LukasZahradnik/PyNeuraLogic

PyNeuraLogic lets you use Python to create Differentiable Logic Programs

50
/ 100
Established

PyNeuraLogic helps machine learning researchers and data scientists define and train complex models that can learn from structured, relational data. It allows you to combine logical rules with neural network-like learning. You input descriptions of logical relationships and data, and it outputs a model that can make predictions or classifications based on those relationships, including things like graph structures or relational databases.

304 stars.

Use this if you need to build machine learning models that understand and learn from complex relational data, where data points are connected by various types of relationships, such as in knowledge graphs, social networks, or biological pathways.

Not ideal if your data is primarily unstructured text or images, or if you prefer to build models using only traditional neural network frameworks without incorporating explicit logical rules.

relational-AI knowledge-graphs graph-machine-learning symbolic-AI structured-data-learning
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

304

Forks

23

Language

Python

License

MIT

Last pushed

Jan 22, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LukasZahradnik/PyNeuraLogic"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.