[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-434":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":9,"rankLanguage":9,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":24,"topics":25,"createdAt":9,"pushedAt":9,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":15,"starSnapshotCount":15,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},434,"awesome-machine-learning","josephmisiti\u002Fawesome-machine-learning","josephmisiti","A curated list of awesome Machine Learning frameworks, libraries and software.",null,"Python",72746,15478,3248,1,0,16,60,322,64,45,"Other",false,"master",true,[],"2026-06-12 02:00:13","# Awesome Machine Learning [![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome) [![Track Awesome List](https:\u002F\u002Fwww.trackawesomelist.com\u002Fbadge.svg)](https:\u002F\u002Fwww.trackawesomelist.com\u002Fjosephmisiti\u002Fawesome-machine-learning\u002F)\n\nA curated list of awesome machine learning frameworks, libraries and software (by language). Inspired by `awesome-php`.\n\n## IMPORTANT NOTE ON PRs:\n\nAs of April 2026, too many PRs are being generated by LLMs, this is no longer fun or manageable. If you want to contribute to this repo, email me at joseph dot misiti @ hey dot com to prove you're human with a link to your PR and I'll merge it. Thank you for your understanding.\n\nAlso, a listed repository should be deprecated if:\n\n* Repository's owner explicitly says that \"this library is not maintained\".\n* Not committed for a long time (2~3 years).\n\nFurther resources:\n\n* For a list of free machine learning books available for download, go [here](https:\u002F\u002Fgithub.com\u002Fjosephmisiti\u002Fawesome-machine-learning\u002Fblob\u002Fmaster\u002Fbooks.md).\n\n* For a list of professional machine learning events, go [here](https:\u002F\u002Fgithub.com\u002Fjosephmisiti\u002Fawesome-machine-learning\u002Fblob\u002Fmaster\u002Fevents.md).\n\n* For a list of (mostly) free machine learning courses available online, go [here](https:\u002F\u002Fgithub.com\u002Fjosephmisiti\u002Fawesome-machine-learning\u002Fblob\u002Fmaster\u002Fcourses.md).\n\n* For a list of blogs and newsletters on data science and machine learning, go [here](https:\u002F\u002Fgithub.com\u002Fjosephmisiti\u002Fawesome-machine-learning\u002Fblob\u002Fmaster\u002Fblogs.md).\n\n* For a list of free-to-attend meetups and local events, go [here](https:\u002F\u002Fgithub.com\u002Fjosephmisiti\u002Fawesome-machine-learning\u002Fblob\u002Fmaster\u002Fmeetups.md).\n\n## Star History\n\n\u003Ca href=\"https:\u002F\u002Fwww.star-history.com\u002F?repos=josephmisiti%2Fawesome-machine-learning&type=date&legend=top-left\">\n \u003Cpicture>\n   \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=josephmisiti\u002Fawesome-machine-learning&type=date&theme=dark&legend=top-left\" \u002F>\n   \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=josephmisiti\u002Fawesome-machine-learning&type=date&legend=top-left\" \u002F>\n   \u003Cimg alt=\"Star History Chart\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=josephmisiti\u002Fawesome-machine-learning&type=date&legend=top-left\" \u002F>\n \u003C\u002Fpicture>\n\u003C\u002Fa>\n\n## Table of Contents\n\n### Frameworks and Libraries\n\u003C!-- MarkdownTOC depth=4 -->\n\u003C!-- Contents-->\n- [Awesome Machine Learning ![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](#awesome-machine-learning-)\n  - [Table of Contents](#table-of-contents)\n    - [Frameworks and Libraries](#frameworks-and-libraries)\n    - [Tools](#tools)\n  - [APL](#apl)\n      - [General-Purpose Machine Learning](#apl-general-purpose-machine-learning)\n  - [C](#c)\n      - [General-Purpose Machine Learning](#c-general-purpose-machine-learning)\n      - [Computer Vision](#c-computer-vision)\n  - [C++](#cpp)\n      - [Computer Vision](#cpp-computer-vision)\n      - [General-Purpose Machine Learning](#cpp-general-purpose-machine-learning)\n      - [Natural Language Processing](#cpp-natural-language-processing)\n      - [Speech Recognition](#cpp-speech-recognition)\n      - [Sequence Analysis](#cpp-sequence-analysis)\n      - [Gesture Detection](#cpp-gesture-detection)\n      - [Reinforcement Learning](#cpp-reinforcement-learning)\n  - [Common Lisp](#common-lisp)\n      - [General-Purpose Machine Learning](#common-lisp-general-purpose-machine-learning)\n  - [Clojure](#clojure)\n      - [Natural Language Processing](#clojure-natural-language-processing)\n      - [General-Purpose Machine Learning](#clojure-general-purpose-machine-learning)\n      - [Deep Learning](#clojure-deep-learning)\n      - [Data Analysis](#clojure-data-analysis--data-visualization)\n      - [Data Visualization](#clojure-data-visualization)\n      - [Interop](#clojure-interop)\n      - [Misc](#clojure-misc)\n      - [Extra](#clojure-extra)\n  - [Crystal](#crystal)\n      - [General-Purpose Machine Learning](#crystal-general-purpose-machine-learning)\n  - [CUDA PTX](#cuda-ptx)\n      - [Neurosymbolic AI](#cuda-ptx-neurosymbolic-ai)\n  - [Elixir](#elixir)\n      - [General-Purpose Machine Learning](#elixir-general-purpose-machine-learning)\n      - [Natural Language Processing](#elixir-natural-language-processing)\n  - [Erlang](#erlang)\n      - [General-Purpose Machine Learning](#erlang-general-purpose-machine-learning)\n  - [Fortran](#fortran)\n      - [General-Purpose Machine Learning](#fortran-general-purpose-machine-learning)\n      - [Data Analysis \u002F Data Visualization](#fortran-data-analysis--data-visualization)\n  - [Go](#go)\n      - [Natural Language Processing](#go-natural-language-processing)\n      - [General-Purpose Machine Learning](#go-general-purpose-machine-learning)\n      - [Spatial analysis and geometry](#go-spatial-analysis-and-geometry)\n      - [Data Analysis \u002F Data Visualization](#go-data-analysis--data-visualization)\n      - [Computer vision](#go-computer-vision)\n      - [Reinforcement learning](#go-reinforcement-learning)\n  - [Haskell](#haskell)\n      - [General-Purpose Machine Learning](#haskell-general-purpose-machine-learning)\n  - [Java](#java)\n      - [Natural Language Processing](#java-natural-language-processing)\n      - [General-Purpose Machine Learning](#java-general-purpose-machine-learning)\n      - [Speech Recognition](#java-speech-recognition)\n      - [Data Analysis \u002F Data Visualization](#java-data-analysis--data-visualization)\n      - [Deep Learning](#java-deep-learning)\n  - [Javascript](#javascript)\n      - [Natural Language Processing](#javascript-natural-language-processing)\n      - [Data Analysis \u002F Data Visualization](#javascript-data-analysis--data-visualization)\n      - [General-Purpose Machine Learning](#javascript-general-purpose-machine-learning)\n      - [Misc](#javascript-misc)\n      - [Demos and Scripts](#javascript-demos-and-scripts)\n  - [Julia](#julia)\n      - [General-Purpose Machine Learning](#julia-general-purpose-machine-learning)\n      - [Natural Language Processing](#julia-natural-language-processing)\n      - [Data Analysis \u002F Data Visualization](#julia-data-analysis--data-visualization)\n      - [Misc Stuff \u002F Presentations](#julia-misc-stuff--presentations)\n  - [Kotlin](#kotlin)\n      - [Deep Learning](#kotlin-deep-learning)\n  - [Lua](#lua)\n      - [General-Purpose Machine Learning](#lua-general-purpose-machine-learning)\n      - [Demos and Scripts](#lua-demos-and-scripts)\n  - [Matlab](#matlab)\n      - [Computer Vision](#matlab-computer-vision)\n      - [Natural Language Processing](#matlab-natural-language-processing)\n      - [General-Purpose Machine Learning](#matlab-general-purpose-machine-learning)\n      - [Data Analysis \u002F Data Visualization](#matlab-data-analysis--data-visualization)\n  - [.NET](#net)\n      - [Computer Vision](#net-computer-vision)\n      - [Natural Language Processing](#net-natural-language-processing)\n      - [General-Purpose Machine Learning](#net-general-purpose-machine-learning)\n      - [Data Analysis \u002F Data Visualization](#net-data-analysis--data-visualization)\n  - [Objective C](#objective-c)\n    - [General-Purpose Machine Learning](#objective-c-general-purpose-machine-learning)\n  - [OCaml](#ocaml)\n    - [General-Purpose Machine Learning](#ocaml-general-purpose-machine-learning)\n  - [OpenCV](#opencv)\n    - [Computer Vision](#opencv-Computer-Vision)\n    - [Text-Detection](#Text-Character-Number-Detection)\n  - [Perl](#perl)\n    - [Data Analysis \u002F Data Visualization](#perl-data-analysis--data-visualization)\n    - [General-Purpose Machine Learning](#perl-general-purpose-machine-learning)\n  - [Perl 6](#perl-6)\n    - [Data Analysis \u002F Data Visualization](#perl-6-data-analysis--data-visualization)\n    - [General-Purpose Machine Learning](#perl-6-general-purpose-machine-learning)\n  - [PHP](#php)\n    - [Natural Language Processing](#php-natural-language-processing)\n    - [General-Purpose Machine Learning](#php-general-purpose-machine-learning)\n  - [Python](#python)\n      - [Computer Vision](#python-computer-vision)\n      - [Natural Language Processing](#python-natural-language-processing)\n      - [General-Purpose Machine Learning](#python-general-purpose-machine-learning)\n      - [Data Analysis \u002F Data Visualization](#python-data-analysis--data-visualization)\n      - [Misc Scripts \u002F iPython Notebooks \u002F Codebases](#python-misc-scripts--ipython-notebooks--codebases)\n      - [Neural Networks](#python-neural-networks)\n      - [Survival Analysis](#python-survival-analysis)\n      - [Federated Learning](#python-federated-learning)\n      - [Kaggle Competition Source Code](#python-kaggle-competition-source-code)\n      - [Reinforcement Learning](#python-reinforcement-learning)\n      - [Speech Recognition](#python-speech-recognition)\n  - [Ruby](#ruby)\n      - [Natural Language Processing](#ruby-natural-language-processing)\n      - [General-Purpose Machine Learning](#ruby-general-purpose-machine-learning)\n      - [Data Analysis \u002F Data Visualization](#ruby-data-analysis--data-visualization)\n      - [Misc](#ruby-misc)\n  - [Rust](#rust)\n      - [General-Purpose Machine Learning](#rust-general-purpose-machine-learning)\n      - [Deep Learning](#rust-deep-learning)\n      - [Natural Language Processing](#rust-natural-language-processing)\n  - [R](#r)\n      - [General-Purpose Machine Learning](#r-general-purpose-machine-learning)\n      - [Data Analysis \u002F Data Visualization](#r-data-analysis--data-visualization)\n  - [SAS](#sas)\n      - [General-Purpose Machine Learning](#sas-general-purpose-machine-learning)\n      - [Data Analysis \u002F Data Visualization](#sas-data-analysis--data-visualization)\n      - [Natural Language Processing](#sas-natural-language-processing)\n      - [Demos and Scripts](#sas-demos-and-scripts)\n  - [Scala](#scala)\n      - [Natural Language Processing](#scala-natural-language-processing)\n      - [Data Analysis \u002F Data Visualization](#scala-data-analysis--data-visualization)\n      - [General-Purpose Machine Learning](#scala-general-purpose-machine-learning)\n  - [Scheme](#scheme)\n      - [Neural Networks](#scheme-neural-networks)\n  - [Swift](#swift)\n      - [General-Purpose Machine Learning](#swift-general-purpose-machine-learning)\n  - [TensorFlow](#tensorflow)\n      - [General-Purpose Machine Learning](#tensorflow-general-purpose-machine-learning)\n\n### [Tools](#tools-1)\n\n- [Neural Networks](#tools-neural-networks)\n- [Misc](#tools-misc)\n\n\n[Credits](#credits)\n\n\u003C!-- \u002FMarkdownTOC -->\n\n\u003Ca name=\"apl\">\u003C\u002Fa>\n## APL\n\n\u003Ca name=\"apl-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n* [naive-apl](https:\u002F\u002Fgithub.com\u002Fmattcunningham\u002Fnaive-apl) - Naive Bayesian Classifier implementation in APL. **[Deprecated]**\n\n\u003Ca name=\"c\">\u003C\u002Fa>\n## C\n\n\u003Ca name=\"c-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n* [Darknet](https:\u002F\u002Fgithub.com\u002Fpjreddie\u002Fdarknet) - 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.\n* [Recommender](https:\u002F\u002Fgithub.com\u002FGHamrouni\u002FRecommender) - A C library for product recommendations\u002Fsuggestions using collaborative filtering (CF).\n* [Hybrid Recommender System](https:\u002F\u002Fgithub.com\u002FSeniorSA\u002Fhybrid-rs-trainner) - A hybrid recommender system based upon scikit-learn algorithms. **[Deprecated]**\n* [neonrvm](https:\u002F\u002Fgithub.com\u002Fsiavashserver\u002Fneonrvm) - 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.\n* [cONNXr](https:\u002F\u002Fgithub.com\u002Falrevuelta\u002FcONNXr) - 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.\n* [libonnx](https:\u002F\u002Fgithub.com\u002Fxboot\u002Flibonnx) - A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.\n* [onnx-c](https:\u002F\u002Fgithub.com\u002Fonnx\u002Fonnx-c) - A lightweight C library for ONNX model inference, optimized for performance and portability across platforms.\n* [qsmm](http:\u002F\u002Fqsmm.org) - A C library implementing the rudiments of a toolchain for working with adaptive probabilistic assembler programs.\n\n\u003Ca name=\"c-computer-vision\">\u003C\u002Fa>\n#### Computer Vision\n\n* [CCV](https:\u002F\u002Fgithub.com\u002Fliuliu\u002Fccv) - C-based\u002FCached\u002FCore Computer Vision Library, A Modern Computer Vision Library.\n* [VLFeat](http:\u002F\u002Fwww.vlfeat.org\u002F) - VLFeat is an open and portable library of computer vision algorithms, which has a Matlab toolbox.\n* [YOLOv8](https:\u002F\u002Fgithub.com\u002Fultralytics\u002Fultralytics) - Ultralytics' YOLOv8 implementation with C++ support for real-time object detection and tracking, optimized for edge devices.\n* [SpecX](https:\u002F\u002Fspecx.pro) - Specialized AI vision for extracting engineering specs from PDF\u002FJPG to Excel.\n\n\u003Ca name=\"cpp\">\u003C\u002Fa>\n## C++\n\n\u003Ca name=\"cpp-computer-vision\">\u003C\u002Fa>\n#### Computer Vision\n\n* [DLib](http:\u002F\u002Fdlib.net\u002Fimaging.html) - DLib has C++ and Python interfaces for face detection and training general object detectors.\n* [EBLearn](http:\u002F\u002Feblearn.sourceforge.net\u002F) - Eblearn is an object-oriented C++ library that implements various machine learning models **[Deprecated]**\n* [OpenCV](https:\u002F\u002Fopencv.org) - OpenCV has C++, C, Python, Java and MATLAB interfaces and supports Windows, Linux, Android and Mac OS.\n* [VIGRA](https:\u002F\u002Fgithub.com\u002Fukoethe\u002Fvigra) - VIGRA is a genertic cross-platform C++ computer vision and machine learning library for volumes of arbitrary dimensionality with Python bindings.\n* [Openpose](https:\u002F\u002Fgithub.com\u002FCMU-Perceptual-Computing-Lab\u002Fopenpose) - A real-time multi-person keypoint detection library for body, face, hands, and foot estimation\n\n\u003Ca name=\"cpp-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* * [Agentic Context Engine](https:\u002F\u002Fgithub.com\u002Fkayba-ai\u002Fagentic-context-engine) -In-context learning framework that allows agents to learn from execution feedback.\n* [Speedster](https:\u002F\u002Fgithub.com\u002Fnebuly-ai\u002Fnebullvm\u002Ftree\u002Fmain\u002Fapps\u002Faccelerate\u002Fspeedster) -Automatically apply SOTA optimization techniques to achieve the maximum inference speed-up on your hardware. [DEEP LEARNING]\n* [BanditLib](https:\u002F\u002Fgithub.com\u002Fjkomiyama\u002Fbanditlib) - A simple Multi-armed Bandit library. **[Deprecated]**\n* [Caffe](https:\u002F\u002Fgithub.com\u002FBVLC\u002Fcaffe) - A deep learning framework developed with cleanliness, readability, and speed in mind. [DEEP LEARNING]\n* [CatBoost](https:\u002F\u002Fgithub.com\u002Fcatboost\u002Fcatboost) - General purpose gradient boosting on decision trees library with categorical features support out of the box. It is easy to install, contains fast inference implementation and supports CPU and GPU (even multi-GPU) computation.\n* [CNTK](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FCNTK) - The Computational Network Toolkit (CNTK) by Microsoft Research, is a unified deep-learning toolkit that describes neural networks as a series of computational steps via a directed graph.\n* [CUDA](https:\u002F\u002Fcode.google.com\u002Fp\u002Fcuda-convnet\u002F) - This is a fast C++\u002FCUDA implementation of convolutional [DEEP LEARNING]\n* [DeepDetect](https:\u002F\u002Fgithub.com\u002Fjolibrain\u002Fdeepdetect) - 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.\n* [Distributed Machine learning Tool Kit (DMTK)](http:\u002F\u002Fwww.dmtk.io\u002F) - A distributed machine learning (parameter server) framework by Microsoft. Enables training models on large data sets across multiple machines. Current tools bundled with it include: LightLDA and Distributed (Multisense) Word Embedding.\n* [DLib](http:\u002F\u002Fdlib.net\u002Fml.html) - A suite of ML tools designed to be easy to imbed in other applications.\n* [DSSTNE](https:\u002F\u002Fgithub.com\u002Famznlabs\u002Famazon-dsstne) - A software library created by Amazon for training and deploying deep neural networks using GPUs which emphasizes speed and scale over experimental flexibility.\n* [DyNet](https:\u002F\u002Fgithub.com\u002Fclab\u002Fdynet) - 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.\n* [Fido](https:\u002F\u002Fgithub.com\u002FFidoProject\u002FFido) - A highly-modular C++ machine learning library for embedded electronics and robotics.\n* [FlexML](https:\u002F\u002Fgithub.com\u002Fozguraslank\u002Fflexml) - Easy-to-use and flexible AutoML library for Python.\n* [igraph](http:\u002F\u002Figraph.org\u002F) - General purpose graph library.\n* [Intel® oneAPI Data Analytics Library](https:\u002F\u002Fgithub.com\u002Foneapi-src\u002FoneDAL) - 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.\n* [LightGBM](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FLightGBM) - 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.