Products and open source
Tools for working with data, optimizing decisions, and building with machine learning.
4 projects
Flagship Product · Early Alpha
A local-first visual ETL tool for data and machine learning pipelines. Preview data at each node, then export standalone Python in pandas or Polars. Core is AGPL-3.0; the Plugin API and SDK are Apache-2.0. Version 0.3.0 is alpha software; the hosted marketplace is planned.
Open-Source Library
A Python library for hyperparameter tuning and feature selection with evolutionary algorithms. It works with scikit-learn estimators, cross-validation and scoring functions. The documentation includes examples for classifiers, regressors and pipelines.
Open-Source Library
A Python library for workforce planning: estimate staffing with Erlang-C and assign shifts subject to demand and scheduling constraints. Includes examples for call centers and operations teams.
Currently Building
An interactive learning platform for Data Science and Machine Learning: notebooks and SQL that run entirely in the browser, a skill graph that shows exactly what to learn next, guided learning paths toward data roles, and spaced-repetition review. Currently in private development.
GitHub stars and monthly PyPI downloads. Metrics snapshot: .
Architecture, data, and machine learning. Tell me what you need to build.
