lab-v2/pyreason

An explainable inference software supporting annotated, real valued, graph based and temporal logic

What it solves

PyReason provides a way to perform explainable inference over graph structures. It addresses the need for reasoning systems that can handle annotated, real-valued, graph-based, and temporal logic, allowing users to derive conclusions from a set of facts and logical rules.

How it works

The software functions as a graphical inference tool. It takes a set of initial conditions (facts) and a set of logical rules, and applies these rules to the graph structure to reason and infer new information.

Who it’s for

It is designed for researchers and developers working with temporal logic, graph-based reasoning, and systems requiring explainable AI inference.

Highlights

  • Supports annotated and real-valued logic.
  • Handles temporal logic and graph-based structures.
  • Provides explainable inference results.
  • Compatible with Python 3.7 through 3.10, with multi-core parallel support for versions 3.9 and 3.10.

Related

  • Project
    pgmpy/pgmpy

    A Python library for causal and probabilistic reasoning using graphical models, providing tools for structure learning, parameter estimation, and causal inference.

  • Project
    LukasZahradnik/PyNeuraLogic

    A framework for writing differentiable logic programs in Python, enabling the creation of expressive relational learning models that extend beyond standard Graph Neural Networks.

  • Project
    GraphRAG-Bench/GraphRAG-Benchmark

    A comprehensive benchmark for evaluating Graph Retrieval-Augmented Generation (GraphRAG) models to determine when they outperform traditional RAG across various reasoning and retrieval tasks.

  • Project
    astroautomata/PySR

    PySR is a Python‑fronted library for symbolic regression that leverages the high‑performance Julia engine SymbolicRegression.jl. It discovers compact, interpretable formulas fitting data, offering scikit‑learn‑style APIs, custom operators, loss functions, and export to SymPy, JAX, or PyTorch.

  • Project
    awslabs/graphrag-toolkit

    A collection of Python tools for building graph-enhanced Generative AI applications using hierarchical lexical graphs and structured knowledge graphs.