\n* [libfm](https:\u002F\u002Fgithub.com\u002Fsrendle\u002Flibfm) - A generic approach that allows to mimic most factorization models by feature engineering.\n* [MCGrad](https:\u002F\u002Fgithub.com\u002Ffacebookincubator\u002FMCGrad\u002F) - A production-ready library for multicalibration, fairness, and bias correction in machine learning models.\n* [MLDB](https:\u002F\u002Fmldb.ai) - The Machine Learning Database is a database designed for machine learning. Send it commands over a RESTful API to store data, explore it using SQL, then train machine learning models and expose them as APIs.\n* [mlpack](https:\u002F\u002Fwww.mlpack.org\u002F) - A scalable C++ machine learning library.\n* [MXNet](https:\u002F\u002Fgithub.com\u002Fapache\u002Fincubator-mxnet) - Lightweight, Portable, Flexible Distributed\u002FMobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, JavaScript and more.\n* [N2D2](https:\u002F\u002Fgithub.com\u002FCEA-LIST\u002FN2D2) - CEA-List's CAD framework for designing and simulating Deep Neural Network, and building full DNN-based applications on embedded platforms\n* [oneDNN](https:\u002F\u002Fgithub.com\u002Foneapi-src\u002FoneDNN) - An open-source cross-platform performance library for deep learning applications.\n* [Opik](https:\u002F\u002Fwww.comet.com\u002Fsite\u002Fproducts\u002Fopik\u002F) - Open source engineering platform to debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards. ([Source Code](https:\u002F\u002Fgithub.com\u002Fcomet-ml\u002Fopik\u002F))\n* [Ombre](https:\u002F\u002Fgithub.com\u002Fpypl0\u002FOmbre) - Open source AI infrastructure layer. Eight agents run automatically: security, caching, memory, hallucination detection, and tamper-proof audit trail. Runs locally.\n  * [ParaMonte](https:\u002F\u002Fgithub.com\u002Fcdslaborg\u002Fparamonte) - A general-purpose library with C\u002FC++ interface for Bayesian data analysis and visualization via serial\u002Fparallel Monte Carlo and MCMC simulations. Documentation can be found [here](https:\u002F\u002Fwww.cdslab.org\u002Fparamonte\u002F).\n* [proNet-core](https:\u002F\u002Fgithub.com\u002Fcnclabs\u002FproNet-core) - A general-purpose network embedding framework: pair-wise representations optimization Network Edit.\n* [PyCaret](https:\u002F\u002Fgithub.com\u002Fpycaret\u002Fpycaret) - An open-source, low-code machine learning library in Python that automates machine learning workflows.\n* [PyCUDA](https:\u002F\u002Fmathema.tician.de\u002Fsoftware\u002Fpycuda\u002F) - Python interface to CUDA\n* [ROOT](https:\u002F\u002Froot.cern.ch) - A modular scientific software framework. It provides all the functionalities needed to deal with big data processing, statistical analysis, visualization and storage.\n* [shark](http:\u002F\u002Fimage.diku.dk\u002Fshark\u002Fsphinx_pages\u002Fbuild\u002Fhtml\u002Findex.html) - A fast, modular, feature-rich open-source C++ machine learning library.\n* [Shogun](https:\u002F\u002Fgithub.com\u002Fshogun-toolbox\u002Fshogun) - The Shogun Machine Learning Toolbox.\n* [sofia-ml](https:\u002F\u002Fcode.google.com\u002Farchive\u002Fp\u002Fsofia-ml) - Suite of fast incremental algorithms.\n* [Stan](http:\u002F\u002Fmc-stan.org\u002F) - A probabilistic programming language implementing full Bayesian statistical inference with Hamiltonian Monte Carlo sampling.\n* [Timbl](https:\u002F\u002Flanguagemachines.github.io\u002Ftimbl\u002F) - A software package\u002FC++ library implementing several memory-based learning algorithms, among which IB1-IG, an implementation of k-nearest neighbor classification, and IGTree, a decision-tree approximation of IB1-IG. Commonly used for NLP.\n* [Vowpal Wabbit (VW)](https:\u002F\u002Fgithub.com\u002FVowpalWabbit\u002Fvowpal_wabbit) - A fast out-of-core learning system.\n* [Warp-CTC](https:\u002F\u002Fgithub.com\u002Fbaidu-research\u002Fwarp-ctc) - A fast parallel implementation of Connectionist Temporal Classification (CTC), on both CPU and GPU.\n* [XGBoost](https:\u002F\u002Fgithub.com\u002Fdmlc\u002Fxgboost) - A parallelized optimized general purpose gradient boosting library.\n* [ThunderGBM](https:\u002F\u002Fgithub.com\u002FXtra-Computing\u002Fthundergbm) - A fast library for GBDTs and Random Forests on GPUs.\n* [ThunderSVM](https:\u002F\u002Fgithub.com\u002FXtra-Computing\u002Fthundersvm) - A fast SVM library on GPUs and CPUs.\n* [LKYDeepNN](https:\u002F\u002Fgithub.com\u002Fmosdeo\u002FLKYDeepNN) - A header-only C++11 Neural Network library. Low dependency, native traditional chinese document.\n* [xLearn](https:\u002F\u002Fgithub.com\u002Faksnzhy\u002Fxlearn) - 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 advertising and recommender systems.\n* [Featuretools](https:\u002F\u002Fgithub.com\u002Ffeaturetools\u002Ffeaturetools) - 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\".\n* [skynet](https:\u002F\u002Fgithub.com\u002FTyill\u002Fskynet) - A library for learning neural networks, has C-interface, net set in JSON. Written in C++ with bindings in Python, C++ and C#.\n* [Feast](https:\u002F\u002Fgithub.com\u002Fgojek\u002Ffeast) - 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.\n* [Hopsworks](https:\u002F\u002Fgithub.com\u002Flogicalclocks\u002Fhopsworks) - 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.\n* [Polyaxon](https:\u002F\u002Fgithub.com\u002Fpolyaxon\u002Fpolyaxon) - A platform for reproducible and scalable machine learning and deep learning.\n* [QuestDB](https:\u002F\u002Fquestdb.io\u002F) - A relational column-oriented database designed for real-time analytics on time series and event data.\n* [Phoenix](https:\u002F\u002Fphoenix.arize.com) - Uncover insights, surface problems, monitor and fine tune your generative LLM, CV and tabular models.\n* [XAD](https:\u002F\u002Fgithub.com\u002Fauto-differentiation\u002FXAD) - Comprehensive backpropagation tool for C++.\n* [Truss](https:\u002F\u002Ftruss.baseten.co) - An open source framework for packaging and serving ML models.\n* [nndeploy](https:\u002F\u002Fgithub.com\u002Fnndeploy\u002Fnndeploy) - An Easy-to-Use and High-Performance AI deployment framework.\n\n\u003Ca name=\"cpp-natural-language-processing\">\u003C\u002Fa>\n#### Natural Language Processing\n\n* [BLLIP Parser](https:\u002F\u002Fgithub.com\u002FBLLIP\u002Fbllip-parser) - BLLIP Natural Language Parser (also known as the Charniak-Johnson parser).\n* [colibri-core](https:\u002F\u002Fgithub.com\u002Fproycon\u002Fcolibri-core) - C++ library, command line tools, and Python binding for extracting and working with basic linguistic constructions such as n-grams and skipgrams in a quick and memory-efficient way.\n* [CRF++](https:\u002F\u002Ftaku910.github.io\u002Fcrfpp\u002F) - Open source implementation of Conditional Random Fields (CRFs) for segmenting\u002Flabeling sequential data & other Natural Language Processing tasks. **[Deprecated]**\n* [CRFsuite](http:\u002F\u002Fwww.chokkan.org\u002Fsoftware\u002Fcrfsuite\u002F) - CRFsuite is an implementation of Conditional Random Fields (CRFs) for labeling sequential data. **[Deprecated]**\n* [frog](https:\u002F\u002Fgithub.com\u002FLanguageMachines\u002Ffrog) - Memory-based NLP suite developed for Dutch: PoS tagger, lemmatiser, dependency parser, NER, shallow parser, morphological analyzer.\n* [libfolia](https:\u002F\u002Fgithub.com\u002FLanguageMachines\u002Flibfolia) - C++ library for the [FoLiA format](https:\u002F\u002Fproycon.github.io\u002Ffolia\u002F)\n* [MeTA](https:\u002F\u002Fgithub.com\u002Fmeta-toolkit\u002Fmeta) - [MeTA : ModErn Text Analysis](https:\u002F\u002Fmeta-toolkit.org\u002F) is a C++ Data Sciences Toolkit that facilitates mining big text data.\n* [MIT Information Extraction Toolkit](https:\u002F\u002Fgithub.com\u002Fmit-nlp\u002FMITIE) - C, C++, and Python tools for named entity recognition and relation extraction\n* [ucto](https:\u002F\u002Fgithub.com\u002FLanguageMachines\u002Fucto) - Unicode-aware regular-expression based tokenizer for various languages. Tool and C++ library. Supports FoLiA format.\n* [SentencePiece](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fsentencepiece) - A C++ library for unsupervised text tokenization and detokenization, widely used in modern NLP models.\n\n\u003Ca name=\"cpp-speech-recognition\">\u003C\u002Fa>\n#### Speech Recognition\n* [Kaldi](https:\u002F\u002Fgithub.com\u002Fkaldi-asr\u002Fkaldi) - Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers.\n* [Vosk](https:\u002F\u002Fgithub.com\u002Falphacep\u002Fvosk-api) - An offline speech recognition toolkit with C++ support, designed for low-resource devices and multiple languages.\n\n\u003Ca name=\"cpp-sequence-analysis\">\u003C\u002Fa>\n#### Sequence Analysis\n* [ToPS](https:\u002F\u002Fgithub.com\u002Fayoshiaki\u002Ftops) - This is an object-oriented framework that facilitates the integration of probabilistic models for sequences over a user defined alphabet. **[Deprecated]**\n\n\u003Ca name=\"cpp-gesture-detection\">\u003C\u002Fa>\n#### Gesture Detection\n* [grt](https:\u002F\u002Fgithub.com\u002Fnickgillian\u002Fgrt) - The Gesture Recognition Toolkit (GRT) is a cross-platform, open-source, C++ machine learning library designed for real-time gesture recognition.\n\n\u003Ca name=\"cpp-reinforcement-learning\">\u003C\u002Fa>\n#### Reinforcement Learning\n* [RLtools](https:\u002F\u002Fgithub.com\u002Frl-tools\u002Frl-tools) - The fastest deep reinforcement learning library for continuous control, implemented header-only in pure, dependency-free C++ (Python bindings available as well).\n\n\u003Ca name=\"common-lisp\">\u003C\u002Fa>\n## Common Lisp\n\n\u003Ca name=\"common-lisp-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* [mgl](https:\u002F\u002Fgithub.com\u002Fmelisgl\u002Fmgl\u002F) - Neural networks (boltzmann machines, feed-forward and recurrent nets), Gaussian Processes.\n* [mgl-gpr](https:\u002F\u002Fgithub.com\u002Fmelisgl\u002Fmgl-gpr\u002F) - Evolutionary algorithms. **[Deprecated]**\n* [cl-libsvm](https:\u002F\u002Fgithub.com\u002Fmelisgl\u002Fcl-libsvm\u002F) - Wrapper for the libsvm support vector machine library. **[Deprecated]**\n* [cl-online-learning](https:\u002F\u002Fgithub.com\u002Fmasatoi\u002Fcl-online-learning) - Online learning algorithms (Perceptron, AROW, SCW, Logistic Regression).\n* [cl-random-forest](https:\u002F\u002Fgithub.com\u002Fmasatoi\u002Fcl-random-forest) - Implementation of Random Forest in Common Lisp.\n\n\u003Ca name=\"clojure\">\u003C\u002Fa>\n## Clojure\n\n\u003Ca name=\"clojure-natural-language-processing\">\u003C\u002Fa>\n#### Natural Language Processing\n\n* [Clojure-openNLP](https:\u002F\u002Fgithub.com\u002Fdakrone\u002Fclojure-opennlp) - Natural Language Processing in Clojure (opennlp).\n* [Infections-clj](https:\u002F\u002Fgithub.com\u002Fr0man\u002Finflections-clj) - Rails-like inflection library for Clojure and ClojureScript.\n\n\u003Ca name=\"clojure-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* [scicloj.ml](https:\u002F\u002Fgithub.com\u002Fscicloj\u002Fscicloj.ml) -  A idiomatic Clojure machine learning library based on tech.ml.dataset with a unique approach for immutable data processing pipelines.\n* [clj-ml](https:\u002F\u002Fgithub.com\u002Fjoshuaeckroth\u002Fclj-ml\u002F) - A machine learning library for Clojure built on top of Weka and friends.\n* [clj-boost](https:\u002F\u002Fgitlab.com\u002Falanmarazzi\u002Fclj-boost) - Wrapper for XGBoost\n* [Touchstone](https:\u002F\u002Fgithub.com\u002Fptaoussanis\u002Ftouchstone) - Clojure A\u002FB testing library.\n* [Clojush](https:\u002F\u002Fgithub.com\u002Flspector\u002FClojush) - The Push programming language and the PushGP genetic programming system implemented in Clojure.\n* [lambda-ml](https:\u002F\u002Fgithub.com\u002Fcloudkj\u002Flambda-ml) - Simple, concise implementations of machine learning techniques and utilities in Clojure.\n* [Infer](https:\u002F\u002Fgithub.com\u002Faria42\u002Finfer) - Inference and machine learning in Clojure. **[Deprecated]**\n* [Encog](https:\u002F\u002Fgithub.com\u002Fjimpil\u002Fenclog) - Clojure wrapper for Encog (v3) (Machine-Learning framework that specializes in neural-nets). **[Deprecated]**\n* [Fungp](https:\u002F\u002Fgithub.com\u002Fvollmerm\u002Ffungp) - A genetic programming library for Clojure. **[Deprecated]**\n* [Statistiker](https:\u002F\u002Fgithub.com\u002Fclojurewerkz\u002Fstatistiker) - Basic Machine Learning algorithms in Clojure. **[Deprecated]**\n* [clortex](https:\u002F\u002Fgithub.com\u002Fhtm-community\u002Fclortex) - General Machine Learning library using Numenta’s Cortical Learning Algorithm. **[Deprecated]**\n* [comportex](https:\u002F\u002Fgithub.com\u002Fhtm-community\u002Fcomportex) - Functionally composable Machine Learning library using Numenta’s Cortical Learning Algorithm. **[Deprecated]**\n\n\u003Ca name=\"clojure-deep-learning\">\u003C\u002Fa>\n#### Deep Learning\n* [MXNet](https:\u002F\u002Fmxnet.apache.org\u002Fversions\u002F1.7.0\u002Fapi\u002Fclojure) - Bindings to Apache MXNet - part of the MXNet project\n* [Deep Diamond](https:\u002F\u002Fgithub.com\u002Funcomplicate\u002Fdeep-diamond) - A fast Clojure Tensor & Deep Learning library\n* [jutsu.ai](https:\u002F\u002Fgithub.com\u002Fhswick\u002Fjutsu.ai) - Clojure wrapper for deeplearning4j with some added syntactic sugar.\n* [cortex](https:\u002F\u002Fgithub.com\u002Foriginrose\u002Fcortex) - Neural networks, regression and feature learning in Clojure.\n* [Flare](https:\u002F\u002Fgithub.com\u002Faria42\u002Fflare) - Dynamic Tensor Graph library in Clojure (think PyTorch, DynNet, etc.)\n* [dl4clj](https:\u002F\u002Fgithub.com\u002Fyetanalytics\u002Fdl4clj) - Clojure wrapper for Deeplearning4j.\n\n\u003Ca name=\"clojure-data-analysis--data-visualization\">\u003C\u002Fa>\n#### Data Analysis\n* [tech.ml.dataset](https:\u002F\u002Fgithub.com\u002Ftechascent\u002Ftech.ml.dataset) - Clojure dataframe library and pipeline for data processing and machine learning\n* [Tablecloth](https:\u002F\u002Fgithub.com\u002Fscicloj\u002Ftablecloth) - A dataframe grammar wrapping tech.ml.dataset, inspired by several R libraries\n* [Panthera](https:\u002F\u002Fgithub.com\u002Falanmarazzi\u002Fpanthera) - Clojure API wrapping Python's Pandas library\n* [Incanter](http:\u002F\u002Fincanter.org\u002F) - Incanter is a Clojure-based, R-like platform for statistical computing and graphics.\n* [PigPen](https:\u002F\u002Fgithub.com\u002FNetflix\u002FPigPen) - Map-Reduce for Clojure.\n* [Geni](https:\u002F\u002Fgithub.com\u002Fzero-one-group\u002Fgeni) - a Clojure dataframe library that runs on Apache Spark\n\n\u003Ca name=\"clojure-data-visualization\">\u003C\u002Fa>\n#### Data Visualization\n* [Hanami](https:\u002F\u002Fgithub.com\u002Fjsa-aerial\u002Fhanami) - Clojure(Script) library and framework for creating interactive visualization applications based in Vega-Lite (VGL) and\u002For Vega (VG) specifications. Automatic framing and layouts along with a powerful templating system for abstracting visualization specs\n* [Saite](https:\u002F\u002Fgithub.com\u002Fjsa-aerial\u002Fsaite) -  Clojure(Script) client\u002Fserver application for dynamic interactive explorations and the creation of live shareable documents capturing them using Vega\u002FVega-Lite, CodeMirror, markdown, and LaTeX\n* [Oz](https:\u002F\u002Fgithub.com\u002Fmetasoarous\u002Foz) - Data visualisation using Vega\u002FVega-Lite and Hiccup, and a live-reload platform for literate-programming\n* [Envision](https:\u002F\u002Fgithub.com\u002Fclojurewerkz\u002Fenvision) - Clojure Data Visualisation library, based on Statistiker and D3.\n* [Pink Gorilla Notebook](https:\u002F\u002Fgithub.com\u002Fpink-gorilla\u002Fgorilla-notebook) - A Clojure\u002FClojurescript notebook application\u002F-library based on Gorilla-REPL\n* [clojupyter](https:\u002F\u002Fgithub.com\u002Fclojupyter\u002Fclojupyter) -  A Jupyter kernel for Clojure - run Clojure code in Jupyter Lab, Notebook and Console.\n* [notespace](https:\u002F\u002Fgithub.com\u002Fscicloj\u002Fnotespace) - Notebook experience in your Clojure namespace\n* [Delight](https:\u002F\u002Fgithub.com\u002Fdatamechanics\u002Fdelight) - A listener that streams your spark events logs to delight, a free and improved spark UI\n\n\u003Ca name=\"clojure-interop\">\u003C\u002Fa>\n#### Interop\n\n* [Java Interop](https:\u002F\u002Fclojure.org\u002Freference\u002Fjava_interop) - Clojure has Native Java Interop from which Java's ML ecosystem can be accessed\n* [JavaScript Interop](https:\u002F\u002Fclojurescript.org\u002Freference\u002Fjavascript-api) - ClojureScript has Native JavaScript Interop from which JavaScript's ML ecosystem can be accessed\n* [Libpython-clj](https:\u002F\u002Fgithub.com\u002Fclj-python\u002Flibpython-clj) - Interop with Python\n* [ClojisR](https:\u002F\u002Fgithub.com\u002Fscicloj\u002Fclojisr) - Interop with R and Renjin (R on the JVM)\n\n\u003Ca name=\"clojure-misc\">\u003C\u002Fa>\n#### Misc\n* [Neanderthal](https:\u002F\u002Fneanderthal.uncomplicate.org\u002F) - Fast Clojure Matrix Library (native CPU, GPU, OpenCL, CUDA)\n* [kixistats](https:\u002F\u002Fgithub.com\u002FMastodonC\u002Fkixi.stats) - A library of statistical distribution sampling and transducing functions\n* [fastmath](https:\u002F\u002Fgithub.com\u002Fgenerateme\u002Ffastmath) - A collection of functions for mathematical and statistical computing, macine learning, etc., wrapping several JVM libraries\n* [matlib](https:\u002F\u002Fgithub.com\u002Fatisharma\u002Fmatlib) - A Clojure library of optimisation and control theory tools and convenience functions based on Neanderthal.\n\n\u003Ca name=\"clojure-extra\">\u003C\u002Fa>\n#### Extra\n* [Scicloj](https:\u002F\u002Fscicloj.github.io\u002Fpages\u002Flibraries\u002F) - Curated list of ML related resources for Clojure.\n\n\u003Ca name=\"crystal\">\u003C\u002Fa>\n## Crystal\n\n\u003Ca name=\"crystal-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* [machine](https:\u002F\u002Fgithub.com\u002Fmathieulaporte\u002Fmachine) - Simple machine learning algorithm.\n* [crystal-fann](https:\u002F\u002Fgithub.com\u002FNeuraLegion\u002Fcrystal-fann) - FANN (Fast Artificial Neural Network) binding.\n\n\u003Ca name=\"cuda-ptx\">\u003C\u002Fa>\n## CUDA PTX\n\n\u003Ca name=\"cuda-ptx-neurosymbolic-ai\">\u003C\u002Fa>\n#### Neurosymbolic AI\n\n* [Knowledge3D (K3D)](https:\u002F\u002Fgithub.com\u002Fdanielcamposramos\u002FKnowledge3D) - Sovereign GPU-native spatial AI architecture with PTX-first cognitive engine (RPN\u002FTRM reasoning), tri-modal fusion (text\u002Fvisual\u002Faudio), 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.\n\n\u003Ca name=\"elixir\">\u003C\u002Fa>\n## Elixir\n\n\u003Ca name=\"elixir-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* [Simple Bayes](https:\u002F\u002Fgithub.com\u002Ffredwu\u002Fsimple_bayes) - A Simple Bayes \u002F Naive Bayes implementation in Elixir.\n* [emel](https:\u002F\u002Fgithub.com\u002Fmrdimosthenis\u002Femel) - A simple and functional machine learning library written in Elixir.\n* [Tensorflex](https:\u002F\u002Fgithub.com\u002Fanshuman23\u002Ftensorflex) - Tensorflow bindings for the Elixir programming language.\n\n\u003Ca name=\"elixir-natural-language-processing\">\u003C\u002Fa>\n#### Natural Language Processing\n\n* [Stemmer](https:\u002F\u002Fgithub.com\u002Ffredwu\u002Fstemmer) - An English (Porter2) stemming implementation in Elixir.\n\n\u003Ca name=\"erlang\">\u003C\u002Fa>\n## Erlang\n\n\u003Ca name=\"erlang-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* [Disco](https:\u002F\u002Fgithub.com\u002Fdiscoproject\u002Fdisco\u002F) - Map Reduce in Erlang. **[Deprecated]**\n\n\u003Ca name=\"fortran\">\u003C\u002Fa>\n## Fortran\n\n\u003Ca name=\"fortran-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* [neural-fortran](https:\u002F\u002Fgithub.com\u002Fmodern-fortran\u002Fneural-fortran) - A parallel neural net microframework.\nRead the paper [here](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.06714).\n\n\u003Ca name=\"fortran-data-analysis--data-visualization\">\u003C\u002Fa>\n#### Data Analysis \u002F Data Visualization\n\n* [ParaMonte](https:\u002F\u002Fgithub.com\u002Fcdslaborg\u002Fparamonte) - A general-purpose Fortran library for Bayesian data analysis and visualization via serial\u002Fparallel Monte Carlo and MCMC simulations. Documentation can be found [here](https:\u002F\u002Fwww.cdslab.org\u002Fparamonte\u002F).\n\n\u003Ca name=\"go\">\u003C\u002Fa>\n## Go\n\n\u003Ca name=\"go-natural-language-processing\">\u003C\u002Fa>\n#### Natural Language Processing\n\n* [Cybertron](https:\u002F\u002Fgithub.com\u002Fnlpodyssey\u002Fcybertron) - Cybertron: the home planet of the Transformers in Go.\n* [snowball](https:\u002F\u002Fgithub.com\u002Ftebeka\u002Fsnowball) - Snowball Stemmer for Go.\n* [word-embedding](https:\u002F\u002Fgithub.com\u002Fynqa\u002Fword-embedding) - Word Embeddings: the full implementation of word2vec, GloVe in Go.\n* [sentences](https:\u002F\u002Fgithub.com\u002Fneurosnap\u002Fsentences) - Golang implementation of Punkt sentence tokenizer.\n* [go-ngram](https:\u002F\u002Fgithub.com\u002FLazin\u002Fgo-ngram) - In-memory n-gram index with compression. *[Deprecated]*\n* [paicehusk](https:\u002F\u002Fgithub.com\u002FRookii\u002Fpaicehusk) - Golang implementation of the Paice\u002FHusk Stemming Algorithm. *[Deprecated]*\n* [go-porterstemmer](https:\u002F\u002Fgithub.com\u002Freiver\u002Fgo-porterstemmer) - A native Go clean room implementation of the Porter Stemming algorithm. **[Deprecated]**\n\n\u003Ca name=\"go-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* [Spago](https:\u002F\u002Fgithub.com\u002Fnlpodyssey\u002Fspago) - Self-contained Machine Learning and Natural Language Processing library in Go.\n* [birdland](https:\u002F\u002Fgithub.com\u002Frlouf\u002Fbirdland) - A recommendation library in Go.\n* [eaopt](https:\u002F\u002Fgithub.com\u002FMaxHalford\u002Feaopt) - An evolutionary optimization library.\n* [leaves](https:\u002F\u002Fgithub.com\u002Fdmitryikh\u002Fleaves) - A pure Go implementation of the prediction part of GBRTs, including XGBoost and LightGBM.\n* [gobrain](https:\u002F\u002Fgithub.com\u002Fgoml\u002Fgobrain) - Neural Networks written in Go.\n* [go-featureprocessing](https:\u002F\u002Fgithub.com\u002Fnikolaydubina\u002Fgo-featureprocessing) - Fast and convenient feature processing for low latency machine learning in Go.\n* [go-mxnet-predictor](https:\u002F\u002Fgithub.com\u002Fsongtianyi\u002Fgo-mxnet-predictor) - Go binding for MXNet c_predict_api to do inference with a pre-trained model.\n* [go-ml-benchmarks](https:\u002F\u002Fgithub.com\u002Fnikolaydubina\u002Fgo-ml-benchmarks) — benchmarks of machine learning inference for Go.\n* [go-ml-transpiler](https:\u002F\u002Fgithub.com\u002Fznly\u002Fgo-ml-transpiler) - An open source Go transpiler for machine learning models.\n* [golearn](https:\u002F\u002Fgithub.com\u002Fsjwhitworth\u002Fgolearn) - Machine learning for Go.\n* [goml](https:\u002F\u002Fgithub.com\u002Fcdipaolo\u002Fgoml) - Machine learning library written in pure Go.\n* [gorgonia](https:\u002F\u002Fgithub.com\u002Fgorgonia\u002Fgorgonia) - Deep learning in Go.\n* [goro](https:\u002F\u002Fgithub.com\u002Faunum\u002Fgoro) - A high-level machine learning library in the vein of Keras.\n* [gorse](https:\u002F\u002Fgithub.com\u002Fzhenghaoz\u002Fgorse) - An offline recommender system backend based on collaborative filtering written in Go.\n* [therfoo](https:\u002F\u002Fgithub.com\u002Ftherfoo\u002Ftherfoo) - An embedded deep learning library for Go.\n* [neat](https:\u002F\u002Fgithub.com\u002Fjinyeom\u002Fneat) - Plug-and-play, parallel Go framework for NeuroEvolution of Augmenting Topologies (NEAT). **[Deprecated]**\n* [go-pr](https:\u002F\u002Fgithub.com\u002Fdaviddengcn\u002Fgo-pr) - Pattern recognition package in Go lang. **[Deprecated]**\n* [go-ml](https:\u002F\u002Fgithub.com\u002Falonsovidales\u002Fgo_ml) - Linear \u002F Logistic regression, Neural Networks, Collaborative Filtering and Gaussian Multivariate Distribution. **[Deprecated]**\n* [GoNN](https:\u002F\u002Fgithub.com\u002Ffxsjy\u002Fgonn) - GoNN is an implementation of Neural Network in Go Language, which includes BPNN, RBF, PCN. **[Deprecated]**\n* [bayesian](https:\u002F\u002Fgithub.com\u002Fjbrukh\u002Fbayesian) - Naive Bayesian Classification for Golang. **[Deprecated]**\n* [go-galib](https:\u002F\u002Fgithub.com\u002Fthoj\u002Fgo-galib) - Genetic Algorithms library written in Go \u002F Golang. **[Deprecated]**\n* [Cloudforest](https:\u002F\u002Fgithub.com\u002Fryanbressler\u002FCloudForest) - Ensembles of decision trees in Go\u002FGolang. **[Deprecated]**\n* [go-dnn](https:\u002F\u002Fgithub.com\u002Fsudachen\u002Fgo-dnn) - Deep Neural Networks for Golang (powered by MXNet)\n\n\u003Ca name=\"go-spatial-analysis-and-geometry\">\u003C\u002Fa>\n#### Spatial analysis and geometry\n\n* [go-geom](https:\u002F\u002Fgithub.com\u002Ftwpayne\u002Fgo-geom) - Go library to handle geometries.\n* [gogeo](https:\u002F\u002Fgithub.com\u002Fgolang\u002Fgeo) - Spherical geometry in Go.\n\n\u003Ca name=\"go-data-analysis--data-visualization\">\u003C\u002Fa>\n#### Data Analysis \u002F Data Visualization\n\n* [dataframe-go](https:\u002F\u002Fgithub.com\u002Frocketlaunchr\u002Fdataframe-go) - Dataframes for machine-learning and statistics (similar to pandas).\n* [gota](https:\u002F\u002Fgithub.com\u002Fgo-gota\u002Fgota) - Dataframes.\n* [gonum\u002Fmat](https:\u002F\u002Fgodoc.org\u002Fgonum.org\u002Fv1\u002Fgonum\u002Fmat) - A linear algebra package for Go.\n* [gonum\u002Foptimize](https:\u002F\u002Fgodoc.org\u002Fgonum.org\u002Fv1\u002Fgonum\u002Foptimize) - Implementations of optimization algorithms.\n* [gonum\u002Fplot](https:\u002F\u002Fgodoc.org\u002Fgonum.org\u002Fv1\u002Fplot) - A plotting library.\n* [gonum\u002Fstat](https:\u002F\u002Fgodoc.org\u002Fgonum.org\u002Fv1\u002Fgonum\u002Fstat) - A statistics library.\n* [SVGo](https:\u002F\u002Fgithub.com\u002Fajstarks\u002Fsvgo) - The Go Language library for SVG generation.\n* [glot](https:\u002F\u002Fgithub.com\u002Farafatk\u002Fglot) - Glot is a plotting library for Golang built on top of gnuplot.\n* [globe](https:\u002F\u002Fgithub.com\u002Fmmcloughlin\u002Fglobe) - Globe wireframe visualization.\n* [gonum\u002Fgraph](https:\u002F\u002Fgodoc.org\u002Fgonum.org\u002Fv1\u002Fgonum\u002Fgraph) - General-purpose graph library.\n* [go-graph](https:\u002F\u002Fgithub.com\u002FStepLg\u002Fgo-graph) - Graph library for Go\u002FGolang language. **[Deprecated]**\n* [RF](https:\u002F\u002Fgithub.com\u002Ffxsjy\u002FRF.go) - Random forests implementation in Go. **[Deprecated]**\n\n\u003Ca name=\"go-computer-vision\">\u003C\u002Fa>\n#### Computer vision\n\n* [GoCV](https:\u002F\u002Fgithub.com\u002Fhybridgroup\u002Fgocv) - Package for computer vision using OpenCV 4 and beyond.\n\n\u003Ca name=\"go-reinforcement-learning\">\u003C\u002Fa>\n#### Reinforcement learning\n\n* [gold](https:\u002F\u002Fgithub.com\u002Faunum\u002Fgold) - A reinforcement learning library.\n* [stable-baselines3](https:\u002F\u002Fgithub.com\u002FDLR-RM\u002Fstable-baselines3) - PyTorch implementations of Stable Baselines (deep) reinforcement learning algorithms.\n\n\u003Ca name=\"haskell\">\u003C\u002Fa>\n## Haskell\n\n\u003Ca name=\"haskell-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n* [haskell-ml](https:\u002F\u002Fgithub.com\u002Fajtulloch\u002Fhaskell-ml) - Haskell implementations of various ML algorithms. **[Deprecated]**\n* [HLearn](https:\u002F\u002Fgithub.com\u002Fmikeizbicki\u002FHLearn) - a suite of libraries for interpreting machine learning models according to their algebraic structure. **[Deprecated]**\n* [hnn](https:\u002F\u002Fgithub.com\u002Falpmestan\u002FHNN) - Haskell Neural Network library.\n* [hopfield-networks](https:\u002F\u002Fgithub.com\u002Fajtulloch\u002Fhopfield-networks) - Hopfield Networks for unsupervised learning in Haskell. **[Deprecated]**\n* [DNNGraph](https:\u002F\u002Fgithub.com\u002Fajtulloch\u002Fdnngraph) - A DSL for deep neural networks. **[Deprecated]**\n* [LambdaNet](https:\u002F\u002Fgithub.com\u002Fjbarrow\u002FLambdaNet) - Configurable Neural Networks in Haskell. **[Deprecated]**\n\n\u003Ca name=\"java\">\u003C\u002Fa>\n## Java\n\n\u003Ca name=\"java-natural-language-processing\">\u003C\u002Fa>\n#### Natural Language Processing\n* [Cortical.io](https:\u002F\u002Fwww.cortical.io\u002F) - Retina: an API performing complex NLP operations (disambiguation, classification, streaming text filtering, etc...) as quickly and intuitively as the brain.\n* [IRIS](https:\u002F\u002Fgithub.com\u002Fcortical-io\u002FIris) - [Cortical.io's](https:\u002F\u002Fcortical.io) FREE NLP, Retina API Analysis Tool (written in JavaFX!) - [See the Tutorial Video](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=CsF4pd7fGF0).\n* [CoreNLP](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Fcorenlp.shtml) - Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words.\n* [Stanford Parser](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Flex-parser.shtml) - A natural language parser is a program that works out the grammatical structure of sentences.\n* [Stanford POS Tagger](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Ftagger.shtml) - A Part-Of-Speech Tagger (POS Tagger).\n* [Stanford Name Entity Recognizer](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002FCRF-NER.shtml) - Stanford NER is a Java implementation of a Named Entity Recognizer.\n* [Stanford Word Segmenter](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Fsegmenter.shtml) - Tokenization of raw text is a standard pre-processing step for many NLP tasks.\n* [Tregex, Tsurgeon and Semgrex](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Ftregex.shtml) - Tregex is a utility for matching patterns in trees, based on tree relationships and regular expression matches on nodes (the name is short for \"tree regular expressions\").\n* [Stanford Phrasal: A Phrase-Based Translation System](https:\u002F\u002Fnlp.stanford.edu\u002Fphrasal\u002F)\n* [Stanford English Tokenizer](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Ftokenizer.shtml) - Stanford Phrasal is a state-of-the-art statistical phrase-based machine translation system, written in Java.\n* [Stanford Tokens Regex](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Ftokensregex.shtml) - A tokenizer divides text into a sequence of tokens, which roughly correspond to \"words\".\n* [Stanford Temporal Tagger](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Fsutime.shtml) - SUTime is a library for recognizing and normalizing time expressions.\n* [Stanford SPIED](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Fpatternslearning.shtml) - Learning entities from unlabeled text starting with seed sets using patterns in an iterative fashion.\n* [Twitter Text Java](https:\u002F\u002Fgithub.com\u002Ftwitter\u002Ftwitter-text\u002Ftree\u002Fmaster\u002Fjava) - A Java implementation of Twitter's text processing library.\n* [MALLET](http:\u002F\u002Fmallet.cs.umass.edu\u002F) - A Java-based package for statistical natural language processing, document classification, clustering, topic modelling, information extraction, and other machine learning applications to text.\n* [OpenNLP](https:\u002F\u002Fopennlp.apache.org\u002F) - A machine learning based toolkit for the processing of natural language text.\n* [LingPipe](http:\u002F\u002Falias-i.com\u002Flingpipe\u002Findex.html) - A tool kit for processing text using computational linguistics.\n* [ClearTK](https:\u002F\u002Fgithub.com\u002FClearTK\u002Fcleartk) - ClearTK provides a framework for developing statistical natural language processing (NLP) components in Java and is built on top of Apache UIMA. **[Deprecated]**\n* [Apache cTAKES](https:\u002F\u002Fctakes.apache.org\u002F) - Apache Clinical Text Analysis and Knowledge Extraction System (cTAKES) is an open-source natural language processing system for information extraction from electronic medical record clinical free-text.\n* [NLP4J](https:\u002F\u002Fgithub.com\u002Femorynlp\u002Fnlp4j) - 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]**\n* [CogcompNLP](https:\u002F\u002Fgithub.com\u002FCogComp\u002Fcogcomp-nlp) - 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.\n\n\u003Ca name=\"java-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* [aerosolve](https:\u002F\u002Fgithub.com\u002Fairbnb\u002Faerosolve) - A machine learning library by Airbnb designed from the ground up to be human friendly.\n* [AMIDST Toolbox](http:\u002F\u002Fwww.amidsttoolbox.com\u002F) - A Java Toolbox for Scalable Probabilistic Machine Learning.\n* [Chips-n-Salsa](https:\u002F\u002Fgithub.com\u002Fcicirello\u002FChips-n-Salsa) - A Java library for genetic algorithms, evolutionary computation, and stochastic local search, with a focus on self-adaptation \u002F self-tuning, as well as parallel execution.\n* [Datumbox](https:\u002F\u002Fgithub.com\u002Fdatumbox\u002Fdatumbox-framework) - Machine Learning framework for rapid development of Machine Learning and Statistical applications.\n* [ELKI](https:\u002F\u002Felki-project.github.io\u002F) - Java toolkit for data mining. (unsupervised: clustering, outlier detection etc.)\n* [Encog](https:\u002F\u002Fgithub.com\u002Fencog\u002Fencog-java-core) - 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.\n* [FlinkML in Apache Flink](https:\u002F\u002Fci.apache.org\u002Fprojects\u002Fflink\u002Fflink-docs-master\u002Fdev\u002Flibs\u002Fml\u002Findex.html) - Distributed machine learning library in Flink.\n* [H2O](https:\u002F\u002Fgithub.com\u002Fh2oai\u002Fh2o-3) - ML engine that supports distributed learning on Hadoop, Spark or your laptop via APIs in R, Python, Scala, REST\u002FJSON.\n* [htm.java](https:\u002F\u002Fgithub.com\u002Fnumenta\u002Fhtm.java) - General Machine Learning library using Numenta’s Cortical Learning Algorithm.\n* [jSciPy](https:\u002F\u002Fgithub.com\u002Fhissain\u002Fjscipy) - A Java port of SciPy's signal processing module, offering filters, transformations, and other scientific computing utilities.\n* [liblinear-java](https:\u002F\u002Fgithub.com\u002Fbwaldvogel\u002Fliblinear-java) - Java version of liblinear.\n* [Mahout](https:\u002F\u002Fgithub.com\u002Fapache\u002Fmahout) - Distributed machine learning.\n* [Meka](http:\u002F\u002Fmeka.sourceforge.net\u002F) - An open source implementation of methods for multi-label classification and evaluation (extension to Weka).\n* [MLlib in Apache Spark](https:\u002F\u002Fspark.apache.org\u002Fdocs\u002Flatest\u002Fmllib-guide.html) - Distributed machine learning library in Spark.\n* [Hydrosphere Mist](https:\u002F\u002Fgithub.com\u002FHydrospheredata\u002Fmist) - a service for deployment Apache Spark MLLib machine learning models as realtime, batch or reactive web services.\n* [Neuroph](http:\u002F\u002Fneuroph.sourceforge.net\u002F) - Neuroph is lightweight Java neural network framework.\n* [ORYX](https:\u002F\u002Fgithub.com\u002Foryxproject\u002Foryx) - Lambda Architecture Framework using Apache Spark and Apache Kafka with a specialization for real-time large-scale machine learning.\n* [Samoa](https:\u002F\u002Fsamoa.incubator.apache.org\u002F) SAMOA is a framework that includes distributed machine learning for data streams with an interface to plug-in different stream processing platforms.\n* [RankLib](https:\u002F\u002Fsourceforge.net\u002Fp\u002Flemur\u002Fwiki\u002FRankLib\u002F) - RankLib is a library of learning to rank algorithms. **[Deprecated]**\n* [rapaio](https:\u002F\u002Fgithub.com\u002Fpadreati\u002Frapaio) - statistics, data mining and machine learning toolbox in Java.\n* [RapidMiner](https:\u002F\u002Frapidminer.com) - RapidMiner integration into Java code.\n* [Stanford Classifier](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Fclassifier.shtml) - A classifier is a machine learning tool that will take data items and place them into one of k classes.