Machine Learning
APL
General-Purpose Machine Learning
C
General-Purpose Machine Learning
Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation.
A C library for product recommendations/suggestions using collaborative filtering (CF).
A hybrid recommender system based upon scikit-learn algorithms. [Deprecated]
An ONNX runtime written in pure C (99) with zero dependencies focused on small embedded devices. Run inference on your machine learning models no matter which framework you train it with. Easy to install and compiles everywhere, even in very old devices.
Python
neonrvm is an open source machine learning library based on RVM technique. It's written in C programming language and comes with Python programming language bindings.
A real-time multi-person keypoint detection library for body, face, hands, and foot estimation
A deep learning framework developed with cleanliness, readability, and speed in mind.
General purpose gradient boosting on decision trees library with categorical features support out of the box. It is easy to install, well documented and supports CPU and GPU (even multi-GPU) computation.
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit. Documentation can be found here.
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, JavaScript and more.
A high performance, easy-to-use, and scalable machine learning package, which can be used to solve large-scale machine learning problems. xLearn is especially useful for solving machine learning problems on large-scale sparse data, which is very common in Internet services such as online advertisement and recommender systems.
Python binding to C++ library for extracting and working with basic linguistic constructions such as n-grams and skipgrams in a quick and memory-efficient way.
A service for deployment Apache Spark MLLib machine learning models as realtime, batch or reactive web services.
Automated machine learning for production and analytics. Lets you focus on the fun parts of ML, while outputting production-ready code, and detailed analytics of your dataset and results. Includes support for NLP, XGBoost, CatBoost, LightGBM, and soon, deep learning.
Pretrain computer vision models on unlabeled data for industrial applications
Swarm Intelligence in Python (Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Algorithm, Immune Algorithm, Artificial Fish Swarm Algorithm in Python)
Face recognition library that recognizes and manipulates faces from Python or from the command line.
A lightweight face recognition and facial attribute analysis (age, gender, emotion and race) framework for Python covering cutting-edge models such as VGG-Face, FaceNet, OpenFace, DeepFace, DeepID, Dlib and ArcFace.
deep learning based cutting-edge facial detector for Python coming with facial landmarks
Easy to install and use deep learning Faster R-CNN face detection for images and video in a docker container. [Deprecated]
FAIR's software system that implements state-of-the-art object detection algorithms, including Mask R-CNN. It is written in Python and powered by the Caffe2 deep learning framework. [Deprecated]
FAIR's next-generation research platform for object detection and segmentation. It is a ground-up rewrite of the previous version, Detectron, and is powered by the PyTorch deep learning framework.
А fast and framework agnostic image augmentation library that implements a diverse set of augmentation techniques. Supports classification, segmentation, detection out of the box. Was used to win a number of Deep Learning competitions at Kaggle, Topcoder and those that were a part of the CVPR workshops.
Python-tesseract is an optical recognition (OCR) tool for python. That is, it will recognize and "read" the text embedded in images. Python-tesseract is a wrapper for Google's Tesseract-OCR Engine.
A library containing Convenience functions to make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with OpenCV and Python.
Generative AI Image Toolset with GANs and Diffusion for Real-World Applications.
A PyTorch implementation of Justin Johnson's neural-style (neural style transfer).
A PyTorch implementation of CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
TF-GAN is a lightweight library for training and evaluating Generative Adversarial Networks (GANs).
A PyTorch implementation of DeepDream. Allows individuals to quickly and easily train their own custom GoogleNet models with custom datasets for DeepDream.
Light face detection and recognition system with huge possibilities, based on Microsoft Face API and TensorFlow made for small IoT devices like raspberry pi.
face recognition system that can be easily integrated into any system without prior machine learning skills. CompreFace provides REST API for face recognition, face verification, face detection, face mask detection, landmark detection, age, and gender recognition and is easily deployed with docker.
as known as `L0CV`, is a new generation of computer vision open source online learning media, a cross-platform interactive learning framework integrating graphics, source code and HTML. the L0CV ecosystem — Notebook, Datasets, Source Code, and from Diving-in to Advanced — as well as the L0CV Hub.
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more.
A PyTorch-based toolkit that offers pre-trained segmentation models for computer vision tasks. It simplifies the development of image segmentation applications by providing a collection of popular architecture implementations, such as UNet and PSPNet, along with pre-trained weights, making it easier for researchers and developers to achieve high-quality pixel-level object segmentation in images.
A TensorFlow Keras-based toolkit that offers pre-trained segmentation models for computer vision tasks. It simplifies the development of image segmentation applications by providing a collection of popular architecture implementations, such as UNet and PSPNet, along with pre-trained weights, making it easier for researchers and developers to achieve high-quality pixel-level object segmentation in images.
MLX is an array framework for machine learning on Apple silicon, developed by Apple machine learning research.
A web mining module for the Python programming language. It has tools for natural language processing, machine learning, among others.
A python framework to transform natural language questions to queries in a database query language.
A sentence aligner, a friendly tool for extracting parallel sentences from comparable corpora. [Deprecated]
Python Natural Language Processing Library. General purpose NLP library for Python. Also contains some specific modules for parsing common NLP formats, most notably for FoLiA, but also ARPA language models, Moses phrasetables, GIZA++ alignments.
Python package that implements a novel white-box machine learning model for text classification, called SS3. Since SS3 has the ability to visually explain its rationale, this package also comes with easy-to-use interactive visualizations tools (online demos).
Python binding to ucto (a unicode-aware rule-based tokenizer for various languages).
Python binding to Frog, an NLP suite for Dutch. (pos tagging, lemmatisation, dependency parsing, NER)
Python bindings for ZPar, a statistical part-of-speech-tagger, constituency parser, and dependency parser for English.
Python interface for converting Penn Treebank trees to Stanford Dependencies.
