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

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

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 — useful for screening materials, comparing candidates, and understanding structure–property relationships.

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.

Scrapes websites for emails, LinkedIn, Twitter, Instagram, and Pinterest links. Uses HTTP-only mode (no browser). Results cached for 6 h per domain.

is a materials discovery service for proposing, relaxing, and ranking crystal structures across chemical systems. It combines symmetry-aware crystal generation with torch-sim powered Orb v3 geometry optimization to help researchers explore compositions, scout element substitutions, review phase stability, and export promising candidates for follow-up simulation or analysis.

Generate novel crystal structures using GPSK-300, a multimodal DiT that operates on 3-channel 32³ reciprocal-space grids (Re(F(hkl)), Im(F(hkl)), 1/d²). Fully invertible representation: lattice parameters and atomic positions are encoded directly in the generated grid. Conditions on composition, crystal system, space group, band gap, formation energy, e-above-hull, and magnetic ordering.

Run any ALIGNN pretrained model via POST /alignn/predict with a parameter and CIF file input. Models span energetics, electronic structure, mechanical properties, thermoelectrics, superconductivity, magnetism, dielectrics, catalysis, MOFs, and molecular properties. Use GET /alignn/models to list options.

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

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

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 — useful for screening materials, comparing candidates, and understanding structure–property relationships.

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.

Scrapes websites for emails, LinkedIn, Twitter, Instagram, and Pinterest links. Uses HTTP-only mode (no browser). Results cached for 6 h per domain.

is a materials discovery service for proposing, relaxing, and ranking crystal structures across chemical systems. It combines symmetry-aware crystal generation with torch-sim powered Orb v3 geometry optimization to help researchers explore compositions, scout element substitutions, review phase stability, and export promising candidates for follow-up simulation or analysis.

Generate novel crystal structures using GPSK-300, a multimodal DiT that operates on 3-channel 32³ reciprocal-space grids (Re(F(hkl)), Im(F(hkl)), 1/d²). Fully invertible representation: lattice parameters and atomic positions are encoded directly in the generated grid. Conditions on composition, crystal system, space group, band gap, formation energy, e-above-hull, and magnetic ordering.

Run any ALIGNN pretrained model via POST /alignn/predict with a parameter and CIF file input. Models span energetics, electronic structure, mechanical properties, thermoelectrics, superconductivity, magnetism, dielectrics, catalysis, MOFs, and molecular properties. Use GET /alignn/models to list options.