deepmodeling/DeePTB

DeePTB: A deep learning package for tight-binding Hamiltonian with ab initio accuracy.

55
/ 100
Established

This project helps materials scientists and physicists accelerate their electronic structure simulations. By using deep learning, you can input initial atomic structures and receive predictions for electronic properties and behavior, even for large systems or at varying temperatures. It enables comprehensive insights into how materials behave at an atomic and electronic level.

102 stars.

Use this if you need to perform accurate electronic structure simulations for a wide range of materials and phenomena, especially for large systems or dynamic conditions, without the high computational cost of traditional methods.

Not ideal if you prefer only traditional ab initio methods or if you are not comfortable using Python packages and command-line installations.

materials-science electronic-structure quantum-mechanics computational-chemistry atomic-modeling
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

102

Forks

29

Language

Python

License

LGPL-3.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

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

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