Compare commits

...

46 Commits

Author SHA1 Message Date
Joseph Misiti
a16191777f
Merge pull request #1452 from nurkhz/add-desert-ant-labs
Add Voz (on-device speech recognition) to Swift and Kotlin
2026-10-27 15:21:38 -04:00
Joseph Misiti
52fb11adda
Merge pull request #1453 from gabrielfruet/add-lightlystudio
Add LightlyStudio to Tools > Misc
2026-10-27 15:21:11 -04:00
fruet
35dbde958f Add LightlyStudio to Tools > Misc
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 14:40:39 -03:00
Nurkan Kirkan
a2a30fb31a Add Voz (on-device speech recognition) to Swift and Kotlin 2026-10-27 16:52:29 +01:00
Joseph Misiti
a613d9b2da
Merge pull request #1446 from jays-beep/patch-1
Add Future AGI to Python General-Purpose Machine Learning
2026-10-22 14:52:54 -04:00
Jay Singh
9bc79b3bfb
Add Future AGI to Python General-Purpose Machine Learning 2026-10-22 23:28:59 +05:30
Joseph Misiti
ae5bcf3fe1
Merge pull request #1445 from marvelefe/docs/add-machine-learning-101
Add Machine Learning 101 to courses.md (Machine-Learning / Data Mining)
2026-10-22 09:20:22 -04:00
marvelefe
b1ec405df5 Add Machine Learning 101 to courses.md (Machine-Learning / Data Mining) 2026-10-22 08:04:01 +01:00
Joseph Misiti
3700ceb649
Merge pull request #1444 from ajhendel/add-mojolearn
Add mojolearn to Python machine learning libraries
2026-10-21 20:20:11 -04:00
Andrew Hendel
3934babcf2 Add mojolearn for reproducible machine learning 2026-10-21 18:36:50 -04:00
Joseph Misiti
d033763aed
Merge pull request #1443 from colemanhindes/add-mimetic-events
Add Mimetic Events to events.md
2026-10-19 09:14:32 -04:00
colemanhindes
2750a63ea7 Add Mimetic Events to events.md and fix Codementor link 2026-10-18 19:32:23 -07:00
Joseph Misiti
9922a4f42c
Merge pull request #1440 from Thorium/add-fuuga
Add Fuuga
2026-10-12 20:31:03 -04:00
Tuomas Hietanen
10f6741062 Add Fuuga
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 23:01:04 +00:00
Joseph Misiti
18146120a5
Merge pull request #1438 from alexkroman/add-tiny-audio 2026-10-09 19:52:52 -04:00
Alex Kroman
35306caa8a Add tiny-audio to Python Speech Recognition
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 13:42:35 -07:00
Ilya Grishutin
bff8a9e61a
Add YOLO Annotator to Python Computer Vision (#1436) 2026-10-07 17:59:25 -04:00
KS
e89485291d
Add PixelBank to courses (#1432)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 12:49:00 -04:00
Speed K
fc9142a2a0
Add yasbd-lib to Python NLP section (#1425) 2026-09-22 08:17:27 -04:00
Ishii Norimi
c2a4d64ad9
Add AI on Browser to JavaScript General-Purpose Machine Learning (#1427) 2026-09-21 09:54:11 -04:00
Shaier
a5100b7519
Add QuiddityML to Educational Tools (#1426) 2026-09-17 06:19:48 -04:00
Justin
2cd5162e73
Add Glyph library to Javascript NLP resources list (#1404) 2026-09-12 10:34:25 -04:00
Agosillo
0fa2efd502
Add MiaIA to C++ machine learning libraries (#1422) 2026-09-08 13:30:34 -04:00
David Liptak
e1d7dca5fc
Add HypercubeESN, HypercubeWTF, HypercubeCascade, and HypercubeHopfield links (#1418)
Introducing the HypercubeAI project — a quest to systematically re-implement classical neural architectures on a Boolean hypercube topology instead of Euclidean grids or random graphs. The central thesis is “topology-native intelligence”: the hypercube’s algebraic structure (vertex-transitive symmetry, Hamming geometry, bitwise addressing) can serve as a first-class computational substrate.
2026-09-02 15:29:21 -04:00
Mownetharan
60e4a0b52e
Add pyinterpret to Python General-Purpose Machine Learning (#1415)
Unified API for SHAP, LIME, permutation importance, and partial dependence.
2026-08-27 11:29:10 -04:00
shyringo
d84bb6323d
Add DeepSeek-V4-Flash-0731 CPU inference engine (#1413) 2026-08-26 17:09:24 -04:00
Samuel Hu
b6187c64dd
Add CosmoEdge to C++ Computer Vision (#1412)
Add CosmoEdge as a C++ edge video AI engine.
2026-08-26 10:36:11 -04:00
shyringo
9494945152
Add qwen3.8-27b-in-c to C machine learning tools (#1409) 2026-08-24 15:57:48 -04:00
Vic Rak
0db15e5f36
Add VoxRT to Speech Recognition (Python, C++, Kotlin, Swift, Go, JavaScript, C) (#1408) 2026-08-21 06:11:51 -04:00
Shivam Lalakiya
8dfdba6622
Add PhilanthroPy to Python General-Purpose Machine Learning (#1403) 2026-08-11 17:49:59 -04:00
Alessio Russo
38487d1c55
Add 'fenn' framework to Neural Networks list (#1401)
Added a new entry for 'fenn' framework in the Neural Networks section.
2026-08-06 14:03:02 -04:00
DaoudiNadia
ec0d7e361c
Add BESSER Neural Network Editor to Tools, Neural Networks (#1398) 2026-07-30 11:00:37 -04:00
Ansh Kansagra
3dfc3b15ef
Update README.md (#1397) 2026-07-27 09:13:10 -04:00
Tanay Mishra
17317a3b41
Add Leanpass autodiff library to README (#1395)
Added Leanpass library to the list of machine learning resources.
2026-07-26 12:44:21 -04:00
Mike Kuykendall
d26871fd3b
Add shimmytok to Rust Natural Language Processing (#1392) 2026-07-21 09:51:37 -04:00
alokkumar-afk
caa358dcf4
Add IIT Bombay AI and Data Science course (#1391)
Adds the IIT Bombay e-Postgraduate Diploma in Artificial Intelligence and Data Science to courses.md under the Machine-Learning / Data Mining section.

