What is TPOT used for?

TPOT is a Python AutoML tool that uses genetic programming to search for and tune machine learning pipelines, built for data scientists working with scikit-learn. It is a good fit for speeding up model selection for data scientists and automating baseline machine learning pipelines.

Yes. TPOT is open source under the LGPL-3.0 licence. Its source code is on GitHub at EpistasisLab/tpot.

Yes. TPOT is open source, so the software itself is free to use.

What is TPOT an alternative to?

TPOT is an open-source alternative to DataRobot, Dataiku and H2O.ai. Other open-source alternatives to DataRobot include MLflow.

Is TPOT actively maintained?

The most recent commit to TPOT was on 11 September 2025, and the latest release is v1.1.0, published on 3 July 2025. The project has 10k stars on GitHub.

TPOT: open-source alternative to DataRobot, Dataiku, H2O.ai

About TPOT

TPOT, which stands for Tree-based Pipeline Optimization Tool and is published by Epistasis Lab, is a Python automated machine learning library. It uses genetic programming to explore and optimize machine learning pipelines, automating steps such as model selection, feature engineering and hyperparameter tuning, and its authors describe it as a data science assistant.

The current version is a ground-up rewrite, previously known as TPOT2, aimed at better efficiency and performance. It adds genetic feature selection, a more flexible way to define search spaces, multi-objective optimization and a modular framework for customizing the evolutionary algorithm. The README cites an academic paper describing the graph-based implementation.

TPOT is released under the LGPL-3.0 license and installs as a Python package, with documentation on the project website. The present version was developed by a team at Cedars-Sinai. It is a library you run in your own Python environment rather than a hosted service.

Key features

Genetic programming search over ML pipelines
Automated model selection and hyperparameter tuning
Genetic feature selection
Flexible search space definitions
Multi-objective optimization
Modular evolutionary algorithm framework
Built around scikit-learn pipelines

Good fit for

→Speeding up model selection for data scientists
→Automating baseline machine learning pipelines

Built with: Jupyter Notebook; Python
Tags: automl; machine-learning; python; genetic-programming; scikit-learn; hyperparameter-tuning; data-science; feature-engineering

TPOT: questions and answers

What is TPOT used for?: TPOT is a Python AutoML tool that uses genetic programming to search for and tune machine learning pipelines, built for data scientists working with scikit-learn. It is a good fit for speeding up model selection for data scientists and automating baseline machine learning pipelines.
Is TPOT open source?: Yes. TPOT is open source under the LGPL-3.0 licence. Its source code is on GitHub at EpistasisLab/tpot.
Is TPOT free?: Yes. TPOT is open source, so the software itself is free to use.
What is TPOT an alternative to?: TPOT is an open-source alternative to DataRobot, Dataiku and H2O.ai. Other open-source alternatives to DataRobot include MLflow.
Is TPOT actively maintained?: The most recent commit to TPOT was on 11 September 2025, and the latest release is v1.1.0, published on 3 July 2025. The project has 10k stars on GitHub.