory.

Memory system for LLMs that remembers everything you teach it during conversation. No reindexing, no context window limits. CPU by default, GPU optional.

Implementation of Hopfield Neural Network in Python based on Hebbian Learning Algorithm

[ICML 2024] Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models

Memory plugin for OpenClaw. Agent's memories strengthen through use, fade when unused, and consolidate overnight.

Synapse Context Engine (SCE) is a brain-inspired hypergraph-based AI memory architecture for persistent context, coherent reasoning, and long-term memory, designed for transparency and safety.

Recurrent predictive coding networks for associative memory employing covariance learning

Holographic vectors you can compute with. Bind structure, bundle sets, unbind components cross NumPy, PyTorch, and JAX.

Your language model forgets everything. Sillage gives it a 4 MB memory that persists across sessions, no gradients, no fine-tuning, no growing index. Beats an unbounded kNN-LM at 1/13 the storage (perplexity 31 → 17). CPU-only, fully reproducible, four preprints with Zenodo DOIs.