The Fuzzy-Pattern Tsetlin Machine library, with zero external dependencies, performs blazingly fast.
-
Updated
Jul 20, 2026 - Julia
The Fuzzy-Pattern Tsetlin Machine library, with zero external dependencies, performs blazingly fast.
Tsetlin Machine for Logical Learning and Reasoning With Graphs
Holographic Reduced Representations
Accelerator for Hyperdimensional Computing (HDC)
Boolean Hypervectors with various operators for experiments in hyperdimensional computing (HDC).
Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples for offline AI.
Geometric agent memory for Agents: 8-tool lean contract, harness injection at wake, session handoff. 79 MCP tools. Not a vector DB. Rust + MCP.
A Walsh Hadamard Derived Linear Vector Symbolic Architecture 🔥
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.
Spiking Semantic SLAM (& path integration) with Spatial Semantic Pointers (SSPs) in Nengo and Nengo-Loihi
Holographic vectors you can compute with. Bind structure, bundle sets, unbind components cross NumPy, PyTorch, and JAX.
Sparse binary hypervectors and associated learners.
Sema is a non-parametric, instance-based reasoning system: a Vector Symbolic Architecture over a content-addressable memory, with inference by weighted automated deduction.
Vector Symbolic Architecture (VSA) primitives for experimentation
Keynote presentation for the Midnight Sun Workshop on Vector Symbolic Architectures
Comprehensive package for cognitive computing technologies like Sparse Distributed Memory, Vector Symbolic Architectures, and much more.
Advanced Retrieval-Augmented Generation that projects high-dimensional vector embeddings onto multi-layered data topologies. Mirroring optical holograms, it ensures contextual, interference-free, and hyper-accurate LLM responses. Solves multi-hop reasoning via native multi-angle querying. Fast, scalable, and plug-and-play.
A memory-first artificial mind: HDC/VSA cognitive organism with perception, provable answers, and forgetting on command. No LLM in the loop.
Generate a website that demonstrates the action of Vector Symbolic Architecture operators by projecting the hypervectors to the surface of a sphere.
GPU-native equilibrium associative memory: a DEQ-transformer with modern-Hopfield attention, HRR positional binding, and non-autoregressive MaskGIT decoding. Dense matmul + FFT + softmax throughout.
Add a description, image, and links to the vector-symbolic-architecture topic page so that developers can more easily learn about it.
To associate your repository with the vector-symbolic-architecture topic, visit your repo's landing page and select "manage topics."