The program covers artificial intelligence, machine learning, and data science and is offered online as a paid course.
2026-07-20 10:12:35 -04:00
Arianna Method
75c821ba74
adding NoTorch to the list: neural networks in C (#1386)
* Arianna Method adds notorch to the C / General-Purpose ML list

notorch — a neural network framework in pure C: training and inference, no dependencies.
Placed under C > General-Purpose Machine Learning, next to onnx-c.

Co-Authored-By: Claude (Arianna Method, intel) <theariannamethod@gmail.com>
Coordinated with Oleg Ataeff (maintainer)

* update description for notorch

---------

Co-authored-by: Oleg Ataeff <iamolegataeff@gmail.com>
2026-07-14 14:00:58 +01:00
Jaedon Munton
a0692c7f92
Add autobatcher to Python General-Purpose Machine Learning (#1380) 2026-07-11 15:59:19 -04:00
Vojtěch Novák
433f2a138e
Add C++ Linear Regression Engine to C++ section (#1357) 2026-06-18 09:51:25 -04:00
Junaid Ali
2697f1548b
Add zij (#1354) 2026-06-16 12:13:41 -04:00
Petr Stanislavovich Berlizov
1bbe471fbb
Add Adaptive Reliability Layer to Python ML tools (#1350) 2026-06-13 12:49:01 -04:00
George
978808ac9c
✨ add anneal to Go / General-Purpose Machine Learning (#1341) 2026-06-01 15:03:51 -04:00
Grant Wasserman
260f944ab9
Add Educational Tools section to README w/ nn-visual entry (#1319)
Added a new section for educational tools with a link to NN Visual. I wondered if some of the other entries in MISC could also fit into this category but I didn't want to take the authority to move them.
2026-05-12 09:17:23 -04:00
pypl0
61d0c511bc
Update README.md (#1300) 2026-04-26 11:32:14 -04:00
Joseph Misiti
ea861c9606
Update README.md 2026-04-21 18:31:55 -04:00
Joseph Misiti
da9c322be2
Update contribution guidelines and deprecation policy (#1298)
Added important note regarding PR contributions and repository deprecation criteria.
2026-04-21 18:31:30 -04:00
3 changed files with 77 additions and 5 deletions

