Sealbook / Open source / Machine learning & data science

Top open-source machine learning & data science on GitHub

4,679 repositories with 1,000+ stars, ranked by stars. Leading: openclaw, tensorflow, stable-diffusion-webui.

	Repository	Stars	Language	License	Activity
1951	sthalles/SimCLRPyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations	★ 2.5k	Jupyter Notebook	MIT	Stale
1952	fhamborg/news-pleasenews-please - an integrated web crawler and information extractor for news that just works	★ 2.5k	Python	Apache-2.0	Archived
1953	wgsxm/PartCrafter[NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers	★ 2.5k	Python	MIT	Slowing
1954	huggingface/evaluate🤗 Evaluate: A library for easily evaluating machine learning models and datasets.	★ 2.5k	Python	Apache-2.0	Active
1955	ipazc/mtcnnMTCNN face detection implementation for TensorFlow, as a PIP package.	★ 2.5k	Jupyter Notebook	MIT	Stale
1956	mckinsey/causalnexA Python library that helps data scientists to infer causation rather than observing correlation.	★ 2.5k	Python	Other	Active
1957	TIBCOSoftware/flogoProject Flogo is an open source ecosystem of opinionated event-driven capabilities to simplify building efficient & modern serverless funct	★ 2.5k	CSS	BSD-3-Clause	Stale
1958	ppogg/YOLOv5-Lite🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~	★ 2.5k	C++	GPL-3.0	Stale
1959	moj-analytical-services/splinkFast, accurate and scalable probabilistic data linkage with support for multiple SQL backends	★ 2.5k	Python	MIT	Active
1960	1sdv/TripStar旅途星辰 (TripStar)是一个创新的 AI 文旅智能体应用，旨在解决用户在规划旅行时面临的各种问题，为提供一站式旅游攻略而生。	★ 2.5k	Vue	GPL-2.0	Active
1961	thuml/AutoformerAbout Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https	★ 2.5k	Jupyter Notebook	MIT	Stale
1962	GaParmar/img2img-turboOne-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more	★ 2.5k	Python	MIT	Stale
1963	dragen1860/MAML-PytorchElegant PyTorch implementation of paper Model-Agnostic Meta-Learning (MAML)	★ 2.5k	Python	MIT	Stale
1964	dickreuter/PokerFully functional Pokerbot that works on PartyPoker, PokerStars and GGPoker, scraping tables with Open-CV (adaptable via gui) or neural netwo	★ 2.5k	Python	GPL-3.0	Stale
1965	microsoft/GraphormerGraphormer is a general-purpose deep learning backbone for molecular modeling.	★ 2.5k	Python	MIT	Active
1966	notAI-tech/NudeNetLightweight nudity detection	★ 2.5k	Python	AGPL-3.0	Slowing
1967	benedekrozemberczki/awesome-decision-tree-papersA collection of research papers on decision, classification and regression trees with implementations.	★ 2.5k	Python	CC0-1.0	Slowing
1968	google/XNNPACKHigh-efficiency floating-point neural network inference operators for mobile, server, and Web	★ 2.5k	C	Other	Active
1969	Lightning-AI/torchmetricsMachine learning metrics for distributed, scalable PyTorch applications.	★ 2.5k	Python	Apache-2.0	Active
1970	jyjblrd/Low-Cost-MocapLow cost motion capture system for room scale tracking	★ 2.5k	TypeScript	MIT	Stale
1971	strasdat/SophusC++ implementation of Lie Groups using Eigen.	★ 2.5k	C++	Other	Stale
1972	nv-tlabs/3dgrutRay tracing and hybrid rasterization of Gaussian particles	★ 2.5k	Python	Apache-2.0	Active
1973	resemble-ai/resemble-enhanceAI powered speech denoising and enhancement	★ 2.5k	Python	MIT	Stale
1974	lgsvl/simulatorA ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles	★ 2.5k	C#	Other	Stale
1975	PizzaDeDados/datascience-pizza🍕 Repositório para juntar informações sobre materiais de estudo em análise de dados e áreas afins, empresas que trabalham com dados e dicion	★ 2.5k	—	MPL-2.0	Stale
