Lists of open-source artificial intelligence software

Machine learning or data mining

Caffe — Image classification and image segmentation
Scikit-learn — library built on top of NumPy, SciPy, and matplotlib
Shogun — C++ library for large-scale machine learning
mlpack — C++ header-only machine learning library
Weka — collection of machine learning algorithms for data mining tasks
Apache Mahout — scalable machine learning library for big data built on Hadoop and Spark
Apache SystemDS — ML system for the end-to-end data science lifecycle
Jubatus — online machine learning and distributed computing framework
KNIME — modular data pipelining
Orange (software) — machine learning, data mining, data visualization, and data analysis.
RapidMiner — predictive analytics
fastText – Word embeddings developed by Meta AI
XGBoost — machine learning library for gradient boosting

TensorFlow – end-to-end open-source platform for machine learning developed by Google Brain^[1]
PyTorch – deep learning framework developed by Meta AI^[1]
PyTorch Lightning – high-level framework built on top of PyTorch for organizing and scaling deep learning models
Keras – Python library for artificial neural networks and integrated into TensorFlow library
MXNet – framework that trains and deploys deep neural networks
Caffe – deep learning framework focused on speed and modularity
Chainer – Python framework on top of NumPy and CuPy
Theano – Python library and optimizing compiler for evaluating mathematical expressions and optimized for GPUs
Deeplearning4j – Java library for the Java virtual machine and deep learning algorithms
Neuroph – object-oriented artificial neural network framework written in Java
Fast Artificial Neural Network (FANN) – C library for feedforward artificial neural networks

AlexNet — pioneering CNN for image classification, won the 2012 ImageNet competition
VGGNet — deep CNN known for its simplicity and use of 3x3 convolution filters
Inception — CNN architecture using parallel convolutional layers of different sizes

EDLUT – event-driven neural network simulator for large-scale spiking networks
Emergent – cognitive modeling platform implementing connectionist neural networks
Encog – machine learning framework for Java and C# supporting neural networks
JOONE – Java-based neural network framework with modular architecture for learning tasks
Nengo – Python library for building and simulating large-scale neural systems
Neuroph – lightweight Java framework for creating neural networks
OpenNN – C++ library for designing, training, and deploying neural networks
SNNS – Stuttgart Neural Network Simulator, supports feedforward and recurrent neural networks

OpenCog – project that aims to build an open source artificial intelligence framework
Soar – cognitive architecture for decision-making and learning in Intelligent agents
CLARION – Connectionist Learning with Adaptive Rule Induction On-line, hybrid connectionist/symbolic cognitive architecture.

GOLOG – logic programming language, situation calculus, first-order logical language for reasoning about action and change.

*model weights only

Hugging Face transformers library – Python library of pretrained transformer models for NLP, computer vision, speech, and more.
Fairseq – Facebook AI Research's sequence-to-sequence learning toolkit for training custom transformer models^[4]^{[additional citation(s) needed]}
OpenNMT – neural machine translation framework that supports transformer architectures^[5]^{[additional citation(s) needed]}

OpenVINO – Intel's toolkit for optimizing deep learning models for edge devices
ONNX – Open Neural Network Exchange format for interoperability between AI frameworks