IBM/LNN

PyTorch implementation of Logic Tensor Networks, a Neural-Symbolic framework.

DeepProbLog is an extension of ProbLog that integrates Probabilistic Logic Programming with deep learning by introducing the neural predicate.

PyNeuraLogic lets you use Python to create Differentiable Logic Programs

Logic Language for World Models 🌱🐋🌍

Keras based framework for neuro-symbolic LM systems

A neurosymbolic perspective on LLMs

Neuro-symbolic agents that verify, remember, and reuse. Learn checked rules without model retraining. Compact math, residual-guided recovery, verified memory, and optional Lean proofs.

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

TorchLean is the first unified Lean 4 framework for neural-network specification, execution, and verification.