khoruzhii/cayleypy-cube
Learned diffusion heuristics with GPU-accelerated search for short paths in large graphs.
This project helps puzzle enthusiasts and competitive solvers find the shortest solutions for complex permutation puzzles like Rubik's Cubes or sliding tile puzzles. You provide a scrambled puzzle state, and it outputs a highly optimized, short sequence of moves to solve it. It's designed for anyone looking to efficiently solve challenging combinatorial puzzles without needing to understand deep mathematical or programming concepts.
Use this if you want to find optimal or near-optimal solutions for large and complex permutation puzzles quickly, leveraging advanced AI.
Not ideal if you're looking for a simple, in-browser tool for common puzzles or if you need to solve puzzles that are not Cayley graphs.
Stars
64
Forks
7
Language
Python
License
MIT
Category
Last pushed
Nov 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/khoruzhii/cayleypy-cube"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lmcinnes/umap
Uniform Manifold Approximation and Projection
pyRiemann/pyRiemann
Machine learning for multivariate data through the Riemannian geometry of positive definite...
geomstats/geomstats
Computations and statistics on manifolds with geometric structures.
higra/Higra
Hierarchical Graph Analysis
pavlin-policar/openTSNE
Extensible, parallel implementations of t-SNE