Starred repositories
A smarter cd command. Supports all major shells.
The architector python package - for 3D metal complex design. C22085
A CLI tool for fetching and managing CIDR IP ranges from RIRs with firewall integration.
IP blocklist extension for Ubuntu ufw firewall
MatterSim: A deep learning atomistic model across elements, temperatures and pressures.
MSE 298 Final Project, Machine Learning for Materials Science; UCLA Winter 2025
Master programming by recreating your favorite technologies from scratch.
A deep learning model for predicting the size and morphology of colloidal nanocrystals (or quantum dots) from synthesis schemes
cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffDock, MACE, Allegro and NEQUIP, based on equivariant neural n…
train and use graph-based ML models of potential energy surfaces
A simple, fast and user-friendly alternative to 'find'
ORB forcefield models from Orbital Materials
High accuracy RAG for answering questions from scientific documents with citations
SevenNet - a graph neural network interatomic potential package supporting efficient multi-GPU parallel molecular dynamics simulations.
a curated list of resources for everyone interested in learning about digital chemistry
Literature survey, paper reviews, experimental setups and a collection of implementations for baselines methods for predictive uncertainty estimation in deep learning models.
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
A list of databases, datasets and books/handbooks where you can find materials properties for machine learning applications.
Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).
Minimal and clean examples of machine learning algorithms implementations
An overview of literature that discusses the use of machine learning for atomistic simulations
[TMLR 2025] Stability-Aware Training of Machine Learning Force Fields with Differentiable Boltzmann Estimators
A workflow for reproducible and open scientific articles
An extremely fast Python package and project manager, written in Rust.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step