Davidwarchy/the-self-grounded-agent

A tiny two-wheel robot with a 100-ray lidar learns objecthood from pure sensorimotor experience. With no labels or tasks, it samples simple actions and tracks how they distort the lidar stream, revealing stable “things” in the world—structures it can use to predict, navigate, and act coherently.

19
/ 100
Experimental
No Package No Dependents
Maintenance 10 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Davidwarchy/the-self-grounded-agent"

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