domain: machine-learning
3991 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| bentoml/BentoML BentoML is a Python framework for building online serving systems for AI apps and model inference, turning model inference scripts into RES… | 94 | 8808 | stable |
| DepthAnything/Depth-Anything-V2 Depth Anything V2 is a foundation model for monocular depth estimation, trained on 595K synthetic labeled images and 62M+ real unlabeled im… | 56 | 8709 | stable |
| VowpalWabbit/vowpal_wabbit Vowpal Wabbit is a fast, open-source machine learning system focused on online, active, and interactive learning, including contextual band… | 90 | 8706 | active |
| bayesian-optimization/BayesianOptimization A pure Python library implementing Bayesian global optimization using Gaussian processes. It finds the maximum of expensive, unknown black-… | 90 | 8696 | stable |
| LykosAI/StabilityMatrix Stability Matrix is a multi-platform desktop application that acts as a package manager for Stable Diffusion UIs and tools like ComfyUI, AU… | 95 | 8688 | active |
| MONAI MONAI is a PyTorch-based open-source framework for deep learning in healthcare imaging, providing domain-specific transforms, 3D architectu… | 87 | 8634 | stable |
| jomjol/AI-on-the-edge-device A firmware application for ESP32-CAM boards that uses TensorFlow Lite CNNs on-device to digitize analog utility meters (water, gas, electri… | 72 | 8624 | active |
| librosa/librosa Librosa is a Python library for audio and music signal processing, providing foundational algorithms for building music information retriev… | 87 | 8576 | stable |
| google-deepmind/alphafold3 Google DeepMind's official implementation of the AlphaFold 3 inference pipeline for predicting biomolecular structures and interactions. It… | 83 | 8495 | active |
| OptimalScale/LMFlow LMFlow is an extensible Python toolkit for finetuning and inference of large foundation models such as LLaMA, GPT-2, and Galactica. It prov… | 64 | 8484 | active |
| bitsandbytes-foundation/bitsandbytes bitsandbytes is a Python library providing k-bit quantization primitives for PyTorch, enabling 8-bit (LLM.int8()) and 4-bit (QLoRA) quantiz… | 99 | 8439 | active |
| lucidrains/imagen-pytorch A PyTorch implementation of Imagen, Google's text-to-image neural network based on cascading DDPMs conditioned on T5 text embeddings. It pr… | 23 | 8424 | active |
| 0xPlaygrounds/rig Rig is a Rust library for building modular, scalable LLM-powered applications and agents, offering a unified API across 20+ model providers… | 86 | 8415 | active |
| CASIA-LMC-Lab/FastSAM FastSAM is a CNN-based Segment Anything Model trained on only 2% of the SA-1B dataset, achieving comparable segmentation performance to SAM… | 19 | 8401 | active |
| nl8590687/ASRT_SpeechRecognition ASRT is a deep-learning-based Chinese speech recognition (speech-to-text) system built with TensorFlow/Keras, using CNN, LSTM, attention me… | 57 | 8383 | active |
| jesse-ai/jesse Jesse is an open-source Python framework for researching, backtesting, optimizing, and live-trading cryptocurrency trading strategies. It i… | 77 | 8380 | active |
| FlashML-org/FreeToken FreeToken is an edge-native Mixture-of-Experts (MoE) LLM serving engine that runs frontier-scale open-weight models on consumer hardware by… | 68 | 8370 | active |
| qualcomm/GenieX GenieX is an on-device generative AI inference runtime for Qualcomm Snapdragon devices, running frontier LLMs and VLMs on the Hexagon NPU, … | 85 | 8326 | active |
| py-why/dowhy DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. It unifies causal graphic… | 76 | 8282 | stable |
| mikel-brostrom/boxmot BoxMOT is a pluggable Python and C++ library providing state-of-the-art multi-object tracking (MOT) algorithms such as ByteTrack, BoT-SORT,… | 95 | 8281 | active |
| THUDM/slime slime is an open-source LLM post-training framework for reinforcement learning scaling, connecting Megatron-based training with SGLang-base… | 80 | 8261 | active |
| lmcinnes/umap UMAP is a Python library implementing Uniform Manifold Approximation and Projection, a non-linear dimensionality reduction technique usable… | 87 | 8255 | stable |
| google-research/bert Google Research's official TensorFlow implementation of BERT, the Bidirectional Encoder Representations from Transformers language model, a… | 10 | 40046 | maintenance |
| jessevig/bertviz BertViz is an interactive Python library for visualizing attention mechanisms in Transformer language models such as BERT, GPT-2, and RoBER… | 50 | 8160 | stable |
| elder-plinius/OBLITERATUS OBLITERATUS is a Python toolkit for abliteration — identifying and removing refusal behaviors from large language models by locating and in… | 71 | 8056 | active |
