sapientinc/HRM

Hierarchical Reasoning Model Official Release

49
/ 100
Emerging

This project offers an advanced AI model designed to solve complex logical puzzles and planning challenges efficiently. It takes in structured problem data, like Sudoku grids or maze layouts, and outputs optimal solutions without needing extensive prior training examples. This is useful for researchers and practitioners working on artificial intelligence problems that require sequential reasoning and robust problem-solving.

12,358 stars. No commits in the last 6 months.

Use this if you need an AI that can solve intricate reasoning tasks, such as complex Sudoku puzzles or pathfinding in mazes, with minimal training data and high computational efficiency.

Not ideal if you are looking for a simple, off-the-shelf solution that doesn't require setting up a PyTorch and CUDA environment or if your problems are not related to abstract logical reasoning.

AI-research problem-solving logical-reasoning pathfinding puzzle-solving
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 22 / 25

How are scores calculated?

Stars

12,358

Forks

1,801

Language

Python

License

Apache-2.0

Last pushed

Sep 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sapientinc/HRM"

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