Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Library for efficient training and application of Machine Learning Interatomic Potentials (MLIP)

Confidence control and FDR estimation for de novo peptide sequencing

Foundation Models for Genomics & Transcriptomics

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

De novo peptide sequencing with InstaNovo: Accurate, database-free peptide identification for large scale proteomics experiments

Benchmarking and validation of Machine Learning Interatomic Potentials (MLIP)

Repo to host a model context protocol for file uploading and downloading up and from filebin.net

Code for the paper (Neurips 25 Oral) "Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies"