tinker495/JAxtar

JAxtar is a project with a JAX-native implementation of parallelizeable A* & Q* solver for neural heuristic search research.

44
/ 100
Emerging

JAxtar helps machine learning researchers quickly find optimal paths or solutions for complex puzzles and problems using advanced search algorithms. It takes in initial problem states and desired target states, often leveraging neural network heuristics, to efficiently output the shortest or lowest-cost sequence of actions. This tool is for researchers developing and testing new AI agents, especially those focused on graph search and reinforcement learning in challenging, high-dimensional environments.

Use this if you are a machine learning researcher working on AI problems that require high-performance, GPU-accelerated pathfinding or solution discovery for complex state spaces.

Not ideal if you are looking for a simple, off-the-shelf pathfinding solution for basic 2D grids or if your research does not involve deep learning frameworks like JAX.

AI research Reinforcement learning Pathfinding algorithms Neural heuristics Puzzle solving
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

44

Forks

4

Language

Python

License

MIT

Last pushed

Mar 06, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tinker495/JAxtar"

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