Blazing fast, lightweight and customizable fuzzy and semantic text search in Python with fuzzywuzzy/thefuzz compatible API.
a python library for doing approximate and phonetic matching of strings.
A "machine learning framework to automate text-and voice-based conversations."
A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.
Natural Language Understanding library for intent classification and entity extraction
Named-entity recognition using neural networks providing state-of-the-art-results
A deep learning-based translation library between 50 languages, built with transformers.
A framework for building industrial-strength applications with Transformer models and LLMs.
Track, log, visualize and evaluate your LLM prompts and prompt chains.
The simplest way to run an LLM locally. Supports tool calling and grammar constrained sampling.
A deep learning library containing thousands of pre-trained models on different tasks. The goto place for anything related to Large Language Models.
Enterprise-Grade Graph RAG for Secure, On-Premise AI with Verifiable Attribution.
A distributed machine learning framework Apache Spark
A data-driven framework to quantify the value of classifiers in a machine learning ensemble.
A delightful machine learning tool that allows you to train/fit, test and use models without writing code
A Repository Containing Classification, Clustering, Regression, Recommender Notebooks with illustration to make them.
A temporal extension of PyTorch Geometric for dynamic graph representation learning.
A graph sampling extension library for NetworkX with a Scikit-Learn like API.
An unsupervised machine learning extension library for NetworkX with a Scikit-Learn like API.
Automatically Build Variant Interpretable ML models fast! AutoViML is pronounced "auto vimal", is a comprehensive and scalable Python AutoML toolkit with imbalanced handling, ensembling, stacking and built-in feature selection. Featured in <a href="https://towardsdatascience.com/why-automl-is-an-essential-new-tool-for-data-scientists-2d9ab4e25e46?source=friendslink&sk=d03a0cc55c23deb497d546d6b9be0653">Medium article</a>.
Python Outlier Detection, comprehensive and scalable Python toolkit for detecting outlying objects in multivariate data. Featured for Advanced models, including Neural Networks/Deep Learning and Outlier Ensembles.
Lightweight, Python library for fast and reproducible machine learning experimentation. Introduces a very simple interface that enables clean machine learning pipeline design.
Curated collection of the neural networks, transformers and models that make your machine learning work faster and more effective.
Unified interface for constructing and managing machine learning workflows on different workflow engines, such as Argo Workflows, Tekton Pipelines, and Apache Airflow.
High performance library for time series distances (DTW) and time series clustering.
Deep learning operations reinvented (for pytorch, tensorflow, jax and others).
automated build consisting of a web-interface, and set of programmatic-interface API, for support vector machines. Corresponding dataset(s) are stored into a SQL database, then generated model(s) used for prediction(s), are stored into a NoSQL datastore.
InterpretML implements the Explainable Boosting Machine (EBM), a modern, fully interpretable machine learning model based on Generalized Additive Models (GAMs). This open-source package also provides visualization tools for EBMs, other glass-box models, and black-box explanations.
a lightweight decision tree framework for Python with categorical feature support covering regular decision tree algorithms such as ID3, C4.5, CART, CHAID and regression tree; also some advanced bagging and boosting techniques such as gradient boosting, random forest and adaboost.
A set of tools for creating and testing machine learning features, with a scikit-learn compatible API.
Universal memory service with semantic search, autonomous consolidation, and multi-client support for AI applications.
A PyTorch-based framework to train and validate the models producing high-quality embeddings.
A seamless way to speed up your Scikit-learn applications with no accuracy loss and code changes.
Python implementation of many of the artificial intelligence algorithms described in the book "Artificial Intelligence, a Modern Approach". It focuses on providing an easy to use, well documented and tested library.
Python library for time series forecasting using machine learning models. It works with any regressor compatible with the scikit-learn API, including popular options like LightGBM, XGBoost, CatBoost, Keras, and many others.
Open source library with an exhaustive battery of feature engineering and selection methods based on pandas and scikit-learn.
Fast, flexible and fun neural networks. This is the successor of PyBrain.
Implementation of image to image (pix2pix) translation from the paper by isola et al.[DEEP LEARNING]
Restricted Boltzmann Machines in Python. [DEEP LEARNING]
Python implementation of cover trees, near-drop-in replacement for scipy.spatial.kdtree [Deprecated]
Aimied at novice machine learners and non-expert programmers, this package offers easy (no coding needed) and comprehensive machine learning (evaluation and full report of predictive performance WITHOUT requiring you to code) in Python for NeuroImaging and any other type of features. This is aimed at absorbing much of the ML workflow, unlike other packages like nilearn and pymvpa, which require you to learn their API and code to produce anything useful.
Open source platform for deploying machine learning models in production.
library for approximate unsupervised inference in Bayesian Hidden Markov Models (HMMs) and explicit-duration Hidden semi-Markov Models (HSMMs), focusing on the Bayesian Nonparametric extensions, the HDP-HMM and HDP-HSMM, mostly with weak-limit approximations.
A wrapper around scikit-learn that makes it simpler to conduct experiments.
Spearmint is a package to perform Bayesian optimization according to the algorithms outlined in the paper: Practical Bayesian Optimization of Machine Learning Algorithms. Jasper Snoek, Hugo Larochelle and Ryan P. Adams. Advances in Neural Information Processing Systems, 2012. [Deprecated]
Optimizing GPU-meta-programming code generating array oriented optimizing math compiler in Python.
Open source software library for numerical computation using data flow graphs.
Hidden Markov Models for Python, implemented in Cython for speed and efficiency.
A Python extension module wrapping the full TiMBL C++ programming interface. Timbl is an elaborate k-Nearest Neighbours machine learning toolkit.
A library consisting of useful tools for data science and machine learning tasks.