View File

@ -2,7 +2,10 @@
A curated list of awesome machine learning frameworks, libraries and software (by language). Inspired by `awesome-php`.
_If you want to contribute to this list (please do), send me a pull request or contact me [@josephmisiti](https://twitter.com/josephmisiti)._
## IMPORTANT NOTE ON PRs:
As 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.
Also, a listed repository should be deprecated if:
* Repository's owner explicitly says that "this library is not maintained".
@ -44,6 +47,7 @@ Further resources:
- [C](#c)
- [General-Purpose Machine Learning](#c-general-purpose-machine-learning)
- [Computer Vision](#c-computer-vision)
- [Speech Recognition](#c-speech-recognition)
- [C++](#cpp)
- [Computer Vision](#cpp-computer-vision)
- [General-Purpose Machine Learning](#cpp-general-purpose-machine-learning)
@ -82,6 +86,7 @@ Further resources:
- [Data Analysis / Data Visualization](#go-data-analysis--data-visualization)
- [Computer vision](#go-computer-vision)
- [Reinforcement learning](#go-reinforcement-learning)
- [Speech Recognition](#go-speech-recognition)
- [Haskell](#haskell)
- [General-Purpose Machine Learning](#haskell-general-purpose-machine-learning)
- [Java](#java)
@ -96,6 +101,7 @@ Further resources:
- [General-Purpose Machine Learning](#javascript-general-purpose-machine-learning)
- [Misc](#javascript-misc)
- [Demos and Scripts](#javascript-demos-and-scripts)
- [Speech Recognition](#javascript-speech-recognition)
- [Julia](#julia)
- [General-Purpose Machine Learning](#julia-general-purpose-machine-learning)
- [Natural Language Processing](#julia-natural-language-processing)
@ -103,6 +109,7 @@ Further resources:
- [Misc Stuff / Presentations](#julia-misc-stuff--presentations)
- [Kotlin](#kotlin)
- [Deep Learning](#kotlin-deep-learning)
- [Speech Recognition](#kotlin-speech-recognition)
- [Lua](#lua)
- [General-Purpose Machine Learning](#lua-general-purpose-machine-learning)
- [Demos and Scripts](#lua-demos-and-scripts)
@ -169,15 +176,18 @@ Further resources:
- [Neural Networks](#scheme-neural-networks)
- [Swift](#swift)
- [General-Purpose Machine Learning](#swift-general-purpose-machine-learning)
- [Speech Recognition](#swift-speech-recognition)
- [TensorFlow](#tensorflow)
- [General-Purpose Machine Learning](#tensorflow-general-purpose-machine-learning)
### [Tools](#tools-1)
- [Educational Tools](#tools-educational-tools)
- [Neural Networks](#tools-neural-networks)
- [Misc](#tools-misc)
[Credits](#credits)
<!-- /MarkdownTOC -->
@ -201,7 +211,10 @@ Further resources:
* [cONNXr](https://github.com/alrevuelta/cONNXr) - 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.
* [libonnx](https://github.com/xboot/libonnx) - A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.
* [onnx-c](https://github.com/onnx/onnx-c) - A lightweight C library for ONNX model inference, optimized for performance and portability across platforms.
* [notorch](https://github.com/ariannamethod/notorch) - Neural networks framework in pure C: training and inference, no dependencies.
* [qsmm](http://qsmm.org) - A C library implementing the rudiments of a toolchain for working with adaptive probabilistic assembler programs.
* [qwen3.8-27b-in-c](https://github.com/shyringo/qwen3.8-27b-in-c) - A native C inference engine for running Qwen3.8-27B locally on a single laptop CPU, with direct GGUF loading and a tested 8 GB memory path.
* [deepseek-v4-flash-0731-in-c](https://github.com/shyringo/deepseek-v4-flash-0731-in-c) - A native C CPU inference engine for running the 284B-A13B DeepSeek-V4-Flash-0731 on one laptop, reaching up to 1.12 token/s on tested hardware while streaming the 167 GB checkpoint from disk with a tested 8 GB memory path and no GPU or Python.
<a name="c-computer-vision"></a>
#### Computer Vision
@ -211,12 +224,17 @@ Further resources:
* [YOLOv8](https://github.com/ultralytics/ultralytics) - Ultralytics' YOLOv8 implementation with C++ support for real-time object detection and tracking, optimized for edge devices.
* [SpecX](https://specx.pro) - Specialized AI vision for extracting engineering specs from PDF/JPG to Excel.
<a name="c-speech-recognition"></a>
#### Speech Recognition
* [VoxRT](https://github.com/VoxRT/voxrt-asr-linux) - On-device streaming speech recognition runtime with C API for Linux (aarch64/x86_64). Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Companion Silero VAD, wake-word, and 14-command KWS via same runtime.
<a name="cpp"></a>
## C++
<a name="cpp-computer-vision"></a>
#### Computer Vision
* [CosmoEdge](https://github.com/cosmo-wander-ai/cosmo-edge) - A C++ edge video AI engine for RTSP ingestion, CV/VLM inference, visual pipeline orchestration, alarms, and event delivery on Sophon and Rockchip NPUs.
* [DLib](http://dlib.net/imaging.html) - DLib has C++ and Python interfaces for face detection and training general object detectors.
* [EBLearn](http://eblearn.sourceforge.net/) - Eblearn is an object-oriented C++ library that implements various machine learning models **[Deprecated]**
* [OpenCV](https://opencv.org) - OpenCV has C++, C, Python, Java and MATLAB interfaces and supports Windows, Linux, Android and Mac OS.
@ -245,13 +263,15 @@ Further resources:
* [LightGBM](https://github.com/Microsoft/LightGBM) - 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.
* [libfm](https://github.com/srendle/libfm) - A generic approach that allows to mimic most factorization models by feature engineering.
* [MCGrad](https://github.com/facebookincubator/MCGrad/) - A production-ready library for multicalibration, fairness, and bias correction in machine learning models.
