The Best Spektral Alternatives in 2026

PyTorch Geometric provides graph neural network tools and libraries for PyTorch projects.

This repository provides segmentation models with pretrained backbones for Keras and TensorFlow Keras.

modAL provides a modular active learning framework for Python built on top of scikit-learn.

Little Ball of Fur provides graph sampling extensions for NetworKit and NetworkX.

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Adala automates data labeling through an autonomous agent framework for organizing labeled datasets.

Cornac provides a framework for comparing multimodal recommender systems and recommendation algorithms.

pytorch tabular provides a unified framework for deep learning models on tabular data.

nilearn provides Python tools for machine learning and neuroimaging analysis.

A Python package to assess and improve fairness of machine learning models.

The Featuretools Python library supports automated feature engineering and is published as open source.

Feature Engine provides Python tools for feature engineering and selection that are compatible with scikit-learn.

A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.

Python package which helps to debug machine learning classifiers and explain their predictions.

An open source Python library for drift detection in machine learning systems.

The lightly Python library supports self supervised learning on images.

Automated machine learning toolkit and a drop-in replacement for a scikit-learn estimator.

Giskard provides open source evaluation and testing tools for LLM agents.

Minimalist neural network library optimized for sparse data and single machine environments.

NALP covers Natural Adversarial Language Processing through a dedicated library.

neuropredict evaluates predictive performance using neuroimaging features.

Open-RAG-Eval evaluates retrieval-augmented generation without requiring golden answers.

This repository implements YOLOv3 variants in PyTorch for real time object detection, training, validation, inference, and export.

Captum explains model behavior and supports interpretability analysis for PyTorch systems.