Pioneering an AI-Driven Future for Materials Science
Our mission is to accelerate the design and discovery of breakthrough materials through the integration of theory, experiments, and AI.
Latest News
Research Focus
Our Five Foundational Pillars for Great Science
Theory
Advancing the science frontier
We integrate solutions to the Schrödinger equation with phenomenological theory to predict and analyze the properties of materials.
Data
Generating AI-ready datasets
We build sophisticated software frameworks for simulation and lab automation to generate high quality data at unprecedented scales.
Learning
Developing cutting-edge AI
We develop data and compute efficient physics-informed AI architectures for massive-scale simulations, interpretation and discovery across vast chemical spaces.
Translation
Maximizing return on data and AI
We focus on technologically relevant materials that can have a major impact on societal well-being, such as next-generation batteries, aerospace alloys, and advanced semiconductors.
Community
Giving back to the community
We democratize access to reproducible materials science innovation through open data, open APIs, and open-source software.
Software
We democratize access to materials analysis and AI through our open-source codes.
Pymatgen (Python Materials Genomics) is a robust, open-source Python library for materials analysis. It is a key pillar of the Materials Project and one of the most popular materials science libraries in the world with millions of downloads each month.
MatGL (Materials Graph Library) is a graph deep learning library for materials science. It implements state-of-the-art foundation potential architectures, including TensorNet, CHGNet, M3GNet, etc.
MatCalc is a Python library for calculating and benchmarking material properties from the potential energy surface (PES). It provides a simplified, consistent interface to access these properties with any parameterization of the PES.