AMLP integrates dataset creation, input/output handling, and analysis for machine learning interatomic potentials. It supports Gaussian, VASP, and CP2K, with LLM agents for code selection and ASE-b…

Tensor Atomic Cluster Expansion

Message Passing Neural Networks for Molecule Property Prediction

Fine-tuning and distillation workflow for pretrained atomic potentials

CUDA implementation of Hierarchical Navigable Small World Graph algorithm

Molecular dynamics and Monte Carlo soft matter simulation on GPUs.

This Python package is designed for mapping the solution space of machine learning models. An understanding of the organisation of the solution space can answer important questions about the reprod…

Uncertainty quantification/estimation experiments repo for Open Catalyst Project model ensembles

A unified platform for fine-tuning atomistic foundation models in chemistry and materials science

Python decompiler for modern Python versions.

an interface to semi-empirical quantum chemistry methods implemented with pytorch

HIP: Hessians with Interatomic Potentials

Source for Doyle lab bandit optimization algorithm

Input files for ASE-MC manuscript

Quantitative assessment of catalytic cycles

Graph neural network prediction of electronic Hamiltonians in atomic orbital representation with many body messages

ORCA Python Interface

PyTorch Autodiff DFT-D3 Implementation.

MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, BrowserComp and xBench.

This is an active learning framework that uses single-ended growing string method and neural networks to build machine learning forcefields that quickly understands reactive energy landscape.

CrySPY is a crystal structure prediction tool written in Python.

jdr - SOTA performance on "DeepSearch" benchmarks in < 1500 lines of code

Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property c…

REICO-unbiased random sampling to generate diverse datasets encompassing a wide range of atomic configurations and bonding scenarios. EMLP trained by RECIO dataset can achieve genuine general and r…

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.