Nervana's high-performance Python-based Deep Learning framework [DEEP LEARNING]. [Deprecated]
Code samples for my book "Neural Networks and Deep Learning" [DEEP LEARNING].
Tool that automatically creates and optimizes machine learning pipelines using genetic programming. Consider it your personal data science assistant, automating a tedious part of machine learning.
The Deep Learning GPU Training System (DIGITS) is a web application for training deep learning models.
an IPython-based environment for conducting data-driven research in a consistent and reproducible way. REP is not trying to substitute scikit-learn, but extends it and provides better user experience. [Deprecated]
Simple machine learning library, including Perceptron, Regression, Support Vector Machine, Decision Tree and more, it's easy to use and easy to learn for beginners.
A web-based application for quick, scalable, and automated hyperparameter tuning and stacked ensembling.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
The lightweight PyTorch wrapper for high-performance AI research.
Toolbox of models, callbacks, and datasets for AI/ML researchers.
Implementations of Machine Learning models from scratch in Python with a focus on transparency. Aims to showcase the nuts and bolts of ML in an accessible way.
A library for Restricted Boltzmann Machine (RBM) and its conditional variants in Tensorflow.
Implementation of machine learning stacking technique as a handy library in Python.
A modular active learning framework for Python, built on top of scikit-learn.
A Modern, Fast, and Modular Deep Learning and Machine Learning framework for Python.
Parris, the automated infrastructure setup tool for machine learning algorithms.
Machine learning from Apple. Turi Create simplifies the development of custom machine learning models. You don't have to be a machine learning expert to add recommendations, object detection, image classification, image similarity or activity classification to your app.
A high performance, memory efficient, maximally parallelized ensemble learning, integrated with scikit-learn.
Examples and best practices for building recommendation systems, provided as Jupyter notebooks. The repo contains some of the latest state of the art algorithms from Microsoft Research as well as from other companies and institutions.
Machine Learning on Graphs, a Python library for machine learning on graph-structured (network-structured) data.
Toolkit for package and deploy machine learning models for serving in production
An asynchronous engine for continuous & autonomous machine learning, built for real-time usage.
Python toolbox for quick implementation, modification, evaluation, and visualization of ensemble learning algorithms for class-imbalanced data. Supports out-of-the-box multi-class imbalanced (long-tailed) classification.
The Fastest Gower Distance Implementation for Python. GPU-accelerated similarity matching for mixed data types, 15-25% faster than alternatives with production-ready reliability.
Python bindings for the BLLIP Natural Language Parser (also known as the Charniak-Johnson parser). [Deprecated]
C++
General-Purpose Machine Learning
In-context learning framework that allows agents to learn from execution feedback.
Automatically apply SOTA optimization techniques to achieve the maximum inference speed-up on your hardware. [DEEP LEARNING]
A machine learning API and server written in C++11. It makes state of the art machine learning easy to work with and integrate into existing applications.
A software library created by Amazon for training and deploying deep neural networks using GPUs which emphasizes speed and scale over experimental flexibility.
A dynamic neural network library working well with networks that have dynamic structures that change for every training instance. Written in C++ with bindings in Python.
A highly-modular C++ machine learning library for embedded electronics and robotics.
A high performance software library developed by Intel and optimized for Intel's architectures. Library provides algorithmic building blocks for all stages of data analytics and allows to process data in batch, online and distributed modes.
Microsoft's fast, distributed, high performance gradient boosting (GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
A production-ready library for multicalibration, fairness, and bias correction in machine learning models.
CEA-List's CAD framework for designing and simulating Deep Neural Network, and building full DNN-based applications on embedded platforms
An open-source cross-platform performance library for deep learning applications.
A general-purpose network embedding framework: pair-wise representations optimization Network Edit.
An open-source, low-code machine learning library in Python that automates machine learning workflows.
A fast parallel implementation of Connectionist Temporal Classification (CTC), on both CPU and GPU.
A header-only C++11 Neural Network library. Low dependency, native traditional chinese document.
A library for automated feature engineering. It excels at transforming transactional and relational datasets into feature matrices for machine learning using reusable feature engineering "primitives".
A library for learning neural networks, has C-interface, net set in JSON. Written in C++ with bindings in Python, C++ and C#.
A feature store for the management, discovery, and access of machine learning features. Feast provides a consistent view of feature data for both model training and model serving.
A data-intensive platform for AI with the industry's first open-source feature store. The Hopsworks Feature Store provides both a feature warehouse for training and batch based on Apache Hive and a feature serving database, based on MySQL Cluster, for online applications.
A platform for reproducible and scalable machine learning and deep learning.
Natural Language Processing
BLLIP Natural Language Parser (also known as the Charniak-Johnson parser).
Memory-based NLP suite developed for Dutch: PoS tagger, lemmatiser, dependency parser, NER, shallow parser, morphological analyzer.
MeTA : ModErn Text Analysis is a C++ Data Sciences Toolkit that facilitates mining big text data.
C, C++, and Python tools for named entity recognition and relation extraction
Speech Recognition
Gesture Detection
Reinforcement Learning
Data Science
Evaluate, trace, test, and ship LLM applications across your dev and production lifecycles.
A framework providing the right abstractions to ease research, development, and deployment of your ML pipelines.
A comparative framework for multimodal recommender systems with a focus on models leveraging auxiliary data.
JAX is Autograd and XLA, brought together for high-performance machine learning research.
High-level utils for PyTorch DL & RL research. It was developed with a focus on reproducibility, fast experimentation and code/ideas reusing. Being able to research/develop something new, rather than write another regular train loop.
High-level wrapper built on the top of Pytorch which supports vision, text, tabular data and collaborative filtering.
A machine learning framework for multi-output/multi-label and stream data.
