microsoft/mattergen
A generative deep learning model for designing inorganic materials across the periodic table with controllable property constraints.
Not currently ranked — collecting fresh signals.
star history
MatterGen implements a generative model that synthesizes novel inorganic crystal structures across the entire periodic table. The model can be fine-tuned to steer generation toward specific property targets such as stability, electronic properties, or mechanical characteristics. It provides pre-trained checkpoints, training pipelines, and evaluation tools for researchers working on materials discovery and computational chemistry.
Frequently asked
- What is microsoft/mattergen?
- A generative deep learning model for designing inorganic materials across the periodic table with controllable property constraints.
- Is mattergen open source?
- Yes — microsoft/mattergen is open source, released under the MIT license.
- What language is mattergen written in?
- microsoft/mattergen is primarily written in Python.
- How popular is mattergen?
- microsoft/mattergen has 1.8k stars on GitHub.
- Where can I find mattergen?
- microsoft/mattergen is on GitHub at https://github.com/microsoft/mattergen.