* [MiaIA](https://github.com/Agosillo/MiaIA) - An open-source C++20 neural-network engine and Unreal Engine 5 Studio for building, training, visualizing, inspecting, and debugging observable feed-forward networks.
* [MLDB](https://mldb.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.
* [mlpack](https://www.mlpack.org/) - A scalable C++ machine learning library.
* [MXNet](https://github.com/apache/incubator-mxnet) - Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, JavaScript and more.
* [N2D2](https://github.com/CEA-LIST/N2D2) - CEA-List's CAD framework for designing and simulating Deep Neural Network, and building full DNN-based applications on embedded platforms
* [oneDNN](https://github.com/oneapi-src/oneDNN) - An open-source cross-platform performance library for deep learning applications.
* [Opik](https://www.comet.com/site/products/opik/) - 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://github.com/comet-ml/opik/))
* [ParaMonte](https://github.com/cdslaborg/paramonte) - A general-purpose library with C/C++ interface for Bayesian data analysis and visualization via serial/parallel Monte Carlo and MCMC simulations. Documentation can be found [here](https://www.cdslab.org/paramonte/).
* [Ombre](https://github.com/pypl0/Ombre) - Open source AI infrastructure layer. Eight agents run automatically: security, caching, memory, hallucination detection, and tamper-proof audit trail. Runs locally.
* [ParaMonte](https://github.com/cdslaborg/paramonte) - A general-purpose library with C/C++ interface for Bayesian data analysis and visualization via serial/parallel Monte Carlo and MCMC simulations. Documentation can be found [here](https://www.cdslab.org/paramonte/).
* [proNet-core](https://github.com/cnclabs/proNet-core) - A general-purpose network embedding framework: pair-wise representations optimization Network Edit.
* [PyCaret](https://github.com/pycaret/pycaret) - An open-source, low-code machine learning library in Python that automates machine learning workflows.
* [PyCUDA](https://mathema.tician.de/software/pycuda/) - Python interface to CUDA
@ -278,6 +298,7 @@ Further resources:
* [XAD](https://github.com/auto-differentiation/XAD) - Comprehensive backpropagation tool for C++.
* [Truss](https://truss.baseten.co) - An open source framework for packaging and serving ML models.
* [nndeploy](https://github.com/nndeploy/nndeploy) - An Easy-to-Use and High-Performance AI deployment framework.
* [ols-regression-engine](https://github.com/VojtechNovakk/ols-regression-engine) - A low-level Linear Regression Engine utilizing the Ordinary Least Squares (OLS) method and QR decomposition.
<a name="cpp-natural-language-processing"></a>
#### Natural Language Processing
@ -297,6 +318,7 @@ Further resources:
#### Speech Recognition
* [Kaldi](https://github.com/kaldi-asr/kaldi) - 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.
* [Vosk](https://github.com/alphacep/vosk-api) - An offline speech recognition toolkit with C++ support, designed for low-resource devices and multiple languages.
* [VoxRT](https://github.com/VoxRT/voxrt-asr-linux) - On-device streaming speech recognition runtime with C/C++ headers for Linux (aarch64/x86_64). Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Companion Silero VAD, wake-word, and 14-command KWS via same runtime.
<a name="cpp-sequence-analysis"></a>
#### Sequence Analysis
@ -481,6 +503,7 @@ Read the paper [here](https://arxiv.org/abs/1902.06714).
* [goro](https://github.com/aunum/goro) - A high-level machine learning library in the vein of Keras.
* [gorse](https://github.com/zhenghaoz/gorse) - An offline recommender system backend based on collaborative filtering written in Go.
* [therfoo](https://github.com/therfoo/therfoo) - An embedded deep learning library for Go.
* [anneal](https://github.com/georgebuilds/anneal) - From-scratch Go port of tinygrad: a graph-rewrite ML compiler with reverse-mode autodiff and a WebGPU backend.
* [neat](https://github.com/jinyeom/neat) - Plug-and-play, parallel Go framework for NeuroEvolution of Augmenting Topologies (NEAT). **[Deprecated]**
* [go-pr](https://github.com/daviddengcn/go-pr) - Pattern recognition package in Go lang. **[Deprecated]**
* [go-ml](https://github.com/alonsovidales/go_ml) - Linear / Logistic regression, Neural Networks, Collaborative Filtering and Gaussian Multivariate Distribution. **[Deprecated]**
@ -517,6 +540,10 @@ Read the paper [here](https://arxiv.org/abs/1902.06714).
* [GoCV](https://github.com/hybridgroup/gocv) - Package for computer vision using OpenCV 4 and beyond.
<a name="go-speech-recognition"></a>
#### Speech Recognition
* [VoxRT](https://github.com/VoxRT/voxrt-asr-linux) - On-device streaming speech recognition runtime with Go bindings. Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Ships alongside C/C++, PyPI, and npm packages for Linux (aarch64/x86_64).
<a name="go-reinforcement-learning"></a>
#### Reinforcement learning
@ -629,6 +656,7 @@ Read the paper [here](https://arxiv.org/abs/1902.06714).
* [Retext](https://github.com/retextjs/retext) - Extensible system for analyzing and manipulating natural language.
* [NLP Compromise](https://github.com/spencermountain/compromise) - Natural Language processing in the browser.
* [nlp.js](https://github.com/axa-group/nlp.js) - An NLP library built in node over Natural, with entity extraction, sentiment analysis, automatic language identify, and so more.
* [Glyph](https://github.com/Koda-OSS/Glyph) - Framework-agnostic TypeScript library for generating, searching, and comparing MinHash fingerprints for fast text similarity, deduplication, and retrieval.