A Pytorch based framework that breaks down machine learning problems into smaller blocks that can be glued together seamlessly with objective to build predictive models with one line of code.
An Automated Machine Learning (AutoML) python package for tabular data. It can handle: Binary Classification, MultiClass Classification and Regression. It provides explanations and markdown reports.
Scalable deep learning training platform, including integrated support for distributed training, hyperparameter tuning, experiment tracking, and model management.
Peer-to-peer network of data owners and data scientists who can collectively train AI models using PySyft
A Python library for quickly creating and sharing demos of models. Debug models interactively in your browser, get feedback from collaborators, and generate public links without deploying anything.
Fastest unstructured dataset management for TensorFlow/PyTorch. Stream & version-control data. Store even petabyte-scale data in a single numpy-like array on the cloud accessible on any machine. Visit activeloop.ai for more info.
An easy-to-use, Python-based feature store. Optimized for time-series data.
Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
An AutoML framework for the automated design of composite modelling pipelines. It can handle classification, regression, and time series forecasting tasks on different types of data (including multi-modal datasets).
An AutoML package for hyperparameters tuning using evolutionary algorithms, with built-in callbacks, plotting, remote logging and more.
Interactive reports to analyze machine learning models during validation or production monitoring.
Streamlit is an framework to create beautiful data apps in hours, not weeks.
Optuna is an automatic hyperparameter optimization software framework, particularly designed for machine learning.
Validation & testing of machine learning models and data during model development, deployment, and production. This includes checks and suites related to various types of issues, such as model performance, data integrity, distribution mismatches, and more.
Shapash is a Python library that provides several types of visualization that display explicit labels that everyone can understand.
Eurybia monitors data and model drift over time and securizes model deployment with data validation.
An open-source deep learning system for large-scale model training and inference with high efficiency and low cost.
Skrub is a Python library that eases preprocessing and feature engineering for machine learning on dataframes.
Free automated data & feature enrichment library for machine learning - automatically searches through thousands of ready-to-use features from public and community shared data sources and enriches your training dataset with only the accuracy improving features.
A tutorial to help machine learning researchers to automatically obtain optimized machine learning models with the optimal learning performance on any specific task.
A Python library for Bayesian Evidential Learning (BEL) in order to estimate the uncertainty of a prediction.
The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
Frouros is an open source Python library for drift detection in machine learning systems.
The best-in-class MLOps platform with experiment tracking, model production monitoring, a model registry, and data lineage from training straight through to production.
Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution.
Data Analysis / Data Visualization
A general-purpose Python library for Bayesian data analysis and visualization via serial/parallel Monte Carlo and MCMC simulations. Documentation can be found here.
A library to compare Pandas, Polars, and Spark data frames. It provides stats and lets users adjust for match accuracy.
AutoViz performs automatic visualization of any dataset with a single line of Python code. Give it any input file (CSV, txt or JSON) of any size and AutoViz will visualize it. See <a href="https://towardsdatascience.com/autoviz-a-new-tool-for-automated-visualization-ec9c1744a6ad?source=friends_link&sk=c9e9503ec424b191c6096d7e3f515d10">Medium article</a>.
A tensor-based framework for large-scale data computation which is often regarded as a parallel and distributed version of NumPy.
A high performance Python library for lazy Out-of-Core DataFrames (similar to Pandas), to visualize and explore big tabular datasets. Documentation can be found here.
A pure-python graphics and GUI library built on PyQt4 / PySide and NumPy.
GPU-based high-performance interactive OpenGL 2D/3D data visualization library.
A data exploration platform designed to be visual, intuitive, and interactive.
Self Organizing Map written in Python (Uses neural networks for data analysis).
Massively parallel self-organizing maps: accelerate training on multicore CPUs, GPUs, and clusters, has python API.
A visualization library for quick and easy generation of common plots in data analysis and machine learning.
A dashboard library for interactive visualizations using flask socketio and react.
Lime is about explaining what machine learning classifiers (or models) are doing. It is able to explain any black box classifier, with two or more classes.
PyCM is a multi-class confusion matrix library written in Python that supports both input data vectors and direct matrix, and a proper tool for post-classification model evaluation that supports most classes and overall statistics parameters
A framework for creating analytical web applications built on top of Plotly.js, React, and Flask
A workflow engine for solving machine learning problems by combining in one analysis pipeline (i) feature engineering and machine learning (ii) model training and prediction (iii) table population and column evaluation via user-defined (Python) functions.
Debugging and visualization tool for machine learning and data science. It extensively leverages Jupyter Notebook to show real-time visualizations of data in running processes such as machine learning training.
A little logger for machine learning research. Output any object to the terminal, CSV, TensorBoard, text logs on disk, and more with just one call to logger.log().
Ignite your models into blazing-fast machine learning APIs with a modern framework.
A GitHub Repository Where you can Learn Datavisualizatoin Basics to Intermediate level.
A general-purpose Python library for Bayesian data analysis and visualization via serial/parallel Monte Carlo and MCMC simulations. Documentation can be found here.
Business Intelligence (BI) in Python (Pandas web interface) [Deprecated]
Simple plotting for Python. Wrapper for D3xterjs; easily render charts in-browser.
Tools for writing, submitting, debugging, and monitoring Storm topologies in pure Python.
Matlab
General-Purpose Machine Learning
A complete object-oriented environment for machine learning in Matlab.
This package contains the matlab implementation of the algorithms described in the book Pattern Recognition and Machine Learning by C. Bishop.
Common Lisp
Clojure
Natural Language Processing
General-Purpose Machine Learning
A idiomatic Clojure machine learning library based on tech.ml.dataset with a unique approach for immutable data processing pipelines.
The Push programming language and the PushGP genetic programming system implemented in Clojure.
Simple, concise implementations of machine learning techniques and utilities in Clojure.
