symbolic-ai

Structured Outputs

Torchhd is a Python library for Hyperdimensional Computing and Vector Symbolic Architectures

PYthon Automated Term Extraction

Neuro-symbolic interpretation learning (mostly just language-learning, for now)

Query language for blending SQL and local language models across structured + unstructured data, with type constraints.

Handwritten Equations Decipherment with Abductive Learning

An expert system using logic-based artificial intelligence and symbolic AI.

A simple Lisp written in Go

Kaleidoscope is an experimental cognitive architecture for emergent intelligence. It uses an E8 lattice physics engine and an RL-steered LLM to autonomously generate novel theories about complex systems. Features a visualization hub of its internal thought-space.

A JavaScript implementation of Douglas Hofstadter and Melanie Mitchell's Copycat program.

Wirewright is an experimental symbolic physics environment

Expert system with deductive querying and verification of constraints expressed in natural language

AGI runtime for bounded recursive self-awareness. Attempting machine consciousness at the Gödel–Turing–Hofstadter Nexus.

Code and data to the publication "SpikE: spike-based embeddings for multi-relational graph data".

Meta Optimization Semantic Evolutionary Search

Axiomatic intelligence. Doing the right thing, provably.

Ein: a tensor logic language unifying neural and symbolic AI

Noor Research Collective - Main Project Metapage

Artificial intelligence with a network of connected neurons

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