\n* [Smile](https:\u002F\u002Fhaifengl.github.io\u002F) - Statistical Machine Intelligence & Learning Engine.\n* [SystemML](https:\u002F\u002Fgithub.com\u002Fapache\u002Fsystemml) - flexible, scalable machine learning (ML) language.\n* [Tribou](https:\u002F\u002Ftribuo.org) - A machine learning library written in Java by Oracle.\n* [Weka](https:\u002F\u002Fwww.cs.waikato.ac.nz\u002Fml\u002Fweka\u002F) - Weka is a collection of machine learning algorithms for data mining tasks.\n* [LBJava](https:\u002F\u002Fgithub.com\u002FCogComp\u002Flbjava) - Learning Based Java is a modelling language for the rapid development of software systems, offers a convenient, declarative syntax for classifier and constraint definition directly in terms of the objects in the programmer's application.\n* [knn-java-library](https:\u002F\u002Fgithub.com\u002Ffelipexw\u002Fknn-java-library) - Just a simple implementation of K-Nearest Neighbors algorithm using with a bunch of similarity measures.\n\n\u003Ca name=\"java-speech-recognition\">\u003C\u002Fa>\n#### Speech Recognition\n* [CMU Sphinx](https:\u002F\u002Fcmusphinx.github.io) - Open Source Toolkit For Speech Recognition purely based on Java speech recognition library.\n\n\u003Ca name=\"java-data-analysis--data-visualization\">\u003C\u002Fa>\n#### Data Analysis \u002F Data Visualization\n\n* [Flink](https:\u002F\u002Fflink.apache.org\u002F) - Open source platform for distributed stream and batch data processing.\n* [Hadoop](https:\u002F\u002Fgithub.com\u002Fapache\u002Fhadoop) - Hadoop\u002FHDFS.\n* [Onyx](https:\u002F\u002Fgithub.com\u002Fonyx-platform\u002Fonyx) - Distributed, masterless, high performance, fault tolerant data processing. Written entirely in Clojure.\n* [Spark](https:\u002F\u002Fgithub.com\u002Fapache\u002Fspark) - Spark is a fast and general engine for large-scale data processing.\n* [Storm](https:\u002F\u002Fstorm.apache.org\u002F) - Storm is a distributed realtime computation system.\n* [Impala](https:\u002F\u002Fgithub.com\u002Fcloudera\u002Fimpala) - Real-time Query for Hadoop.\n* [DataMelt](https:\u002F\u002Fjwork.org\u002Fdmelt\u002F) - Mathematics software for numeric computation, statistics, symbolic calculations, data analysis and data visualization.\n* [Dr. Michael Thomas Flanagan's Java Scientific Library.](https:\u002F\u002Fwww.ee.ucl.ac.uk\u002F~mflanaga\u002Fjava\u002F) **[Deprecated]**\n\n\u003Ca name=\"java-deep-learning\">\u003C\u002Fa>\n#### Deep Learning\n\n* [Deeplearning4j](https:\u002F\u002Fgithub.com\u002Fdeeplearning4j\u002Fdeeplearning4j) - Scalable deep learning for industry with parallel GPUs.\n* [Keras Beginner Tutorial](https:\u002F\u002Fvictorzhou.com\u002Fblog\u002Fkeras-neural-network-tutorial\u002F) - Friendly guide on using Keras to implement a simple Neural Network in Python.\n* [deepjavalibrary\u002Fdjl](https:\u002F\u002Fgithub.com\u002Fdeepjavalibrary\u002Fdjl) - Deep Java Library (DJL) is an open-source, high-level, engine-agnostic Java framework for deep learning, designed to be easy to get started with and simple to use for Java developers.\n\n\u003Ca name=\"javascript\">\u003C\u002Fa>\n## JavaScript\n\n\u003Ca name=\"javascript-natural-language-processing\">\u003C\u002Fa>\n#### Natural Language Processing\n\n* [Twitter-text](https:\u002F\u002Fgithub.com\u002Ftwitter\u002Ftwitter-text) - A JavaScript implementation of Twitter's text processing library.\n* [natural](https:\u002F\u002Fgithub.com\u002FNaturalNode\u002Fnatural) - General natural language facilities for node.\n* [Knwl.js](https:\u002F\u002Fgithub.com\u002Floadfive\u002FKnwl.js) - A Natural Language Processor in JS.\n* [Retext](https:\u002F\u002Fgithub.com\u002Fretextjs\u002Fretext) - Extensible system for analyzing and manipulating natural language.\n* [NLP Compromise](https:\u002F\u002Fgithub.com\u002Fspencermountain\u002Fcompromise) - Natural Language processing in the browser.\n* [nlp.js](https:\u002F\u002Fgithub.com\u002Faxa-group\u002Fnlp.js) - An NLP library built in node over Natural, with entity extraction, sentiment analysis, automatic language identify, and so more.\n\n\n\n\u003Ca name=\"javascript-data-analysis--data-visualization\">\u003C\u002Fa>\n#### Data Analysis \u002F Data Visualization\n\n* [D3.js](https:\u002F\u002Fd3js.org\u002F)\n* [High Charts](https:\u002F\u002Fwww.highcharts.com\u002F)\n* [NVD3.js](http:\u002F\u002Fnvd3.org\u002F)\n* [dc.js](https:\u002F\u002Fdc-js.github.io\u002Fdc.js\u002F)\n* [chartjs](https:\u002F\u002Fwww.chartjs.org\u002F)\n* [dimple](http:\u002F\u002Fdimplejs.org\u002F)\n* [amCharts](https:\u002F\u002Fwww.amcharts.com\u002F)\n* [D3xter](https:\u002F\u002Fgithub.com\u002FNathanEpstein\u002FD3xter) - Straight forward plotting built on D3. **[Deprecated]**\n* [statkit](https:\u002F\u002Fgithub.com\u002Frigtorp\u002Fstatkit) - Statistics kit for JavaScript. **[Deprecated]**\n* [datakit](https:\u002F\u002Fgithub.com\u002Fnathanepstein\u002Fdatakit) - A lightweight framework for data analysis in JavaScript\n* [science.js](https:\u002F\u002Fgithub.com\u002Fjasondavies\u002Fscience.js\u002F) - Scientific and statistical computing in JavaScript. **[Deprecated]**\n* [Z3d](https:\u002F\u002Fgithub.com\u002FNathanEpstein\u002FZ3d) - Easily make interactive 3d plots built on Three.js **[Deprecated]**\n* [Sigma.js](http:\u002F\u002Fsigmajs.org\u002F) - JavaScript library dedicated to graph drawing.\n* [C3.js](https:\u002F\u002Fc3js.org\u002F) - customizable library based on D3.js for easy chart drawing.\n* [Datamaps](https:\u002F\u002Fdatamaps.github.io\u002F) - Customizable SVG map\u002Fgeo visualizations using D3.js. **[Deprecated]**\n* [ZingChart](https:\u002F\u002Fwww.zingchart.com\u002F) - library written on Vanilla JS for big data visualization.\n* [cheminfo](https:\u002F\u002Fwww.cheminfo.org\u002F) - Platform for data visualization and analysis, using the [visualizer](https:\u002F\u002Fgithub.com\u002Fnpellet\u002Fvisualizer) project.\n* [Learn JS Data](http:\u002F\u002Flearnjsdata.com\u002F)\n* [AnyChart](https:\u002F\u002Fwww.anychart.com\u002F)\n* [FusionCharts](https:\u002F\u002Fwww.fusioncharts.com\u002F)\n* [Nivo](https:\u002F\u002Fnivo.rocks) - built on top of the awesome d3 and Reactjs libraries\n\n\n\u003Ca name=\"javascript-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* [Auto ML](https:\u002F\u002Fgithub.com\u002FClimbsRocks\u002Fauto_ml) - Automated machine learning, data formatting, ensembling, and hyperparameter optimization for competitions and exploration- just give it a .csv file! **[Deprecated]**\n* [Catniff](https:\u002F\u002Fgithub.com\u002Fnguyenphuminh\u002Fcatniff) - Torch-like deep learning framework for Javascript with support for tensors, autograd, optimizers, and other neural net constructs.\n* [Convnet.js](https:\u002F\u002Fcs.stanford.edu\u002Fpeople\u002Fkarpathy\u002Fconvnetjs\u002F) - ConvNetJS is a JavaScript library for training Deep Learning models[DEEP LEARNING] **[Deprecated]**\n* [Creatify MCP](https:\u002F\u002Fgithub.com\u002FTSavo\u002Fcreatify-mcp) - Model Context Protocol server that exposes Creatify AI's video generation capabilities to AI assistants, enabling natural language video creation workflows.\n* [Clusterfck](https:\u002F\u002Fharthur.github.io\u002Fclusterfck\u002F) - Agglomerative hierarchical clustering implemented in JavaScript for Node.js and the browser. **[Deprecated]**\n* [Clustering.js](https:\u002F\u002Fgithub.com\u002Femilbayes\u002Fclustering.js) - Clustering algorithms implemented in JavaScript for Node.js and the browser. **[Deprecated]**\n* [Decision Trees](https:\u002F\u002Fgithub.com\u002Fserendipious\u002Fnodejs-decision-tree-id3) - NodeJS Implementation of Decision Tree using ID3 Algorithm. **[Deprecated]**\n* [DN2A](https:\u002F\u002Fgithub.com\u002Fantoniodeluca\u002Fdn2a.js) - Digital Neural Networks Architecture. **[Deprecated]**\n* [figue](https:\u002F\u002Fcode.google.com\u002Farchive\u002Fp\u002Ffigue) - K-means, fuzzy c-means and agglomerative clustering.\n* [Gaussian Mixture Model](https:\u002F\u002Fgithub.com\u002Flukapopijac\u002Fgaussian-mixture-model) - Unsupervised machine learning with multivariate Gaussian mixture model.\n* [Node-fann](https:\u002F\u002Fgithub.com\u002Frlidwka\u002Fnode-fann) - FANN (Fast Artificial Neural Network Library) bindings for Node.js **[Deprecated]**\n* [Keras.js](https:\u002F\u002Fgithub.com\u002Ftranscranial\u002Fkeras-js) - Run Keras models in the browser, with GPU support provided by WebGL 2.\n* [Kmeans.js](https:\u002F\u002Fgithub.com\u002Femilbayes\u002FkMeans.js) - Simple JavaScript implementation of the k-means algorithm, for node.js and the browser. **[Deprecated]**\n* [LDA.js](https:\u002F\u002Fgithub.com\u002Fprimaryobjects\u002Flda) - LDA topic modelling for Node.js\n* [Learning.js](https:\u002F\u002Fgithub.com\u002Fyandongliu\u002Flearningjs) - JavaScript implementation of logistic regression\u002Fc4.5 decision tree **[Deprecated]**\n* [machinelearn.js](https:\u002F\u002Fgithub.com\u002Fmachinelearnjs\u002Fmachinelearnjs) - Machine Learning library for the web, Node.js and developers\n* [mil-tokyo](https:\u002F\u002Fgithub.com\u002Fmil-tokyo) - List of several machine learning libraries.