Materials science toolkit powered by machine learning interatomic potentials (MLIPs). Relax crystal structures, compute phonon band structures, assess thermodynamic stability via energy-above-hull analysis, and generate doped or defective structures for computational screening workflows. Accepts CIF files as input; heavy calculations run asynchronously.

generates candidate inorganic crystal structures with diffusion-based property conditioning. Use it to sample materials within a target chemical system or steer generations toward target magnetic density and supply-concentration preferences (HHI score). Batch routes return ZIP archives of CIF files, while the single-structure route returns one CIF directly.

Materials science endpoints

is a model that generates crystal structures from chemical compositions.

is a text-guided diffusion model for crystal structure generation. Generate structures from text descriptions, target compositions, or explore chemical systems.

API for first-principles calculations and properties

API for molecular calculations using g-XTB

SKY is an LLM-powered synthesis exploration agent for inorganic materials. It performs composition- and structure-based similarity search on the Materials Project, retrieves neighbor synthesis recipes + metadata, and surfaces property/structure summaries. Ryan Nduma, Hyunsoo Park, Kinga Mastej - Imperial College London, Materials Design Group