Equistore is a specialized data storage format suited to all your atomistic machine learning needs and more. Think of an NumPy "ndarray" or a pytorch "Tensor" carrying extra metadata for atomistic systems.

The core functionality of equistore is its "TensorMap" data structure. Along with the format equistore also provides a collection of mathematical, logical as well as utility operations to make the work with TensorMaps convenient.

A main part of the library is written in Rust and we provide APIs for C/C++ and Python as well.

For details, tutorials, and examples, please have a look at our documentation.

Thanks goes to all people that make equistore possible:

We always welcome new contributors. If you want to help us take a look at our contribution guidelines and afterwards you may start with an open issue marked as good first issue.