domain: machine-learning
3991 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| ByteDance-Seed/VeOmni VeOmni is a PyTorch-native framework for single- and multi-modal model pre-training and post-training, with a modular, trainer-free design … | 82 | 2173 | active |
| MoonshotAI/MoBA MoBA (Mixture of Block Attention) is a PyTorch implementation of a trainable block-sparse attention mechanism for long-context large langua… | 27 | 2169 | active |
| google-deepmind/mujoco_playground MuJoCo Playground is an open-source Python library of GPU-accelerated robot learning environments built on MuJoCo MJX and MuJoCo Warp. It s… | 76 | 2168 | active |
| yatengLG/ISAT_with_segment_anything ISAT_with_segment_anything is an interactive semi-automatic image annotation tool built on the Segment Anything Model family (SAM, SAM2, SA… | 84 | 2166 | active |
| withcatai/node-llama-cpp node-llama-cpp is a Node.js library providing bindings to llama.cpp for running LLMs locally, with pre-built binaries and automatic GPU sup… | 93 | 2162 | active |
| facebookresearch/mae A PyTorch/GPU re-implementation of the Masked Autoencoders (MAE) paper for self-supervised vision learning. It includes pre-training code, … | 10 | 8370 | maintenance |
| galilai-group/stable-worldmodel A Python library providing a unified platform for reproducible world model research, covering data collection, training, and evaluation via… | 81 | 2156 | active |
| google/gin-config Gin-config is a lightweight Python configuration framework based on dependency injection. Functions or classes decorated with @gin.configur… | 63 | 2155 | stable |
| TsingZ0/PFLlib PFLlib is a beginner-friendly Python library and benchmark for traditional and personalized federated learning, offering 39 algorithms, 24 … | 59 | 2155 | active |
| NannyML/nannyml NannyML is an open-source Python library for post-deployment machine learning monitoring. It estimates model performance without access to … | 40 | 2150 | active |
| google-deepmind/pysc2 PySC2 is DeepMind's Python component of the StarCraft II Learning Environment, exposing Blizzard's StarCraft II Machine Learning API as a P… | 23 | 8307 | maintenance |
| google/trax Trax is an end-to-end deep learning library built on JAX and TensorFlow that focuses on clear code and speed, developed and maintained by t… | 10 | 8306 | maintenance |
| rupeshs/fastsdcpu FastSD CPU is a Python application that runs Stable Diffusion image generation quickly on CPUs and Intel AI PCs using Latent Consistency Mo… | 78 | 2143 | active |
| ViTAE-Transformer/ViTPose Official PyTorch implementation of ViTPose and ViTPose++, Vision Transformer models for human and generic body pose estimation from NeurIPS… | 59 | 2138 | stable |
| utkuozbulak/pytorch-cnn-visualizations A PyTorch library implementing a wide range of convolutional neural network visualization and interpretability techniques, including Grad-C… | 32 | 8233 | maintenance |
| cvxpy/cvxpylayers CVXPYlayers is a Python library for constructing differentiable convex optimization layers in PyTorch, JAX, and MLX using CVXPY. It solves … | 87 | 2126 | active |
| hexo-ai/sia SIA is a Python framework implementing a self-improving AI loop in which a Meta-Agent generates a task-specific Target Agent and a Feedback… | 59 | 2123 | active |
| yyfz/Pi3 Pi3 (π³) is a feed-forward neural network for visual geometry reconstruction that eliminates the need for a fixed reference view, using a p… | 59 | 2122 | active |
| autonomousvision/sdfstudio SDFStudio is a unified and modular framework for neural implicit surface reconstruction built on top of nerfstudio. It provides unified imp… | 31 | 2120 | active |
| fastmachinelearning/hls4ml hls4ml is a Python package that converts machine learning models from Keras, PyTorch, and ONNX into high-level synthesis (C++) code for FPG… | 82 | 2114 | active |
| deepspeedai/DeepSpeed-MII DeepSpeed-MII is a Python library for high-throughput, low-latency large language model inference, built on DeepSpeed. It provides blocked … | 43 | 2111 | active |
| fangwei123456/spikingjelly SpikingJelly is an open-source deep learning framework for Spiking Neural Networks (SNNs) built on PyTorch. It provides a beginner-friendly… | 77 | 2110 | active |
| automl/auto-sklearn auto-sklearn is an automated machine learning (AutoML) toolkit that acts as a drop-in replacement for scikit-learn estimators, automaticall… | 63 | 8126 | maintenance |