| shenweichen/DeepCTR DeepCTR is a Python library of easy-to-use, modular, and extendible deep-learning based CTR (click-through rate) prediction models built on… | 77 | 8050 | stable |
| LibrePhotos/librephotos LibrePhotos is a self-hosted, open-source photo management service built with Django and React. It offers AI-powered features like face rec… | 96 | 8049 | active |
| asg017/sqlite-vec sqlite-vec is a vector search extension for SQLite written in pure C with no dependencies, supporting float, int8, and binary vectors in ve… | 76 | 8046 | active |
| InternLM/lmdeploy LMDeploy is a toolkit for compressing, quantizing, deploying, and serving large language models, built around its high-performance TurboMin… | 95 | 8024 | active |
| nadermx/backgroundremover A free, open-source command line tool that removes backgrounds from images and videos using the U2Net AI model built on PyTorch. It is inst… | 93 | 8020 | active |
| lanpa/tensorboardX A Python library for writing TensorBoard event files from PyTorch, Chainer, MXNet, NumPy, and other frameworks without needing TensorFlow. … | 78 | 7998 | active |
| Upsonic/Upsonic Upsonic is a Python framework for building autonomous and traditional AI agents, with support for tools, memory, knowledge bases, RAG, mult… | 77 | 7948 | active |
| MochiDiffusion/MochiDiffusion A native macOS app built with SwiftUI for running Stable Diffusion and FLUX.2 Klein image generation locally on Apple Silicon Macs. It uses… | 78 | 7926 | active |
| NVIDIA/Isaac-GR00T NVIDIA Isaac GR00T N1.7 is an open vision-language-action (VLA) foundation model for generalized humanoid robot skills, taking language and… | 76 | 7926 | stable |
| TheLastBen/fast-stable-diffusion A collection of Google Colab notebooks for quickly running Stable Diffusion UIs (AUTOMATIC1111, ComfyUI) and training DreamBooth models for… | 57 | 7910 | active |
| alirezamika/autoscraper AutoScraper is a Python library that automatically learns scraping rules from a URL or HTML content plus a list of sample data you want to … | 66 | 7904 | stable |
| pinokiocomputer/pinokio Pinokio is a desktop application that acts as a one-click launcher and browser for open-source AI apps, letting users discover, install, ru… | 91 | 7878 | active |
| stanfordnlp/stanza Stanza is the Stanford NLP Group's official Python library for linguistic analysis of human language text. It provides a neural pipeline bu… | 97 | 7867 | stable |
| PriorLabs/TabPFN TabPFN is a pre-trained tabular foundation model (transformer) that performs classification, regression, forecasting, and anomaly detection… | 99 | 7855 | active |
| open-mmlab/mmpose MMPose is an open-source pose estimation toolbox and benchmark built on PyTorch as part of the OpenMMLab ecosystem. It provides implementat… | 39 | 7855 | active |
| evidentlyai/evidently Evidently is an open-source Python framework for evaluating, testing, and monitoring ML and LLM-powered systems, with 100+ built-in metrics… | 89 | 7849 | active |
| wang-xinyu/tensorrtx A C++ collection of popular deep learning networks (YOLO variants, ResNet, MobileNet, Swin Transformer, OCR models, and more) implemented f… | 76 | 7827 | active |
| MaartenGr/BERTopic BERTopic is a Python library for topic modeling that leverages transformer-based sentence embeddings and class-based TF-IDF (c-TF-IDF) to d… | 77 | 7804 | stable |
| Blaizzy/mlx-audio MLX-Audio is a Python library built on Apple's MLX framework for fast text-to-speech (TTS), speech-to-text (STT), and speech-to-speech (STS… | 88 | 7793 | active |
| openai/gym Gym is a Python toolkit for developing and comparing reinforcement learning algorithms via a standard API between learning algorithms and e… | 10 | 37251 | maintenance |
| alteryx/featuretools Featuretools is an open-source Python library for automated feature engineering, using Deep Feature Synthesis (DFS) to generate features fr… | 65 | 7666 | active |
| myshell-ai/MeloTTS MeloTTS is a high-quality multi-lingual text-to-speech library supporting English (multiple accents), Spanish, French, Chinese, Japanese, a… | 16 | 7608 | active |
| google-deepmind/weathernext Google DeepMind's WeatherNext family of AI weather forecasting models, including WeatherNext 2, GraphCast, and GenCast, with code and pretr… | 82 | 7596 | active |
| OpenMathLib/OpenBLAS OpenBLAS is an optimized open-source implementation of the BLAS (Basic Linear Algebra Subprograms) library, based on GotoBLAS2, with LAPACK… | 93 | 7563 | stable |
| HIPS/autograd Autograd is a Python library that efficiently computes derivatives of native Python and NumPy code, supporting reverse-mode (backpropagatio… | 85 | 7523 | stable |
