Search pages, resources, and actions
Models, datasets, and services for materials science research.
Multi-head universal foundation interatomic potential covering inorganic crystals, molecules, surfaces, and reactive chemistry in a single model. Trained on OMAT-24 (100M PBE/PBE+U configurations) and fine-tuned across seven heads (omat_pbe, omol, oc20, spice, rgd1, mptrj, matpes). Predicts energies, forces, and stresses.
Screen candidate materials against criteria using DFT predictions, experimental data, and knowledge graph traversal. Includes phase gate evaluation.
NIST JARVIS database of DFT-computed materials properties. 55,000+ materials with formation energies, band gaps, elastic constants, and more.
444 technical reports from NASA Technical Reports Server covering rocket propulsion, thermal protection, turbine materials, and spacecraft systems (1963-2024). Fully embedded in the knowledge graph.
Multi-agent discourse for alloy selection. Metallurgist, DFT expert, and experimentalist debate material candidates with evidence-based challenges and consensus building.
210,000+ crystal structures with computed properties: band gap, formation energy, density, space group, crystal system. From the Materials Project database.
Materials Knowledge Graph curated from 5 million scientific papers. 69,618 entities and 5.38M relationships across 7 entity types. The backbone ontology for materials science.
Comprehensive metal AM dataset covering powder bed fusion, process parameters, microstructure, and mechanical properties. 4.5GB across 4 parts.
Chemical Entities of Biological Interest — 170,000+ chemical entities with classifications, structures, and relationships.
Computation-Ready Experimental Metal-Organic Framework database. Crystal structures optimized for computational screening.
Fatigue testing data for additively manufactured metals. Process-structure-property relationships for AM parts.
Multi-principal element alloy (MPEA/HEA) compositions, processing, and properties database.
Foundation model for atomistic simulations. Universal machine learning interatomic potential trained on 150K Materials Project structures. Predicts energies, forces, and stresses for any material.
Universal potential for charge-informed atomistic modeling. Predicts energy, forces, stress, and magnetic moments.
Open-source DFT simulation suite for electronic structure calculations. Plane-wave pseudopotential method for ground state, structural optimization, and molecular dynamics.
Automated literature review workflow. Agents search, evaluate, and synthesize findings from scientific papers across multiple databases.
