Radar check
What we found when we opened it. Every bar is one fact, with its date.
Last code pushed 27 Oct 2025, 12 months before this check.
Latest release 1.5.1 on 27 Oct 2025.
Public since August 2022, a little over 4 years.
244 stars and 20 forks.
0 commits and 0 new issues in the last 90 days.
12 contributors. No pull requests merged in 90 days; changes go in directly.
No security policy file says how to report a problem. No published security advisories.
How the bars are scored
- Alive. Days since the last code push: a week or less 100, a month 90, three months 70, six months 50, a year 30, eighteen months 15, older 0.
- Releases. Age of the latest GitHub release, on a similar scale; no bar when the project publishes no releases.
- Maturity. Age of the project: eight years 100, five 90, three 70, two 55, one 40, six months 25, younger 10.
- Adoption. Stars on a log scale: 100,000 stars is 100, 10,000 is 80, 1,000 is 60, 100 is 40.
- Activity. Commits in the last 90 days: 300 or more 100, 100 85, 30 65, 10 45, any 25.
- Community. People who have contributed: 100 or more 100, 30 80, 10 60, 5 40, 2 25, one 10.
- Security. A published security policy 80, none 40; published advisories are listed, not scored.
Checked by Repo Radar on 26 Oct 2026 from the repository on GitHub.
In simple English
This tool automates the tedious work of preparing data for machine learning models. It takes tables of related data and time series, and then builds thousands of statistical features automatically. It runs much faster than similar open source tools by using a custom database engine written in C++. The community version is free to use for learning and experimentation, but it has restrictions against commercial use.
What it is
A Python library and companion engine for automated feature engineering on relational and time-series data. It generates thousands of candidate features, selects the best ones, and connects directly to standard machine learning predictors.
What it is good for
Data scientists and solo builders who want to speed up exploratory data analysis and model training on complex, multi-table datasets or time-series logs.
- Runs significantly faster than traditional feature engineering libraries.
- Includes out-of-the-box support for popular models like XGBoost.
- Provides a visual monitoring interface to inspect generated features and pipelines.
- The custom licence prohibits productive or commercial use without upgrading.
- Requires Docker on macOS and Windows to run the underlying engine service.
- Debugging complex relational data models can be difficult for non-specialists.
Manual feature engineering and slower Python feature generation scripts
XGBoost for making predictions on the generated features
- alteryx/featuretools7.7k stars
Automates feature engineering for relational datasets using a purely Python-based approach.
- blue-yonder/tsfresh9.5k stars
Extracts relevant features from time series for classification and regression tasks.
- basicmachines-co/basic-memory4.3k stars
Gives an AI assistant a memory that is stored as plain text files you can read.
- deepset-ai/haystack27k stars
A Python framework for joining language models, document search and tools into one working pipeline.
- Giskard-AI/giskard-oss5.9k stars
A Python library that writes tests for language-model programs and tries to break them on purpose.
pip install getml curl -L https://raw.githubusercontent.com/getml/getml-community/refs/heads/main/runtime/docker-compose.yml | docker compose -f - up