| Kaggle/kaggle-cli The official Kaggle command-line interface for interacting with Kaggle competitions, datasets, models, notebooks, and discussion forums. It… | 97 | 7511 | active |
| h2oai/h2o-3 H2O-3 is an open-source, distributed, in-memory machine learning platform implementing algorithms such as GLM, GBM/XGBoost, Random Forest, … | 77 | 7494 | stable |
| hybridgroup/gocv GoCV is a Go language binding for the OpenCV 4 computer vision library, supporting Linux, macOS, Windows, and Docker. It includes support f… | 76 | 7491 | active |
| EleutherAI/gpt-neox GPT-NeoX is EleutherAI's library for training large-scale autoregressive transformer language models on GPUs, built on NVIDIA's Megatron an… | 62 | 7459 | active |
| LargeWorldModel/LWM Large World Model (LWM) is a family of open-source 7B-parameter multimodal autoregressive transformer models trained on long videos and boo… | 25 | 7425 | active |
| apple/ml-fastvlm Official implementation of FastVLM, a vision language model with an efficient hybrid vision encoder (FastViTHD) that reduces token count an… | 28 | 7411 | active |
| facebookresearch/SlowFast PySlowFast is a PyTorch-based open-source video understanding codebase from Facebook AI Research (FAIR). It provides implementations of sta… | 65 | 7410 | active |
| open-compass/opencompass OpenCompass is a Python-based evaluation platform and toolkit for benchmarking large language models across 100+ datasets, supporting model… | 96 | 7365 | active |
| arcee-ai/mergekit mergekit is a Python toolkit for merging pre-trained large language models directly in weight space, supporting many merge methods (SLERP, … | 63 | 7310 | active |
| google/flax Flax is a neural network library and ecosystem for JAX designed for flexibility, featuring the newer NNX API with first-class Python refere… | 99 | 7303 | active |
| naver/dust3r DUSt3R is the official PyTorch implementation of a CVPR 2024 model that performs dense, unconstrained stereo and multi-view 3D reconstructi… | 45 | 7288 | active |
| flyteorg/flyte Flyte is an open-source workflow orchestration platform for coordinating data, ML models, and AI agents at scale, authored in pure Python a… | 95 | 7245 | active |
| liuliu/ccv ccv is a modern, minimalist computer vision library written in C/C++ with an application-driven set of state-of-the-art algorithms includin… | 77 | 7243 | active |
| Alluxio/alluxio Alluxio is an open-source distributed caching and data orchestration platform that sits between compute frameworks (Spark, Presto, Trino, P… | 31 | 7231 | stable |
| feast-dev/feast Feast is an open-source feature store for machine learning that manages offline stores for historical training data and low-latency online … | 99 | 7230 | stable |
| stanfordnlp/GloVe Stanford's C implementation of the GloVe model for training distributed word representations (word embeddings), plus downloadable pre-train… | 38 | 7230 | stable |
| kohya-ss/sd-scripts A collection of Python training, generation, and utility scripts for Stable Diffusion and other image generation models, most widely used f… | 89 | 7210 | active |
| BVLC/caffe Caffe is a fast, modular deep learning framework developed by Berkeley AI Research, focused on convolutional neural networks for vision, sp… | 23 | 34556 | maintenance |
| tensorflow/tensorboard TensorBoard is TensorFlow's visualization toolkit, a suite of web applications for inspecting and understanding machine learning training r… | 88 | 7206 | active |
| PeterL1n/BackgroundMattingV2 Official PyTorch implementation of the CVPR 2021 paper 'Real-Time High-Resolution Background Matting'. It produces state-of-the-art alpha m… | 23 | 7189 | stable |
| CMU-Perceptual-Computing-Lab/openpose OpenPose is a real-time multi-person keypoint detection library that jointly estimates human body, face, hand, and foot keypoints (135 tota… | 23 | 34413 | maintenance |
| scikit-learn-contrib/imbalanced-learn imbalanced-learn is a Python library offering re-sampling techniques (over-sampling, under-sampling, and combinations) for datasets with st… | 83 | 7121 | stable |
| ymcui/Chinese-LLaMA-Alpaca-2 A project releasing Chinese-adapted LLaMA-2 base models and Alpaca-2 instruction-tuned chat models with an extended Chinese vocabulary, inc… | 54 | 7120 | stable |
| yangchris11/samurai SAMURAI is the official implementation of a zero-shot visual object tracker built on top of Segment Anything Model 2 (SAM 2), using a motio… | 27 | 7112 | active |
| rocketride-org/rocketride-server RocketRide is an open-source AI pipeline engine with a high-throughput C++ runtime and 100+ Python-extensible nodes for building, debugging… | 80 | 7090 | active |