Clojure wrapper for Encog (v3) (Machine-Learning framework that specializes in neural-nets). [Deprecated]
Deep Learning
Data Analysis
Data Visualization
Clojure(Script) library and framework for creating interactive visualization applications based in Vega-Lite (VGL) and/or Vega (VG) specifications. Automatic framing and layouts along with a powerful templating system for abstracting visualization specs
Clojure(Script) client/server application for dynamic interactive explorations and the creation of live shareable documents capturing them using Vega/Vega-Lite, CodeMirror, markdown, and LaTeX
Data visualisation using Vega/Vega-Lite and Hiccup, and a live-reload platform for literate-programming
A Clojure/Clojurescript notebook application/-library based on Gorilla-REPL
Interop
Crystal
CUDA PTX
Neurosymbolic AI
Sovereign GPU-native spatial AI architecture with PTX-first cognitive engine (RPN/TRM reasoning), tri-modal fusion (text/visual/audio), and 3D persistent memory ("Houses"). Features sub-100µs inference, procedural knowledge compression (69:1 ratio), and multi-agent swarm architecture. Zero external dependencies for core inference paths.
Elixir
General-Purpose Machine Learning
Natural Language Processing
Erlang
General-Purpose Machine Learning
Fortran
General-Purpose Machine Learning
Go
Natural Language Processing
General-Purpose Machine Learning
Self-contained Machine Learning and Natural Language Processing library in Go.
A pure Go implementation of the prediction part of GBRTs, including XGBoost and LightGBM.
Fast and convenient feature processing for low latency machine learning in Go.
Go binding for MXNet cpredictapi to do inference with a pre-trained model.
An offline recommender system backend based on collaborative filtering written in Go.
Plug-and-play, parallel Go framework for NeuroEvolution of Augmenting Topologies (NEAT). [Deprecated]
Linear / Logistic regression, Neural Networks, Collaborative Filtering and Gaussian Multivariate Distribution. [Deprecated]
Spatial analysis and geometry
Data Analysis / Data Visualization
Haskell
Java
Natural Language Processing
ClearTK provides a framework for developing statistical natural language processing (NLP) components in Java and is built on top of Apache UIMA. [Deprecated]
The NLP4J project provides software and resources for natural language processing. The project started at the Center for Computational Language and EducAtion Research, and is currently developed by the Center for Language and Information Research at Emory University. [Deprecated]
This project collects a number of core libraries for Natural Language Processing (NLP) developed in the University of Illinois' Cognitive Computation Group, for example illinois-core-utilities which provides a set of NLP-friendly data structures and a number of NLP-related utilities that support writing NLP applications, running experiments, etc, illinois-edison a library for feature extraction from illinois-core-utilities data structures and many other packages.
General-Purpose Machine Learning
A machine learning library by Airbnb designed from the ground up to be human friendly.
A Java library for genetic algorithms, evolutionary computation, and stochastic local search, with a focus on self-adaptation / self-tuning, as well as parallel execution.
Machine Learning framework for rapid development of Machine Learning and Statistical applications.
Java toolkit for data mining. (unsupervised: clustering, outlier detection etc.)
An advanced neural network and machine learning framework. Encog contains classes to create a wide variety of networks, as well as support classes to normalize and process data for these neural networks. Encog trainings using multithreaded resilient propagation. Encog can also make use of a GPU to further speed processing time. A GUI based workbench is also provided to help model and train neural networks.
ML engine that supports distributed learning on Hadoop, Spark or your laptop via APIs in R, Python, Scala, REST/JSON.
General Machine Learning library using Numenta’s Cortical Learning Algorithm.
A Java port of SciPy's signal processing module, offering filters, transformations, and other scientific computing utilities.
Lambda Architecture Framework using Apache Spark and Apache Kafka with a specialization for real-time large-scale machine learning.
Data Analysis / Data Visualization
Deep Learning
JavaScript
Natural Language Processing
Data Analysis / Data Visualization
General-Purpose Machine Learning
Torch-like deep learning framework for Javascript with support for tensors, autograd, optimizers, and other neural net constructs.
Model Context Protocol server that exposes Creatify AI's video generation capabilities to AI assistants, enabling natural language video creation workflows.
Clustering algorithms implemented in JavaScript for Node.js and the browser. [Deprecated]
NodeJS Implementation of Decision Tree using ID3 Algorithm. [Deprecated]
Unsupervised machine learning with multivariate Gaussian mixture model.
FANN (Fast Artificial Neural Network Library) bindings for Node.js [Deprecated]
Simple JavaScript implementation of the k-means algorithm, for node.js and the browser. [Deprecated]
JavaScript implementation of logistic regression/c4.5 decision tree [Deprecated]
Bayesian bandit implementation for Node and the browser. [Deprecated]
JavaScript implementation of the k nearest neighbors algorithm for supervised learning.
C++ Neural Network library for Node.js. It has advantage on large dataset and multi-threaded training. [Deprecated]
Node.js library with support for both simple and multiple linear regression. [Deprecated]
Machine learning and numerical analysis tools for Node.js and the Browser!
Machine learning toolkit with classification and clustering for Node.js; supports visualization (see visualml.io).
A deep learning library for the browser, accelerated by WebGL and WebAssembly.
Fast Deep Neural Network JavaScript Framework. WebDNN uses next generation JavaScript API, WebGPU for GPU execution, and WebAssembly for CPU execution.
A JavaScript Native PyTorch-aligned Machine Learning Framework, built from scratch on WebGPU.
Misc
A standard library for JavaScript and Node.js, with an emphasis on numeric computing. The library provides a collection of robust, high performance libraries for mathematics, statistics, streams, utilities, and more.
