Software

Modern science runs on tools as much as on ideas. Alongside our research, we build open-source infrastructure: the frameworks, pipelines and benchmarks that turn one-off analyses into reproducible, reusable capabilities.

We believe this is not a byproduct of research but part of its core. A well-designed tool compounds, accelerating not just our own discovery loop but that of every lab and R&D team that adopts it. Each release is versioned, tested, archived with a DOI, and built to outlive the paper that introduced it.

CADAQUES. Cost-Aware Dual Architecture for Query-Efficient Autonomous Discovery. A framework for autonomous experimentation under budget constraints: it decides which measurement to make next so that every query buys maximal information.

[Github]‍ ‍[Documentation]‍ ‍[Preprint]

ALTEA. Autonomous Learning for Tomographic Ensembles and Attributes. A reproducible, provenance-tracked pipeline for tomographic image stacks: automated slice quality control, learned segmentation, and quantitative 3D morphometry of heterogeneous materials.

[Github]‍ ‍[Documentation]