| flwrlabs/flower Flower (flwr) is an open-source Python framework for building federated and collaborative AI systems, supporting any ML framework such as P… | 99 | 7085 | active |
| zai-org/GLM-4 Official repository for the GLM-4 series of open-weight, multilingual (primarily Chinese/English) multimodal chat language models from Z.ai… | 67 | 7070 | active |
| tensortrade-org/tensortrade TensorTrade is an open-source Python framework for building, training, and evaluating reinforcement learning agents for algorithmic trading… | 64 | 7067 | active |
| SakanaAI/AI-Scientist-v2 An end-to-end autonomous AI research system that generates hypotheses, runs machine learning experiments, analyzes data, and writes complet… | 46 | 7050 | active |
| deepseek-ai/DeepSpec DeepSpec is a full-stack Python codebase from DeepSeek for training and evaluating draft models used in speculative decoding of large langu… | 54 | 7041 | active |
| NVIDIA/warp NVIDIA Warp is a Python framework that JIT-compiles regular Python functions into efficient CPU or CUDA GPU kernels. It provides differenti… | 98 | 7033 | active |
| google/gemma.cpp A lightweight, standalone C++ inference engine for Google's Gemma foundation models (Gemma 2/3, PaliGemma 2), with a small ~2K LoC core and… | 72 | 7031 | active |
| apple/corenet CoreNet is Apple's deep neural network training toolkit for training standard and novel small and large-scale models, including foundation … | 45 | 7007 | active |
| TheTom/turboquant_plus TurboQuant+ is a Python reference implementation of the TurboQuant KV cache compression method (ICLR 2026), using PolarQuant codebooks and … | 56 | 7006 | active |
| deeppavlov/DeepPavlov DeepPavlov is an open-source Python NLP library built on PyTorch and Hugging Face transformers for developing, training, and deploying stat… | 39 | 6989 | active |
| lance-format/lance Lance is an open lakehouse data format (file format, table format, and catalog spec) for multimodal AI, implemented in Rust with Python and… | 94 | 6973 | active |
| deepchem/deepchem DeepChem is a Python library that democratizes deep learning for drug discovery, quantum chemistry, materials science, and biology. It prov… | 67 | 6961 | active |
| interpretml/interpret InterpretML is a Python library that unifies machine learning interpretability techniques, letting users train inherently interpretable gla… | 91 | 6928 | active |
| leejet/stable-diffusion.cpp A pure C/C++ inference engine for diffusion models (Stable Diffusion, FLUX, Wan, Qwen Image, Z-Image, and more) built on ggml in the style … | 91 | 6846 | active |
| eriklindernoren/ML-From-Scratch A Python library providing bare-bones NumPy implementations of fundamental machine learning models and algorithms, from linear regression t… | 32 | 32528 | maintenance |
| clearml/clearml ClearML is an open-source Python SDK and platform for MLOps/LLMOps that provides auto-logged experiment tracking, data versioning, pipeline… | 99 | 6840 | stable |
| postgresml/postgresml PostgresML is a PostgreSQL extension that brings machine learning and AI inference directly into the database, with GPU acceleration and pg… | 36 | 6821 | active |
| NicolasHug/Surprise Surprise is a Python scikit for building and analyzing recommender systems that work with explicit rating data. It provides ready-to-use pr… | 70 | 6808 | stable |
| ml-explore/mlx-lm A Python package for running and fine-tuning large language models on Apple silicon using the MLX framework. It integrates with the Hugging… | 80 | 6801 | active |
| facebookresearch/fairseq Fairseq is a PyTorch-based sequence modeling toolkit from Facebook AI Research for training custom models for translation, summarization, l… | 10 | 32231 | maintenance |
| simplescaling/s1 s1 is an open-source research project implementing simple test-time scaling for large language models, including the s1K dataset of 1,000 c… | 33 | 6668 | active |
| pathwaycom/arc-task-gen A Python tool that generates original ARC-AGI-1-style puzzle tasks distribution-matched to the public evaluation set. It produces tasks in … | 56 | 6665 | active |
| yangjianxin1/Firefly Firefly is an open-source one-stop training tool for large language models, supporting pretraining, instruction fine-tuning (SFT), and DPO … | 21 | 6653 | active |
| linkedin/Liger-Kernel Liger Kernel is a collection of Triton kernels designed to make LLM training faster and more memory-efficient, offering drop-in replacement… | 90 | 6588 | active |
| ml5js/ml5-library ml5.js is a friendly, beginner-oriented JavaScript machine learning library for the browser, built on top of TensorFlow.js. It provides acc… | 23 | 6587 | active |