@ -699,6 +727,11 @@ Read the paper [here](https://arxiv.org/abs/1902.06714).
* [WebDNN](https://github.com/mil-tokyo/webdnn) - Fast Deep Neural Network JavaScript Framework. WebDNN uses next generation JavaScript API, WebGPU for GPU execution, and WebAssembly for CPU execution.
* [WebNN](https://webnn.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.
* [Kandle](https://github.com/final-kk/kandle) - A JavaScript Native PyTorch-aligned Machine Learning Framework, built from scratch on WebGPU.
* [AI on Browser](https://github.com/ai-on-browser/ai-on-browser.github.io) - An educational, pure JavaScript library designed to help developers and students understand the inner workings of ML algorithms without the magic of external libraries.
<a name="javascript-speech-recognition"></a>
#### Speech Recognition
* [VoxRT](https://github.com/VoxRT/voxrt-asr-linux) - On-device streaming speech recognition runtime with npm bindings. Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Ships alongside C/C++, Python (PyPI), and Go packages for Linux (aarch64/x86_64).
<a name="javascript-misc"></a>
#### Misc
@ -808,6 +841,11 @@ Read the paper [here](https://arxiv.org/abs/1902.06714).
#### Deep Learning
* [KotlinDL](https://github.com/JetBrains/KotlinDL) - Deep learning framework written in Kotlin.
<a name="kotlin-speech-recognition"></a>
#### Speech Recognition
* [VoxRT](https://github.com/VoxRT/voxrt-asr-android) - On-device streaming speech recognition SDK for Android with Kotlin bindings (JitPack). Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Companion Silero VAD, wake-word, and 14-command KWS via same runtime.
* [Voz](https://desertant.com/models/voz/) - On-device speech recognition SDK for Android in Kotlin with word timestamps. Source-available.
<a name="lua"></a>
## Lua
@ -940,6 +978,7 @@ on MNIST digits[DEEP LEARNING].
#### Natural Language Processing
* [Stanford.NLP for .NET](https://github.com/sergey-tihon/Stanford.NLP.NET/) - A full port of Stanford NLP packages to .NET and also available precompiled as a NuGet package.
* [Fuuga](https://bitbucket.org/thorium/fuuga) - LLM pipeline built from scratch in F# on TorchSharp: BPE tokenizer training, pre-training, LoRA/QLoRA/DPO fine-tuning, weight import from Hugging Face and GGUF models, RAG-grounded generation and an OpenAI-compatible server. GPU or CPU, no Python.
<a name="net-general-purpose-machine-learning"></a>
#### General-Purpose Machine Learning
@ -1097,6 +1136,7 @@ be
* [segmentation_models.pytorch](https://github.com/qubvel/segmentation_models.pytorch) - 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.
* [segmentation_models](https://github.com/qubvel/segmentation_models) - 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](https://github.com/ml-explore/mlx)- MLX is an array framework for machine learning on Apple silicon, developed by Apple machine learning research.
* [YOLO Annotator](https://github.com/ILYAGRISH/yolo-annotator) - Offline desktop tool (PyQt6) for labeling images: boxes, polygons, oriented boxes, keypoints, brush masks and semantic/panoptic regions. Exports YOLO, COCO (incl. RLE and Panoptic), Pascal VOC, LabelMe and PNG masks.
<a name="python-natural-language-processing"></a>
#### Natural Language Processing
@ -1149,6 +1189,7 @@ be
* [Transformers](https://github.com/huggingface/transformers) - A deep learning library containing thousands of pre-trained models on different tasks. The goto place for anything related to Large Language Models.
* [TextCL](https://github.com/alinapetukhova/textcl) - Text preprocessing package for use in NLP tasks.
* [VeritasGraph](https://github.com/bibinprathap/VeritasGraph) - Enterprise-Grade Graph RAG for Secure, On-Premise AI with Verifiable Attribution.
* [yasbd-lib](https://github.com/speedyk-005/yasbd-lib) - High-accuracy, rule-based sentence boundary detector (SBD) with drop-in pysbd adapter, streaming APIs, CLI, and a spaCy component across 39+ languages.
<a name="python-general-purpose-machine-learning"></a>
#### General-Purpose Machine Learning
@ -1172,6 +1213,7 @@ be
* [PyOD](https://github.com/yzhao062/pyod) -> 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.
* [steppy](https://github.com/neptune-ml/steppy) -> Lightweight, Python library for fast and reproducible machine learning experimentation. Introduces a very simple interface that enables clean machine learning pipeline design.
* [steppy-toolkit](https://github.com/neptune-ml/steppy-toolkit) -> Curated collection of the neural networks, transformers and models that make your machine learning work faster and more effective.
* [mojolearn](https://github.com/mojolearn/mojolearn) - GPU machine learning implemented in Mojo with Python bindings for classical models and neural training and inference. In `identical` mode, mojolearn returns the same bits on Apple, NVIDIA and AMD GPUs.
* [CNTK](https://github.com/Microsoft/CNTK) - Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit. Documentation can be found [here](https://docs.microsoft.com/cognitive-toolkit/).
* [Couler](https://github.com/couler-proj/couler) - Unified interface for constructing and managing machine learning workflows on different workflow engines, such as Argo Workflows, Tekton Pipelines, and Apache Airflow.
* [auto_ml](https://github.com/ClimbsRocks/auto_ml) - 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.
@ -1180,6 +1222,7 @@ be
* [machine learning](https://github.com/jeff1evesque/machine-learning) - automated build consisting of a [web-interface](https://github.com/jeff1evesque/machine-learning#web-interface), and set of [programmatic-interface](https://github.com/jeff1evesque/machine-learning#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.
