Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Graph deep learning library for materials
| Date | Stars |
|---|---|
| 2026-07-31 | 564 |
| 2026-08-01 | 564 |
| 2026-08-06 | 564 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
15.0
growth rate 0.00%/day
[](https://github.com/materialyzeai/matgl/blob/main/LICENSE) [](https://github.com/materialyzeai/matgl/workflows/Lint/badge.svg) [](https://github.com/materialyzeai/matgl/actions/workflows/test.yml) [](https://pepy.tech/project/matgl) [](https://codecov.io/gh/materialyzeai/matgl) [](https://pypi.org/project/matgl?logo=pypi&logoColor=white) # Materials Graph Library <img src="https://github.com/materialyzeai/matgl/blob/main/assets/MatGL.png?raw=true" alt="matgl" width="30%" style="float: right"> ## Official Documentation <https://matgl.ai> ## Introduction MatGL (Materials Graph Library) is a graph deep learning library for materials science. Mathematical graphs are a natural representation for a collection of atoms. Graph deep learning models have been shown to consistently deliver exceptional performance as surrogate models for the prediction of materials properties. The goal is for MatGL to serve as an extensible platform to develop and share materials graph deep learning models. This first version of MatGL is a collaboration between the [Materialyze.AI][materialyze] and Intel Labs. MatGL is part of the MatML ecosystem, which includes the [MatGL] (Materials Graph Library) and [maml] (MAterials Machine Learning) packages, the [MatPES] (Materials Potential Energy Surface) dataset, and the [MatCalc] (Materials Calculator). ## Status Major milestones are summarized below. Please refer to the [changelog] for details. - v3.0.0 (May 5 2026): PyG implementations of `M3GNet` and `QET`. Corrected message-passing convention in `TensorNet`, `M3GNet`, and `QET`. New pre-trained weights re-released on Hugging Face (`materialyze` org), which is now the canonical source for all matgl models. - v2.0.0 (Nov 13 2025): [QET] architecture added. PYG backend is now the default. - v1.3.0 (Aug 12 2025): Pretrained molecular potentials and PyG framework added. - v1.1.0 (May 7 2024): Implementation of [CHGNet] + pre-trained models. - v1.0.0 (Feb 14 2024): Implementation of [TensorNet] and [SO3Net]. - v0.5.1 (Jun 9 2023): Model versioning implemented. - v0.5.0 (Jun 8 2023): Simplified saving and loading of models. Now models can be loaded with one line of code! - v0.4.0 (Jun 7 2023): Near feature parity with original TF implementations. Re-trained M3Gnet universal potential now available. - v0.1.0 (Feb 16 2023): Initial implementations of M3GNet and MEGNet architectures have been completed. Expect bugs! ## Major update: v3.0.0 (May 2026) > **DGL support removed.** The DGL backend has been removed. matgl now targets PyTorch Geometric (PyG) exclusively. > Models that previously had only DGL implementations have either been ported to PyG or removed. A bug in the message-passing convention of `TensorNet`, `M3GNet`, and `QET` has been corrected: edge messages are now aggregated onto the source (center) node so each atom correctly collects information from its neighbors. Pre-trained weights generated under the old convention are no longer numerically valid. New weights — including `TensorNet-PES-MatPES-PBE-2025.2` and the PyG `M3GNet` / `QET` potentials — have been retrained against the corrected convention and uploaded to the [`materialyze`](https://huggingface.co/materialyze) Hugging Face org, which is now the canonical (and only) source for matgl pre-trained models. The legacy GitHub `pretrained_models/` download fallback (`RemoteFile`, `PRETRAINED_MODELS_BASE_URL`) has been removed in this release. ## Current Architectures <div style="float: left; padding: 10px; width: 200px"> <img src="htt
Excerpt of 32,757 characters
Read on GitHub
586
293
196
19
14
14
Janosh Riebesell · @periodiclabs · United States
12
11
Andrew S. Rosen · Princeton University
11
4
4
3
2
2
2
2
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b786ff2b13c9376f, topic:learning