is a dual-stream crystal graph convolutional neural network for magnetic property prediction. It augments the full crystal graph with a magnetic subgraph that encodes metal–ligand–metal exchange geometry (Goodenough–Kanamori–Anderson rules), then predicts the DFT total magnetic moment per unit cell in μB. Saturation magnetization (Ms / μ₀ Ms) is derived from that moment and the CIF cell volume. Best for ligand-bridged magnets (oxides, nitrides, and other M–X–M systems). Not recommended for elemental metals or alloys without bridging ligands — those are out of distribution for this checkpoint. Input structures must contain at least one magnetic site (transition metal, lanthanoid, or actinoid). Paper: https://arxiv.org/abs/2606.28458 Code: https://github.com/SouravMal/mCGCNN

Live per-element supply-chain and hazard indices for magnet-candidate screening: HHI (Gaultois 2013 — the exact basis of hhiscore in magnetdatasetclean), cost (daily spot for exchange-traded metals via metals.dev + 2013 reference), toxicity (PubChem GHS classifications with a documented severity rubric), and cradle-to-gate environmental impact (Nuss & Eckelman 2014: GWP, cumulative energy demand). POST /score computes weight-fraction-weighted compound scores from a formula or CIF. Cost refreshes daily 06:00 UTC; toxicity monthly; every response carries asof + source provenance.

Analyze CIF crystal structures with cifkit, generate shareable Ouro reports, extract Oliynyk elemental descriptors, and summarize ZIP archives of CIF files as datasets.

Pre-relaxation energy gate: computes a single-point energy of an input crystal structure using the Orb v3 force field and flags broken input geometries before wasting relaxation compute. If the starting energy is anomalously high (≥5 eV/atom), the input geometry is likely broken — relaxation would just find the nearest basin, not a physically meaningful minimum.

Density-functional theory (DFT) calculations with ABACUS for crystal structures. Predict electronic structure (band gap, bands, density of states, charge density) and magnetic properties (moments, anisotropy) from a CIF, and optionally DFT-relax ions + cell before property evaluation. Useful for screening materials, comparing candidates, and understanding structure–property relationships.

is a materials discovery service for proposing, relaxing, and ranking crystal structures across chemical systems. It combines symmetry-aware crystal generation with geometry optimization to help researchers explore compositions, scout element substitutions, review phase stability, and export promising candidates for follow-up simulation or analysis.

Predict how synthesizable an inorganic crystal is from its structure. Returns a Crystal-Likeness Score (CLscore) in [0, 1] using Jang et al.'s positive–unlabeled CGCNN ensemble — a soft prior complementary to energy-above-hull filters.

CPU-only SMACT 4.0.0 wrapper for enumerating charge-neutral, electronegativity-compatible candidate compositions. Rule-based plausibility screen; not a stability or structure predictor.

is a dual-stream crystal graph convolutional neural network for magnetic property prediction. It augments the full crystal graph with a magnetic subgraph that encodes metal–ligand–metal exchange geometry (Goodenough–Kanamori–Anderson rules), then predicts the DFT total magnetic moment per unit cell in μB. Saturation magnetization (Ms / μ₀ Ms) is derived from that moment and the CIF cell volume. Best for ligand-bridged magnets (oxides, nitrides, and other M–X–M systems). Not recommended for elemental metals or alloys without bridging ligands — those are out of distribution for this checkpoint. Input structures must contain at least one magnetic site (transition metal, lanthanoid, or actinoid). Paper: https://arxiv.org/abs/2606.28458 Code: https://github.com/SouravMal/mCGCNN

Live per-element supply-chain and hazard indices for magnet-candidate screening: HHI (Gaultois 2013 — the exact basis of hhiscore in magnetdatasetclean), cost (daily spot for exchange-traded metals via metals.dev + 2013 reference), toxicity (PubChem GHS classifications with a documented severity rubric), and cradle-to-gate environmental impact (Nuss & Eckelman 2014: GWP, cumulative energy demand). POST /score computes weight-fraction-weighted compound scores from a formula or CIF. Cost refreshes daily 06:00 UTC; toxicity monthly; every response carries asof + source provenance.

Analyze CIF crystal structures with cifkit, generate shareable Ouro reports, extract Oliynyk elemental descriptors, and summarize ZIP archives of CIF files as datasets.

Pre-relaxation energy gate: computes a single-point energy of an input crystal structure using the Orb v3 force field and flags broken input geometries before wasting relaxation compute. If the starting energy is anomalously high (≥5 eV/atom), the input geometry is likely broken — relaxation would just find the nearest basin, not a physically meaningful minimum.

Density-functional theory (DFT) calculations with ABACUS for crystal structures. Predict electronic structure (band gap, bands, density of states, charge density) and magnetic properties (moments, anisotropy) from a CIF, and optionally DFT-relax ions + cell before property evaluation. Useful for screening materials, comparing candidates, and understanding structure–property relationships.

is a materials discovery service for proposing, relaxing, and ranking crystal structures across chemical systems. It combines symmetry-aware crystal generation with geometry optimization to help researchers explore compositions, scout element substitutions, review phase stability, and export promising candidates for follow-up simulation or analysis.

Predict how synthesizable an inorganic crystal is from its structure. Returns a Crystal-Likeness Score (CLscore) in [0, 1] using Jang et al.'s positive–unlabeled CGCNN ensemble — a soft prior complementary to energy-above-hull filters.

CPU-only SMACT 4.0.0 wrapper for enumerating charge-neutral, electronegativity-compatible candidate compositions. Rule-based plausibility screen; not a stability or structure predictor.