* [XGBoost](https://github.com/dmlc/xgboost) - Python bindings for eXtreme Gradient Boosting (Tree) Library.
* [InterpretML](https://github.com/interpretml/interpret) - 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.
* [pyinterpret](https://github.com/mowne67/pyinterpret) - Unified API for SHAP, LIME, permutation importance, and partial dependence explanations.
* [ChefBoost](https://github.com/serengil/chefboost) - 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.
* [Apache SINGA](https://singa.apache.org) - An Apache Incubating project for developing an open source machine learning library.
* [Bayesian Methods for Hackers](https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers) - Book/iPython notebooks on Probabilistic Programming in Python.
@ -1207,6 +1250,7 @@ be
* [prophet](https://facebook.github.io/prophet/) - Fast and automated time series forecasting framework by Facebook.
* [skforecast](https://github.com/skforecast/skforecast) - 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.
* [Feature-engine](https://github.com/feature-engine/feature_engine) - Open source library with an exhaustive battery of feature engineering and selection methods based on pandas and scikit-learn.
* [PhilanthroPy](https://github.com/PhilanthroPy-Project/PhilanthroPy) - A scikit-learn native toolkit for nonprofit and academic-medical-center fundraising analytics: leakage-safe donor propensity, lapse, planned-giving, wealth-screening and revenue-forecasting estimators.
* [gensim](https://github.com/RaRe-Technologies/gensim) - Topic Modelling for Humans.
* [Gower Express](https://github.com/momonga-ml/gower-express.git) - The Fastest Gower Distance Implementation for Python. GPU-accelerated similarity matching for mixed data types, 15-25% faster than alternatives with production-ready reliability.
* [tweetopic](https://centre-for-humanities-computing.github.io/tweetopic/) - Blazing fast short-text-topic-modelling for Python.
@ -1272,6 +1316,7 @@ be
* [stacked_generalization](https://github.com/fukatani/stacked_generalization) - Implementation of machine learning stacking technique as a handy library in Python.
* [modAL](https://github.com/modAL-python/modAL) - A modular active learning framework for Python, built on top of scikit-learn.
* [Cogitare](https://github.com/cogitare-ai/cogitare): A Modern, Fast, and Modular Deep Learning and Machine Learning framework for Python.
* [Leanpass](https://github.com/Terminay/LeanPass) - A lightweight, NumPy-only autodiff library for small ML projects and learning how backpropagation works. It is 700x times lighter than Pytorch and 900x times lighter than TensorFlow.
* [Parris](https://github.com/jgreenemi/Parris) - Parris, the automated infrastructure setup tool for machine learning algorithms.
* [neonrvm](https://github.com/siavashserver/neonrvm) - 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.
* [Turi Create](https://github.com/apple/turicreate) - 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.
@ -1324,12 +1369,15 @@ be
* [AutoGluon](https://github.com/awslabs/autogluon): AutoML for Image, Text, Tabular, Time-Series, and MultiModal Data.
* [PyBroker](https://github.com/edtechre/pybroker) - Algorithmic Trading with Machine Learning.
* [Frouros](https://github.com/IFCA/frouros): Frouros is an open source Python library for drift detection in machine learning systems.
* [Adaptive Reliability Layer](https://github.com/pberlizov/adaptive-reliability-layer): A bounded controller for production ML under distribution shift — detects drift, learns from delayed labels, and takes the smallest safe steering step to defer unnecessary retrains.
* [CometML](https://github.com/comet-ml/comet-examples): The best-in-class MLOps platform with experiment tracking, model production monitoring, a model registry, and data lineage from training straight through to production.
* [ClearML](https://github.com/clearml/clearml) - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution.
* [Okrolearn](https://github.com/Okerew/okrolearn): A python machine learning library created to combine powefull data analasys features with tensors and machine learning components, while maintaining support for other libraries.
* [Opik](https://github.com/comet-ml/opik): Evaluate, trace, test, and ship LLM applications across your dev and production lifecycles.
* [pyclugen](https://github.com/clugen/pyclugen) - Multidimensional cluster generation in Python.
* [mlforgex](https://github.com/dhgefergfefruiwefhjhcduc/ML_Forgex) - Lightweight ML utility for automated training, evaluation, and prediction with CLI and Python API support.
* [autobatcher](https://github.com/doublewordai/autobatcher) - Drop-in AsyncOpenAI replacement that transparently batches requests via the Batch API for cheaper LLM inference.
* [Future AGI](https://github.com/future-agi/future-agi) - Open-source, self-hostable platform to evaluate, trace, and guard LLM applications and AI agents.
<a name="python-data-analysis--data-visualization"></a>
#### Data Analysis / Data Visualization
@ -1453,6 +1501,7 @@ be
<a name="python-neural-networks"></a>
#### Neural Networks
* [fenn](https://github.com/pyfenn/fenn) - A simple Python framework for building ML/DL workflows and LLM agents faster, with prebuilt trainers, agent templates, logging, configuration management, and much more.
* [Kinho](https://github.com/kinhosz/Neural) - Simple API for Neural Network. Better for image processing with CPU/GPU + Transfer Learning.
* [nn_builder](https://github.com/p-christ/nn_builder) - nn_builder is a python package that lets you build neural networks in 1 line