\n* [Node-SVM](https:\u002F\u002Fgithub.com\u002Fnicolaspanel\u002Fnode-svm) - Support Vector Machine for Node.js\n* [Brain](https:\u002F\u002Fgithub.com\u002Fharthur\u002Fbrain) - Neural networks in JavaScript **[Deprecated]**\n* [Brain.js](https:\u002F\u002Fgithub.com\u002FBrainJS\u002Fbrain.js) - Neural networks in JavaScript - continued community fork of [Brain](https:\u002F\u002Fgithub.com\u002Fharthur\u002Fbrain).\n* [Bayesian-Bandit](https:\u002F\u002Fgithub.com\u002Fomphalos\u002Fbayesian-bandit.js) - Bayesian bandit implementation for Node and the browser. **[Deprecated]**\n* [Synaptic](https:\u002F\u002Fgithub.com\u002Fcazala\u002Fsynaptic) - Architecture-free neural network library for Node.js and the browser.\n* [kNear](https:\u002F\u002Fgithub.com\u002FNathanEpstein\u002FkNear) - JavaScript implementation of the k nearest neighbors algorithm for supervised learning.\n* [NeuralN](https:\u002F\u002Fgithub.com\u002Ftotemstech\u002Fneuraln) - C++ Neural Network library for Node.js. It has advantage on large dataset and multi-threaded training. **[Deprecated]**\n* [kalman](https:\u002F\u002Fgithub.com\u002Fitamarwe\u002Fkalman) - Kalman filter for JavaScript. **[Deprecated]**\n* [shaman](https:\u002F\u002Fgithub.com\u002Fluccastera\u002Fshaman) - Node.js library with support for both simple and multiple linear regression. **[Deprecated]**\n* [ml.js](https:\u002F\u002Fgithub.com\u002Fmljs\u002Fml) - Machine learning and numerical analysis tools for Node.js and the Browser!\n* [ml5](https:\u002F\u002Fgithub.com\u002Fml5js\u002Fml5-library) - Friendly machine learning for the web!\n* [Pavlov.js](https:\u002F\u002Fgithub.com\u002FNathanEpstein\u002FPavlov.js) - Reinforcement learning using Markov Decision Processes.\n* [MXNet](https:\u002F\u002Fgithub.com\u002Fapache\u002Fincubator-mxnet) - Lightweight, Portable, Flexible Distributed\u002FMobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, JavaScript and more.\n* [TensorFlow.js](https:\u002F\u002Fjs.tensorflow.org\u002F) - A WebGL accelerated, browser based JavaScript library for training and deploying ML models.\n* [JSMLT](https:\u002F\u002Fgithub.com\u002Fjsmlt\u002Fjsmlt) - Machine learning toolkit with classification and clustering for Node.js; supports visualization (see [visualml.io](https:\u002F\u002Fvisualml.io)).\n* [xgboost-node](https:\u002F\u002Fgithub.com\u002Fnuanio\u002Fxgboost-node) - Run XGBoost model and make predictions in Node.js.\n* [Netron](https:\u002F\u002Fgithub.com\u002Flutzroeder\u002Fnetron) - Visualizer for machine learning models.\n* [tensor-js](https:\u002F\u002Fgithub.com\u002FHoff97\u002Ftensorjs) - A deep learning library for the browser, accelerated by WebGL and WebAssembly.\n* [WebDNN](https:\u002F\u002Fgithub.com\u002Fmil-tokyo\u002Fwebdnn) - Fast Deep Neural Network JavaScript Framework. WebDNN uses next generation JavaScript API, WebGPU for GPU execution, and WebAssembly for CPU execution.\n* [WebNN](https:\u002F\u002Fwebnn.dev) - A new web standard that allows web apps and frameworks to accelerate deep neural networks with on-device hardware such as GPUs, CPUs, or purpose-built AI accelerators.\n* [Kandle](https:\u002F\u002Fgithub.com\u002Ffinal-kk\u002Fkandle) - A JavaScript Native PyTorch-aligned Machine Learning Framework, built from scratch on WebGPU.\n\n\u003Ca name=\"javascript-misc\">\u003C\u002Fa>\n#### Misc\n\n* [stdlib](https:\u002F\u002Fgithub.com\u002Fstdlib-js\u002Fstdlib) - 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.\n* [sylvester](https:\u002F\u002Fgithub.com\u002Fjcoglan\u002Fsylvester) - Vector and Matrix math for JavaScript. **[Deprecated]**\n* [simple-statistics](https:\u002F\u002Fgithub.com\u002Fsimple-statistics\u002Fsimple-statistics) - 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.\n* [regression-js](https:\u002F\u002Fgithub.com\u002FTom-Alexander\u002Fregression-js) - A javascript library containing a collection of least squares fitting methods for finding a trend in a set of data.\n* [Lyric](https:\u002F\u002Fgithub.com\u002Fflurry\u002FLyric) - Linear Regression library. **[Deprecated]**\n* [GreatCircle](https:\u002F\u002Fgithub.com\u002Fmwgg\u002FGreatCircle) - Library for calculating great circle distance.\n* [MLPleaseHelp](https:\u002F\u002Fgithub.com\u002Fjgreenemi\u002FMLPleaseHelp) - MLPleaseHelp is a simple ML resource search engine. You can use this search engine right now at [https:\u002F\u002Fjgreenemi.github.io\u002FMLPleaseHelp\u002F](https:\u002F\u002Fjgreenemi.github.io\u002FMLPleaseHelp\u002F), provided via GitHub Pages.\n* [Pipcook](https:\u002F\u002Fgithub.com\u002Falibaba\u002Fpipcook) - A JavaScript application framework for machine learning and its engineering.\n\n\u003Ca name=\"javascript-demos-and-scripts\">\u003C\u002Fa>\n#### Demos and Scripts\n* [The Bot](https:\u002F\u002Fgithub.com\u002Fsta-ger\u002FTheBot) - Example of how the neural network learns to predict the angle between two points created with [Synaptic](https:\u002F\u002Fgithub.com\u002Fcazala\u002Fsynaptic).\n* [Half Beer](https:\u002F\u002Fgithub.com\u002Fsta-ger\u002FHalfBeer) - Beer glass classifier created with [Synaptic](https:\u002F\u002Fgithub.com\u002Fcazala\u002Fsynaptic).\n* [NSFWJS](http:\u002F\u002Fnsfwjs.com) - Indecent content checker with TensorFlow.js\n* [Rock Paper Scissors](https:\u002F\u002Frps-tfjs.netlify.com\u002F) - Rock Paper Scissors trained in the browser with TensorFlow.js\n* [Heroes Wear Masks](https:\u002F\u002Fheroeswearmasks.fun\u002F) - A fun TensorFlow.js-based oracle that tells, whether one wears a face mask or not. It can even tell when one wears the mask incorrectly.\n\n\u003Ca name=\"julia\">\u003C\u002Fa>\n## Julia\n\n\u003Ca name=\"julia-general-purpose-machine-learning\">\u003C\u002Fa>\n#### General-Purpose Machine Learning\n\n* [MachineLearning](https:\u002F\u002Fgithub.com\u002Fbenhamner\u002FMachineLearning.jl) - Julia Machine Learning library. **[Deprecated]**\n* [MLBase](https:\u002F\u002Fgithub.com\u002FJuliaStats\u002FMLBase.jl) - A set of functions to support the development of machine learning algorithms.\n* [PGM](https:\u002F\u002Fgithub.com\u002FJuliaStats\u002FPGM.jl) - A Julia framework for probabilistic graphical models.\n* [DA](https:\u002F\u002Fgithub.com\u002Ftrthatcher\u002FDiscriminantAnalysis.jl) - Julia package for Regularized Discriminant Analysis.\n* [Regression](https:\u002F\u002Fgithub.com\u002Flindahua\u002FRegression.jl) - Algorithms for regression analysis (e.g. linear regression and logistic regression). **[Deprecated]**\n* [Local Regression](https:\u002F\u002Fgithub.com\u002FJuliaStats\u002FLoess.jl) - Local regression, so smooooth!\n* [Naive Bayes](https:\u002F\u002Fgithub.com\u002Fnutsiepully\u002FNaiveBayes.jl) - Simple Naive Bayes implementation in Julia. **[Deprecated]**\n* [Mixed Models](https:\u002F\u002Fgithub.com\u002Fdmbates\u002FMixedModels.jl) - A Julia package for fitting (statistical) mixed-effects models.\n* [Simple MCMC](https:\u002F\u002Fgithub.com\u002Ffredo-dedup\u002FSimpleMCMC.jl) - basic MCMC sampler implemented in Julia. **[Deprecated]**\n* [Distances](https:\u002F\u002Fgithub.com\u002FJuliaStats\u002FDistances.jl) - Julia module for Distance evaluation.\n* [Decision Tree](https:\u002F\u002Fgithub.com\u002Fbensadeghi\u002FDecisionTree.jl) - Decision Tree Classifier and Regressor.\n* [Neural](https:\u002F\u002Fgithub.com\u002Fcompressed\u002FBackpropNeuralNet.jl) - A neural network in Julia.\n* [MCMC](https:\u002F\u002Fgithub.com\u002Fdoobwa\u002FMCMC.jl) - MCMC tools for Julia. **[Deprecated]**\n* [Mamba](https:\u002F\u002Fgithub.com\u002Fbrian-j-smith\u002FMamba.jl) - Markov chain Monte Carlo (MCMC) for Bayesian analysis in Julia.\n* [GLM](https:\u002F\u002Fgithub.com\u002FJuliaStats\u002FGLM.jl) - Generalized linear models in Julia.\n* [Gaussian Processes](https:\u002F\u002Fgithub.com\u002FSTOR-i\u002FGaussianProcesses.jl) - Julia package for Gaussian processes.\n* [Online Learning](https:\u002F\u002Fgithub.com\u002Flendle\u002FOnlineLearning.jl) **[Deprecated]**\n* [GLMNet](https:\u002F\u002Fgithub.com\u002Fsimonster\u002FGLMNet.jl) - Julia wrapper for fitting Lasso\u002FElasticNet GLM models using glmnet.\n* [Clustering](https:\u002F\u002Fgithub.com\u002FJuliaStats\u002FClustering.jl) - Basic functions for clustering data: k-means, dp-means, etc.\n* [SVM](https:\u002F\u002Fgithub.com\u002FJuliaStats\u002FSVM.jl) - SVM for Julia. **[Deprecated]**\n* [Kernel Density](https:\u002F\u002Fgithub.com\u002FJuliaStats\u002FKernelDensity.jl) - Kernel density estimators f","awesome-machine-learning 项目是一个精心整理的机器学习框架、库和软件列表。该项目主要按照编程语言分类，汇集了多种语言下的优秀机器学习资源，特别强调Python相关的工具与库。其核心功能在于提供一个易于访问且持续更新的资源指南，帮助开发者快速找到合适的机器学习解决方案。此外，还提供了免费书籍、在线课程、专业会议等额外的学习资料链接。适合于正在寻找合适机器学习工具的研究人员、工程师以及任何对机器学习感兴趣的人士使用。",2,"2026-06-11 02:35:46","top_all"]