Find open-source science resources

E(3)-equivariant neural network interatomic potentials achieving DFT accuracy with up to 1000× less training data than invariant models, foundational architecture behind MACE and Allegro (Harvard, MIT, Nature Communications 2022)

Interactive and hardware-agnostic SDK for laboratory automation, enabling programmatic control of liquid handlers, plate readers, and other lab instruments across multiple vendors; foundational infrastructure for self-driving laboratories and AI-driven experimental execution (447+ stars)

LLM papers for scientific discovery

Equivariant graph attention Transformer (ICLR2023)

First agentic LLM for autonomous data science with end-to-end pipeline from data to analyst-grade reports

Deep learning library for Chemistry based on Tensorflow

Co-create PowerPoint presentations with Generative AI from documents or topics