A JavaScript implementation of descriptive, regression, and inference statistics. Implemented in literate JavaScript with no dependencies, designed to work in all modern browsers (including IE) as well as in Node.js.
A javascript library containing a collection of least squares fitting methods for finding a trend in a set of data.
Data Science with Python
Continually updated Data Science Python Notebooks: Spark, Hadoop MapReduce, HDFS, AWS, Kaggle, scikit-learn, matplotlib, pandas, NumPy, SciPy, and various command lines.
Some experiments with the coordinate descent algorithm used in the (Sparse) Group Lasso model.
Kanji / Hiragana / Katakana to Romaji Converter. Edict Dictionary & parallel sentences Search. Sentence Similarity between two JP Sentences. Sentiment Analysis of Japanese Text. Run Cabocha(ISO--8859-1 configured) in Python.
IPython notebooks for EEG/MEG data processing using mne-python.
IPython notebooks for a complete course around understanding Nervana's Neon.
Optimization library focused on machine learning, pythonic implementations of gradient descent, LBFGS, rmsprop, adadelta and others.
Code for Allen Downey's book Think Complexity.
Text and supporting code for Think OS: A Brief Introduction to Operating Systems.
"I learned Python by hacking first, and getting serious later. I wanted to do this with Machine Learning. If this is your style, join me in getting a bit ahead of yourself."
TensorDebugger (TDB) is a visual debugger for deep learning. It features interactive, node-by-node debugging and visualization for TensorFlow.
IPython notebooks from Data School's video tutorials on scikit-learn.
Notebooks and code for the book "Introduction to Machine Learning with Python"
Materials and IPython notebooks for "Python for Data Analysis" by Wes McKinney, published by O'Reilly Media
Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained
This repository contains Jupyter notebooks implementing the algorithms found in the book and summary of the textbook.
Code for hyperparameter tuning/optimization of machine learning and deep learning algorithms.
Given clinical parameters about a patient, can we predict whether or not they have heart disease?
This basically to gauge the understanding of Machine Learning Workflow and Regression technique in specific.
Julia
General-Purpose Machine Learning
A set of functions to support the development of machine learning algorithms.
Algorithms for regression analysis (e.g. linear regression and logistic regression).
A Julia package for manifold learning and nonlinear dimensionality reduction.
Natural Language Processing
Data Analysis / Data Visualization
Kotlin
Lua
General-Purpose Machine Learning
Cephes mathematical functions library, wrapped for Torch. Provides and wraps the 180+ special mathematical functions from the Cephes mathematical library, developed by Stephen L. Moshier. It is used, among many other places, at the heart of SciPy. [Deprecated]
Autograd automatically differentiates native Torch code. Inspired by the original Python version.
A signal processing toolbox for Torch-7. FFT, DCT, Hilbert, cepstrums, stft.
framework for torch which provides a set of abstractions aiming at encouraging code re-use as well as encouraging modular programming.
A completely unstable and experimental package that extends Torch's builtin nn library.
A Recurrent Neural Network library that extends Torch's nn. RNNs, LSTMs, GRUs, BRNNs, BLSTMs, etc.
A deep learning library designed for streamlining research and development using the Torch7 distribution. It emphasizes flexibility through the elegant use of object-oriented design patterns. [Deprecated]
An optimization library for Torch. SGD, Adagrad, Conjugate-Gradient, LBFGS, RProp and more.
A package for unsupervised learning in Torch. Provides modules that are compatible with nn (LinearPsd, ConvPsd, AutoEncoder, ...), and self-contained algorithms (k-means, PCA). [Deprecated]
OpenGM is a C++ library for graphical modelling, and inference. The Lua bindings provide a simple way of describing graphs, from Lua, and then optimizing them with OpenGM. [Deprecated]
A Lua wrapper around the Locality sensitive hashing library SHKit [Deprecated]
KNN, kernel-weighted average, local linear regression smoothers. [Deprecated]
An image/graph library for Torch. This package provides routines to construct graphs on images, segment them, build trees out of them, and convert them back to images. [Deprecated]
A video/graph library for Torch. This package provides routines to construct graphs on videos, segment them, build trees out of them, and convert them back to videos. [Deprecated]
code and tools around integral images. A library for finding interest points based on fast integral histograms. [Deprecated]
allows us to use hugin to stitch images and apply same stitching to a video sequence. [Deprecated]
A package for feature extraction in Torch. Provides SIFT and dSIFT modules. [Deprecated]
Demos and Scripts
.NET
Natural Language Processing
General-Purpose Machine Learning
Multi-platform genetic algorithm library for .NET Core and .NET Framework. The library has several implementations of GA operators, like: selection, crossover, mutation, reinsertion and termination.
ML.NET is a cross-platform open-source machine learning framework which makes machine learning accessible to .NET developers. ML.NET was originally developed in Microsoft Research and evolved into a significant framework over the last decade and is used across many product groups in Microsoft like Windows, Bing, PowerPoint, Excel and more.
Objective C
General-Purpose Machine Learning
Fast multilayer perceptron neural network library for iOS and Mac OS X. MLPNeuralNet predicts new examples by trained neural networks. It is built on top of the Apple's Accelerate Framework, using vectorized operations and hardware acceleration if available. [Deprecated]
An Objective-C multilayer perceptron library, with full support for training through backpropagation. Implemented using vDSP and vecLib, it's 20 times faster than its Java equivalent. Includes sample code for use from Swift.
It implemented 3 layers of neural networks ( Input Layer, Hidden Layer and Output Layer ) and it was named Back Propagation Neural Networks (BPN). This network can be used in products recommendation, user behavior analysis, data mining and data analysis. [Deprecated]
It implemented multi-perceptrons neural network (ニューラルネットワーク) based on Back Propagation Neural Networks (BPN) and designed unlimited-hidden-layers.
