Building Ouro, using AI to search for room-temp superconductors and rare-earth free permanent magnets.
Predicts the DFT formation energy per atom from the JARVIS-DFT optB88vdW dataset.
Predicts the DFT total energy per atom from the JARVIS-DFT optB88vdW dataset.
Predicts formation energy per atom using a model trained on Materials Project data.
Predicts the electronic band gap from the JARVIS-DFT optB88vdW functional.
Predicts the electronic (high-frequency) contribution to the dielectric function ε∞x.
Predicts the maximum component of the dielectric tensor from DFPT calculations.
Predicts the maximum piezoelectric strain coefficient dij from DFPT calculations.
Predicts the Voigt-averaged bulk modulus Kv.
Predicts the Voigt-averaged shear modulus Gv.
Access all ALIGNN pretrained models through individual endpoints. Each endpoint accepts a CIF file and returns a JSON prediction. Models span energetics, electronic structure, mechanical properties, thermoelectrics, superconductivity, magnetism, dielectrics, catalysis, MOFs, and molecular properties.
Search Materials Project summaries using structured filters for formula, chemistry, symmetry, and basic properties.
Resolve a user query such as an MP ID, formula, or chemical system into canonical Materials Project candidates.
Fetch a structure by Materials Project material ID and return a CIF file payload that Ouro can save as a file asset.
Search, resolve, and retrieve Materials Project materials for agentic workflows and interactive research, including summary discovery and Ouro-ready CIF export.
Relax the input crystal structure with NequIP-OAM-XL and return a relaxed CIF for downstream phonon and thermoelectric property calculations.
Compute phonons then derive minimum lattice thermal conductivity κ_min(T) using the Wigner Transport Equation formalism.
Predict p-type and n-type Seebeck coefficients and optical band gap from a crystal structure using ALIGNN pretrained models. Useful for fast electronic screening before full transport calculations.
Compute harmonic phonons, DOS, and band structure for a crystal structure using phonopy with NequIP-OAM-XL forces. Useful for spotting imaginary modes before kappa or ZT estimation.
Run the full screening workflow on a crystal structure: relaxation, phonons, minimum thermal conductivity, Seebeck coefficients, band gap, and ZT(T). Returns a single JSON response for fast candidate triage.
Predict ZT_max and thermoelectric properties for inorganic crystal structures using first-principles methods: phono3py BTE for lattice thermal conductivity, BoltzTraP2 for electronic transport from ABACUS DFT band structure, and ML ensemble scissor correction. Falls back to Slack + SPB models when the first-principles path is unavailable.