Stars
Code release for Normalizing Flow Maps
PyTorch implementation of Parallel Rollout Approximation
BootLoops 1.0: certified computational tools and house engines for exact and high-precision physics and quantitative science, built to be driven by LLM agents. MIT; docs CC BY 4.0.
Differentiable, Hardware Accelerated, Molecular Dynamics
Codebase for Germinal, a broadly enabling generative pipeline for efficient generation of epitope-targeted de novo antibodies.
OpenMM plugin for running JAX force fields through JaxForce
Implementation of the time-dependent dual TRILEX theory
Implementation of the Euclidean fast attention (EFA) algorithm
One file. Under 200 lines. Zero dependencies. It's a coding agent.
Generative model for protein binder design for protein and small molecule targets. Combines a pretrained flow-based generative model (built on La-Proteina) with inference-time optimization.
ALCHEMI Toolkit-Ops is a collection of optimized batch kernels to accelerate computational chemistry and material science workflows.
JAX in JavaScript – ML library for the web, running on WebGPU & Wasm
DIfferentiable MOlecular Simulator (DIMOS): A pyTorch based framework for machine-learning enhanced simulations
BoltzGen: Toward Universal Binder Design
code for adjoint-based diffusion samplers
SO3LR Tauri: machine-learned force fields for reactive (bio)molecular simulations, from H to At
A debugging and profiling tool that can trace and visualize python code execution
Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems [ICML'25]
A JupyterLab and Jupyter Notebook extension for formatting code with Ruff.
[ICLR 2025 Spotlight] Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions
Predicting mutational effects on protein binding from folding energy. ICML 2025.