* [NeuralTalk](https://github.com/karpathy/neuraltalk) - NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.
@ -1465,7 +1514,11 @@ be
* [Jina AI](https://jina.ai/) An easier way to build neural search in the cloud. Compatible with Jupyter Notebooks.
* [sequitur](https://github.com/shobrook/sequitur) PyTorch library for creating and training sequence autoencoders in just two lines of code
* [ANEE](https://github.com/abkmystery/ANEE) - Adaptive Neural Execution Engine for transformers. Per-token sparse inference with dynamic layer skipping, profiler-based gating, and KV-cache-safe compute reduction.
* [zij](https://github.com/junaidaliop/zij) - A canon of deep learning optimization algorithms.
* [HypercubeESN](https://github.com/dliptak001/HypercubeESN) - Echo State Network on a Boolean hypercube reservoir: XOR Hamming-1 connectivity, no stored adjacency, C++23 + Python (`pip install hypercube-esn`).
* [HypercubeWTF](https://github.com/dliptak001/HypercubeWTF) - Frozen hypercube reservoir for static fields (synthetic-time orbit + thin CNN readout). Sibling of HypercubeESN.
* [HypercubeCascade](https://github.com/dliptak001/HypercubeCascade) - Etalon transit then WTF orbit on one cube, then a thin HypercubeCNN readout.
* [HypercubeHopfield](https://github.com/dliptak001/HypercubeHopfield) - Modern Hopfield associative memory on a hypercube graph with sparse local-attention retrieval (C++23 + Python).
<a name="python-spiking-neural-networks"></a>
@ -1535,6 +1588,8 @@ be
<a name="python-speech-recognition"></a>
#### Speech Recognition
* [EspNet](https://github.com/espnet/espnet) - ESPnet is an end-to-end speech processing toolkit for tasks like speech recognition, translation, and enhancement, using PyTorch and Kaldi-style data processing.
* [VoxRT](https://github.com/VoxRT/voxrt-asr-linux) - On-device streaming speech recognition toolkit with Python bindings. Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Ships companion VAD (Silero), wake-word, and 14-command keyword spotting via same runtime.
* [tiny-audio](https://github.com/alexkroman/tiny-audio) - Minimal, hackable PyTorch/Hugging Face codebase for training LLM-based speech recognition by connecting a frozen pretrained speech encoder to a pretrained LLM through a small trained projector, with word timestamps, speaker diarization and a free course.
<a name="python-development tools"></a>
#### Development Tools
@ -1613,6 +1668,7 @@ be
* [huggingface/tokenizers](https://github.com/huggingface/tokenizers) - Fast State-of-the-Art Tokenizers optimized for Research and Production
* [rust-bert](https://github.com/guillaume-be/rust-bert) - Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
* [shimmy](https://github.com/Michael-A-Kuykendall/shimmy) - Python-free Rust inference server for NLP models with OpenAI API compatibility and hot model swapping.
* [shimmytok](https://github.com/Michael-A-Kuykendall/shimmytok) - Pure-Rust tokenizer for GGUF models, compatible with llama.cpp tokenization.
<a name="r"></a>
## R
@ -1828,6 +1884,11 @@ be
* [Awesome CoreML](https://github.com/SwiftBrain/awesome-CoreML-models) - A curated list of pretrained CoreML models.
* [Awesome Core ML Models](https://github.com/likedan/Awesome-CoreML-Models) - A curated list of machine learning models in CoreML format.
<a name="swift-speech-recognition"></a>
#### Speech Recognition
* [VoxRT](https://github.com/VoxRT/voxrt-asr-ios) - On-device streaming speech recognition SDK for iOS with Swift bindings (SPM). Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Companion Silero VAD, wake-word, and 14-command KWS via same runtime.
* [Voz](https://desertant.com/models/voz/) - On-device speech recognition for iOS and macOS (SPM) with word timestamps, running on the Neural Engine. Source-available.
<a name="tensorflow"></a>
## TensorFlow
@ -1840,9 +1901,15 @@ be
<a name="tools"></a>
## Tools
<a name="tools-educational-tools"></a>
#### Educational Tools
* [NN Visual](https://nn-visual.com) - Interactive visualizations explaining neural networks, backpropagation, attention mechanisms, and transformers.
* [QuiddityML](https://quiddityml.com/?utm_source=github&utm_medium=awesome&utm_campaign=awesome-machine-learning) - The Duolingo of machine learning: short lessons, 11 types of hands-on exercises on the skills the job needs, spaced repetition so you don't forget what you learned, and a clear beginner-to-advanced roadmap covering Python, PyTorch, math for ML, ML foundations, NLP, vision, and more.
<a name="tools-neural-networks"></a>
#### Neural Networks
* [layer](https://github.com/cloudkj/layer) - Neural network inference from the command line
* [BESSER Neural Network Editor](https://editor.besser-pearl.org) - Browser-based visual editor for designing neural networks and automatically generating PyTorch and TensorFlow code.
<a name="tools-misc"></a>
#### Misc
@ -1902,7 +1969,8 @@ be
* [HyperAgency](https://github.com/vuics/h9y) - 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.
* [Bread Dataset Viewer](https://github.com/Bread-Technologies/mle_vscode_extension) - 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.
* [Bread WandB Viewer](https://github.com/Bread-Technologies/bread_wandb_viewer_extension) - 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.
* [Cortexa](https://automata-index.vercel.app) - Free, open-access search engine for robotics, ML, and AI research papers (arXiv, MDPI, IEEE OA).
* [LightlyStudio](https://github.com/lightly-ai/lightly-studio) - Open-source tool to curate and label computer vision datasets.
<a name="books"></a>
## Books