It is a non-supervisory and self-learning algorithm (adjust the weights) in the neural network of Machine Learning. [Deprecated]
OCaml
General-Purpose Machine Learning
OpenCV
OpenSource-Computer-Vision
Perl 6
Data Analysis / Data Visualization
PHP
Natural Language Processing
default
Machine Learning
Neural Networks
Variety of supported types of Artificial Neural Network and learning algorithms.
Simple API for Neural Network. Better for image processing with CPU/GPU + Transfer Learning.
nn_builder is a python package that lets you build neural networks in 1 line
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences. [Deprecated]
Neuron is simple class for time series predictions. It's utilize LNU (Linear Neural Unit), QNU (Quadratic Neural Unit), RBF (Radial Basis Function), MLP (Multi Layer Perceptron), MLP-ELM (Multi Layer Perceptron - Extreme Learning Machine) neural networks learned with Gradient descent or LeLevenberg–Marquardt algorithm. [Deprecated]
Very simple implementation of neural networks for dummies in python without using any libraries, with detailed comments.
TResNet models were designed and optimized to give the best speed-accuracy tradeoff out there on GPUs.
Federated Learning
Misc Scripts / iPython Notebooks / Codebases
A slightly larger, somewhat feature-complete, PyTorch-inspired, NumPy implementation of a tensor reverse-mode automatic differentiation engine.
Jupyter notebooks that cover how to implement from scratch different ML algorithms (ordinary least squares, gradient descent, k-means, alternating least squares), using Python NumPy, and how to then make these implementations scalable using Map/Reduce and Spark.
Spiking Neural Networks
A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware.
Python Survival Analysis
Kaggle Competition Source Code
> source code and experiments results for Home Credit Default Risk.
> source code and experiments results for Google AI Open Images - Object Detection Track.
> source code and experiments results for TGS Salt Identification Challenge.
source code and experiments results for Airbus Ship Detection Challenge.
source code and experiments results for 2018 Data Science Bowl.
source code and experiments results for Santander Value Prediction Challenge.
An implementation of Dell Zhang's solution to Wikipedia's Participation Challenge on Kaggle.
Code for the Kaggle acquire valued shoppers challenge.
Reinforcement Learning
DeepMind Lab is a 3D learning environment based on id Software's Quake III Arena via ioquake3 and other open source software. Its primary purpose is to act as a testbed for research in artificial intelligence, especially deep reinforcement learning.
A library for developing and comparing reinforcement learning algorithms (successor of gym).
Serpent.AI is a game agent framework that allows you to turn any video game you own into a sandbox to develop AI and machine learning experiments. For both researchers and hobbyists.
ViZDoom allows developing AI bots that play Doom using only the visual information (the screen buffer). It is primarily intended for research in machine visual learning, and deep reinforcement learning, in particular.
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
An Open Source Distributed Framework for Reinforcement Learning that makes build and train your agents easily.
An open source robotics benchmark for meta- and multi-task reinforcement learning
Application-oriented deep reinforcement learning framework addressing real-world decision problems.
RLlib is an industry level, highly scalable RL library for tf and torch, based on Ray. It's used by companies like Amazon and Microsoft to solve real-world decision making problems at scale.
DI-engine is a generalized Decision Intelligence engine. It supports most basic deep reinforcement learning (DRL) algorithms, such as DQN, PPO, SAC, and domain-specific algorithms like QMIX in multi-agent RL, GAIL in inverse RL, and RND in exploration problems.
Gym4ReaL is a comprehensive suite of realistic environments designed to support the development and evaluation of RL algorithms that can operate in real-world scenarios. The suite includes a diverse set of tasks exposing RL algorithms to a variety of practical challenges.
Speech Recognition
Ruby
Natural Language Processing
General-Purpose Machine Learning
Curated list of ML related resources for Ruby.
JRuby Mahout is a gem that unleashes the power of Apache Mahout in the world of JRuby. [Deprecated]
A general classifier module to allow Bayesian and other types of classifications.
Rust
General-Purpose Machine Learning
linfa aims to provide a comprehensive toolkit to build Machine Learning applications with Rust
deeplearn-rs provides simple networks that use matrix multiplication, addition, and ReLU under the MIT license.
a machine learning framework featuring logistic regression, support vector machines, decision trees and random forests.
open source framework for machine intelligence, sharing concepts from TensorFlow and Caffe. Available under the MIT license.
Deep Learning
R
SAS
Demos and Scripts
Example code and materials that illustrate applications of SAS machine learning techniques.
Example code and materials that illustrate techniques for integrating SAS with other analytics technologies in Java, PMML, Python and R.
Scala
Natural Language Processing
FACTORIE is a toolkit for deployable probabilistic modelling, implemented as a software library in Scala. It provides its users with a succinct language for creating relational factor graphs, estimating parameters and performing inference.
Data Analysis / Data Visualization
General-Purpose Machine Learning
An ONNX (Open Neural Network eXchange) API and backend for typeful, functional deep learning in Scala (3).
A genomics processing engine and specialized file format built using Apache Avro, Apache Spark and Parquet. Apache 2 licensed.
Simply written algorithms to help study ML or write your own implementations.
An in-memory machine learning library built on top of Breeze. It provides immutable objects and exposes its functionality through a scikit-learn-like API.
Tools
Misc
The AI-native database built for LLM applications, providing incredibly fast vector and full-text search. Developed using C++20
Qdrant is open source vector similarity search engine with extended filtering support, written in Rust.
Is an open source on-prem AI coding autonomous assistant that lives inside your repo, edits and tests files at SSD speed. Think Claude Code but with UI. plug in any LLM (OpenAI, Gemini, Ollama, etc.) and let it work for you.
Milvus is open source vector database for production AI, written in Go and C++, scalable and blazing fast for billions of embedding vectors.
