The Best mgl Alternatives in 2026

PyTorch Geometric Temporal provides models and tools for spatiotemporal signal processing with neural learning.

This Common Lisp repository collects algorithms for online linear classification.

This repository implements random forest models in Common Lisp for classification tasks.

Bender helps developers build neural networks for iOS using TensorFlow models and Metal.

Katib automates machine learning on Kubernetes, including hyperparameter tuning and neural architecture search.

neural-fortran provides a parallel framework for deep learning in Fortran.

Archai supports neural architecture search with fast, reproducible, and modular research tools.

Learnergy is a Python library for energy-based machine learning models.

doddle-model is an in-memory machine learning library for Scala, built on Breeze with a scikit-learn-like API using typeclasses.

AutoKeras automates development of deep learning models through a machine learning library.

AutoGluon provides tools for automated machine learning and model development.

FEDOT automates machine learning model development through its modeling framework.

Enables single machine or distributed training and evaluation of deep learning models.

Detecto supports building and training computer vision models with the PyTorch machine learning framework.

ML_Forgex trains, evaluates, and predicts with machine learning models on cleaned datasets.

Auto_ViML builds multiple machine learning models with a single line of code.

AutoGL provides automated graph learning through a machine learning framework and toolkit.

Lightwood builds and customizes machine learning pipelines using a declarative JSON-AI syntax.

Guild AI automates and optimizes machine learning experiments while tracking each run.

m2cgen converts machine learning models into native code for multiple programming languages without runtime dependencies.

EvalML builds, optimizes, and evaluates machine learning pipelines with automated data checks and objective functions.

KerasTuner searches hyperparameters to optimize machine learning models built with Keras.

numpy-ml collects machine learning algorithms in NumPy, presented as an intentionally readable Python package.

Karate Club offers algorithms for unsupervised learning on graph data in Python.