lil-lab/knotgym

[NeurIPS DB 2025] A gym environment for visual spatial reasoning - knot so simple :)

29
/ 100
Experimental

This environment helps researchers study how AI agents can understand and manipulate complex 3D shapes. It takes a virtual 'agent' within a simulation, and outputs how well it performs at tying and untying knots. It's designed for AI researchers and cognitive scientists exploring spatial reasoning and robotic manipulation.

Use this if you are an AI researcher developing or testing algorithms for spatial reasoning, robotic manipulation, or complex shape understanding.

Not ideal if you are looking for a tool to physically tie knots or manage real-world objects, as this is a simulation environment for AI research.

AI-research robotics-simulation spatial-reasoning cognitive-science machine-learning
No License No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 7 / 25
Community 10 / 25

How are scores calculated?

Stars

15

Forks

2

Language

Python

License

Last pushed

Dec 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lil-lab/knotgym"

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