Weaviate is an open source vector search engine and vector database. Weaviate uses machine learning to vectorize and store data, and to find answers to natural language queries. With Weaviate you can also bring your custom ML models to production scale.
Data Science Version Control is an open-source version control system for machine learning projects with pipelines support. It makes ML projects reproducible and shareable.
Python library for experiment metrics logging into simply formatted local files.
open source visual data ETL to streamline the end-to-end visual data processing pipeline: extract unstructured visual data from pre-built data sources, transform it into analysable structured insights by Vision AI models imported from various ML platforms, and load the insights into warehouses or applications.
Kedro is a data and development workflow framework that implements best practices for data pipelines with an eye towards productionizing machine learning models.
a lightweight library to define data transformations as a directed-acyclic graph (DAG). It helps author reliable feature engineering and machine learning pipelines, and more.
Python tool to help you configure, organize, log and reproduce experiments. Like a notebook lab in the context of Chemistry/Biology. The community has built multiple add-ons leveraging the proposed standard.
A tool that allows the conversion of ML models into native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart) with zero dependencies.
A library for doing continuous integration with ML projects. Use GitHub Actions & GitLab CI to train and evaluate models in production like environments and automatically generate visual reports with metrics and graphs in pull/merge requests. Framework & language agnostic.
ML powered analytics engine for outlier/anomaly detection and root cause analysis.
Aqueduct enables you to easily define, run, and manage AI & ML tasks on any cloud infrastructure.
Open-source LLM evaluation and red teaming framework. Test prompts, models, agents, and RAG pipelines. Run adversarial attacks (jailbreaks, prompt injection) and integrate security testing into CI/CD.
Open-source CLI security scanner for agentic workflows. Scans your workflow’s source code, detects vulnerabilities, and generates an interactive visualization along with a detailed security report. Supports LangGraph, CrewAI, n8n, OpenAI Agents, and more.
Open-source runtime security scanner for AI agents. Detects prompt injection, jailbreak, PII leakage, memory poisoning, and tool misuse. Zero deps, MIT licensed.
Visual AI agent workflow automation platform with local LLM integration. Build intelligent workflows using drag-and-drop, no cloud required.
Open source Kubernetes-style control plane for deploying AI agents as distributed microservices, with built-in service discovery, durable workflows, and observability.
Chrome extension that uses local LLMs to assist with writing and drafting responses based on the context of your open tabs.
Godot 4.x asset that enables NPCs to interact with players using local LLMs for structured, offline-first learning conversations in games.
Curated list of top Hugging Face models for NLP, vision, and audio tasks with demos and benchmarks.
Production-ready Multi-AI Agents framework with self-reflection. Fastest agent instantiation (3.77μs), 100+ LLM support via LiteLLM, MCP integration, agentic workflows (route/parallel/loop/repeat), built-in memory, Python & JS SDKs.
Open-source SDK for running LLMs and multimodal models on-device across iOS, Android, and cross-platform apps.
agentic AI operating system (h9y.ai) that replaces brittle/fragmented automations with long-lived, self-improving systems. Open-source, self-hosted/cloud, visual workflow, omni-channel, decentralized, extensible.
A VS Code extension for viewing and exploring large machine learning datasets (CSV, JSON, Parquet, etc.) directly within the editor without VS Code crashing in a clean UI.
A VS Code extension to view Weights & Biases experiments, logs, and artifacts within the IDE, eliminating the need to switch to the web UI and keeping data private.
All-in-one web-based IDE for machine learning and data science. The workspace is deployed as a docker container and is preloaded with a variety of popular data science libraries (e.g., Tensorflow, PyTorch) and dev tools (e.g., Jupyter, VS Code).
A starter kit for Jupyter notebooks and machine learning. Companion docker images consist of all combinations of python versions, machine learning frameworks (Keras, PyTorch and Tensorflow) and CPU/CUDA versions.
Deepnote is a drop-in replacement for Jupyter with an AI-first design, sleek UI, new blocks, and native data integrations. Use Python, R, and SQL locally in your favorite IDE, then scale to Deepnote cloud for real-time collaboration, Deepnote agent, and deployable data apps.
A curated collection of battle-tested tools, frameworks, and best practices for building, scaling, and monitoring production-grade Retrieval-Augmented Generation (RAG) systems. Covers frameworks, vector databases, retrieval & reranking, evaluation, observability, deployment, and security.
Swift
General-Purpose Machine Learning
Fast Neural Networks framework built on top of Metal. Supports TensorFlow models.
Highly optimized artificial intelligence and machine learning library written in Swift.
a next-generation platform for machine learning, incorporating the latest research across machine learning, compilers, differentiable programming, systems design, and beyond.
A bare bones library that includes a general matrix language and wraps some OpenCV for iOS development. [Deprecated]
A toolbox framework of AI modules written in Swift: Graphs/Trees, Linear Regression, Support Vector Machines, Neural Networks, PCA, KMeans, Genetic Algorithms, MDP, Mixture of Gaussians.
A simple Machine Learning Framework written in Swift. Currently features Simple Linear Regression, Polynomial Regression, and Ridge Regression.
The first neural network / machine learning library written in Swift. This is a project for AI algorithms in Swift for iOS and OS X development. This project includes algorithms focused on Bayes theorem, neural networks, SVMs, Matrices, etc...
Swift Language Bindings of TensorFlow. Using native TensorFlow models on both macOS / Linux.
TensorFlow
Books
This book teaches you how to take machine learning models from your personal laptop to large distributed clusters. You’ll explore key concepts and patterns behind successful distributed machine learning systems, and learn technologies like TensorFlow, Kubernetes, Kubeflow, and Argo Workflows directly from a key maintainer and contributor, with real-world scenarios and hands-on projects.