1976	yunabe/lgoInteractive Go programming with Jupyter	★ 2.5k	Go	BSD-3-Clause	Stale
1977	kevmo314/magic-copyMagic Copy is a Chrome extension that uses Meta's Segment Anything Model to extract a foreground object from an image and copy it to the cli	★ 2.5k	TypeScript	MIT	Stale
1978	metarank/metarankA low code Machine Learning personalized ranking service for articles, listings, search results, recommendations that boosts user engagement	★ 2.5k	Scala	Apache-2.0	Active
1979	NVlabs/ProtoMotionsProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.	★ 2.5k	Python	Apache-2.0	Active
1980	test-time-training/ttt-video-ditOfficial PyTorch implementation of One-Minute Video Generation with Test-Time Training	★ 2.5k	Python	MIT	Slowing
1981	google-parfait/tensorflow-federatedAn open-source framework for machine learning and other computations on decentralized data.	★ 2.5k	Python	Apache-2.0	Active
1982	benedekrozemberczki/awesome-community-detectionA curated list of community detection research papers with implementations.	★ 2.5k	Python	CC0-1.0	Slowing
1983	volcengine/ai-app-lab	★ 2.5k	JavaScript	Apache-2.0	Active
1984	Jack-Cherish/Deep-Learning:computer:深度学习实战：手写数字识别、Discuz验证码识别、垃圾分类、语义分割	★ 2.5k	Python	—	Stale
1985	lining808/CS-Ebook一个高质量、经典计算机书籍推荐清单，特点为：只收集高质量，各方向经典书籍，不求书多，只求书精。	★ 2.5k	Python	—	Slowing
1986	TorchIO-project/torchioMedical imaging processing for AI applications.	★ 2.5k	Python	Apache-2.0	Active
1987	hawk86104/three-vue-tres🎉一款让你的三维可视化项目快速落地的开源框架，天然具备良好的跨平台与🎊国产化适配能力支持低代码编辑器、Web / 小程序 / App 全端部署，永久免费商用。融合数字孪生、三维可视化（WebGL / WebGPU / three.js / tres.js / tvt.js），	★ 2.4k	JavaScript	Apache-2.0	Active
1988	fossasia/susi_androidSUSI.AI Android App https://play.google.com/apps/testing/ai.susi	★ 2.4k	Kotlin	Apache-2.0	Archived
1989	DorsaRoh/Machine-LearningML from scratch	★ 2.4k	Jupyter Notebook	MIT	Stale
1990	leggedrobotics/darknet_rosYOLO ROS: Real-Time Object Detection for ROS	★ 2.4k	C++	BSD-3-Clause	Stale
1991	github/CodeSearchNetDatasets, tools, and benchmarks for representation learning of code.	★ 2.4k	Jupyter Notebook	MIT	Archived
1992	LyWangPX/Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-SolutionsSolutions of Reinforcement Learning, An Introduction	★ 2.4k	Jupyter Notebook	MIT	Stale
1993	iliane5/meridianMeridian cuts through news noise by scraping hundreds of sources, analyzing stories with AI, and delivering concise, personalized daily brie	★ 2.4k	TypeScript	MIT	Stale
1994	Stability-AI/stability-sdkSDK for interacting with stability.ai APIs (e.g. stable diffusion inference)	★ 2.4k	Jupyter Notebook	MIT	Slowing
1995	aws-samples/aws-machine-learning-university-accelerated-nlpMachine Learning University: Accelerated Natural Language Processing Class	★ 2.4k	Jupyter Notebook	Other	Stale
1996	reiinakano/scikit-plotAn intuitive library to add plotting functionality to scikit-learn objects.	★ 2.4k	Python	MIT	Stale
1997	deeplearningturkiye/turkce-yapay-zeka-kaynaklariTürkiye'de yapılan derin öğrenme (deep learning) ve makine öğrenmesi (machine learning) çalışmalarının derlendiği sayfa.	★ 2.4k	—	MIT	Stale
1998	jameslyons/python_speech_featuresThis library provides common speech features for ASR including MFCCs and filterbank energies.	★ 2.4k	Python	MIT	Stale
1999	amzn/computer-vision-basics-in-microsoft-excelComputer Vision Basics in Microsoft Excel (using just formulas)	★ 2.4k	—	Other	Stale
2000	wolny/pytorch-3dunet3D U-Net model for volumetric semantic segmentation written in pytorch	★ 2.4k	Jupyter Notebook	MIT	Slowing