View File

@ -2,6 +2,7 @@ The following is a list of free or paid online courses on machine learning, stat
## Machine-Learning / Data Mining
* [Machine Learning 101](https://machinelearning101.com) - Interactive, browser-based platform for learning core ML algorithms through hands-on visualizations - free
* [System Designer - ML Systems](https://systemdesigner.net/ml-systems) - Interactive learning platform for ML systems and MLOps with 28 lessons on training pipelines, model serving, feature stores, and monitoring. Includes AI tutor, whiteboards, quizzes, and hands-on projects - free
* [System Designer - GenAI](https://systemdesigner.net/genai) - Interactive learning platform for GenAI and LLMs with 32 lessons on RAG systems, vector databases, agentic AI, and deployment. Includes AI tutor, whiteboards, quizzes, and projects - free
* [Artificial Intelligence (Columbia University)](https://www.edx.org/course/artificial-intelligence-ai-columbiax-csmm-101x-0) - free
@ -71,3 +72,5 @@ The following is a list of free or paid online courses on machine learning, stat
* [LabEx Machine Learning Skill Tree](https://labex.io/skilltrees/ml) - free and $ Hands-on labs
* [LLM Evaluation with Opik](https://www.comet.com/site/llm-course/) - free Hands-on labs
* [Advanced Machine Learning](https://www.trainindata.com/p/advanced-machine-learning) - $ intermediate and advanced courses
* [IIT Bombay e-Postgraduate Diploma in Artificial Intelligence and Data Science](https://www.mygreatlearning.com/iit-bombay-pg-diploma-ai-data-science) - Online postgraduate diploma covering artificial intelligence, machine learning and data science - $
* [PixelBank](https://pixelbank.dev/learn) - free and $ Interactive courses (ML, computer vision, 3D vision, LLMs, GPU programming) with 1,100+ coding problems for implementing algorithms from scratch

View File

@ -3,4 +3,5 @@ The following is a list of professional events on Machine Learning and Artificia
## Machine Learning and Artificial Intelligence
* [AI & ML Events](https://aiml.events) - The best upcoming hand-picked conferences and exhibitions in the field of artificial intelligence and machine learning
* [Codementor Events](https:///www.codementor.io/events) - The best developer-focused free virtual events platform, ranging from technical to career related topics
* [Codementor Events](https://www.codementor.io/events) - The best developer-focused free virtual events platform, ranging from technical to career related topics
* [Mimetic Events](https://events.trymimetic.com) - Calendar of AI conferences, meetups and hackathons in San Francisco, New York, Los Angeles and other cities, updated daily