| akfamily/akquant AKQuant is a high-performance quantitative research and backtesting framework with a Rust core engine and Python interface for strategy dev… | 78 | 2095 | active |
| patrick-kidger/diffrax Diffrax is a JAX-based library providing numerical differential equation solvers for ODEs, SDEs, and CDEs. It is fully autodifferentiable a… | 80 | 2089 | active |
| ContinualAI/avalanche Avalanche is an end-to-end continual learning library built on PyTorch, developed by ContinualAI. It provides modules for benchmarks, train… | 27 | 2088 | active |
| tumuyan/RealSR-NCNN-Android An Android application for image super-resolution and upscaling built on NCNN and MNN inference engines, bundling models like RealSR, Real-… | 84 | 2087 | active |
| DepthAnything/Video-Depth-Anything Video Depth Anything is a transformer-based monocular depth estimation model for arbitrarily long videos, built on Depth Anything V2. It pr… | 41 | 2087 | active |
| vitoplantamura/OnnxStream A lightweight C++ inference library for ONNX models that streams weights to run large models in very little memory, accelerated by XNNPACK.… | 59 | 2086 | active |
| NanoNets/docext docext is an on-premises document intelligence toolkit powered by vision-language models, offering OCR-free structured data extraction, PDF… | 50 | 2085 | active |
| marlbenchmark/on-policy The official PyTorch implementation of Multi-Agent PPO (MAPPO), an on-policy reinforcement learning algorithm for cooperative multi-agent s… | 32 | 2085 | active |
| facebookresearch/ai4animationpy AI4AnimationPy is a Python framework for AI-driven character animation using neural networks, providing motion capture processing, training… | 59 | 2078 | active |
| roboterax/humanoid-gym Humanoid-Gym is a reinforcement learning framework built on Nvidia Isaac Gym for training locomotion skills in humanoid robots, with emphas… | 27 | 2075 | active |
| uber/orbit Orbit is a Python package for Bayesian time series forecasting and inference with an initialize-fit-predict interface. It uses probabilisti… | 83 | 2069 | stable |
| facebookresearch/ConvNeXt-V2 Official PyTorch implementation of ConvNeXt V2, a family of pure convolutional neural network models co-designed with a fully convolutional… | 10 | 2069 | stable |
| intel/openvino-plugins-ai-audacity A set of AI-enabled effects, generators, and analyzers for Audacity, powered by Intel OpenVINO running fully locally on CPU, GPU, or NPU. I… | 73 | 2066 | active |
| sunnypilot/sunnypilot sunnypilot is an open-source driver assistance system forked from comma.ai's openpilot, providing adaptive cruise control, automated lane c… | 98 | 2065 | active |
| brightmart/text_classification A collection of deep learning baseline models for text classification in NLP, implemented in TensorFlow. It covers classic architectures li… | 32 | 7940 | maintenance |
| facebookresearch/theseus Theseus is a PyTorch-based library for building custom differentiable nonlinear optimization layers, supporting problems in robotics and vi… | 23 | 2055 | active |
| marcoslucianops/DeepStream-Yolo A collection of configuration files, parsers, and conversion utilities for running YOLO-family object detection models on NVIDIA DeepStream… | 61 | 2054 | active |
| WenjieDu/PyPOTS PyPOTS is a Python toolbox for machine learning and data mining on partially-observed time series with missing values. It integrates 50+ st… | 93 | 2051 | active |
| ricky0123/vad A JavaScript/TypeScript library that runs Silero VAD via ONNX Runtime Web to detect voice activity directly in the browser. It provides a s… | 69 | 2043 | active |
| Cloud-CV/EvalAI EvalAI is an open-source platform for evaluating and comparing machine learning and AI algorithms at scale. It provides a central leaderboa… | 67 | 2039 | active |
| bytedance/Protenix Protenix is an open-source PyTorch reproduction of AlphaFold 3 for high-accuracy biomolecular structure prediction, covering proteins, nucl… | 79 | 2038 | active |
| emilianavt/OpenSeeFace OpenSeeFace is a robust realtime face and facial landmark tracking library that runs on CPU at 30-60 fps using ONNX-converted MobileNetV3 m… | 49 | 2038 | active |
| jeshraghian/snntorch snnTorch is a Python library for gradient-based deep learning with spiking neural networks, built as an extension of PyTorch. It provides s… | 67 | 2036 | active |
| pykeen/pykeen PyKEEN is a Python library for training and evaluating multimodal knowledge graph embedding models built on PyTorch. It provides a high-lev… | 70 | 2032 | active |
| n00mkrad/flowframes Flowframes is a Windows GUI application for AI-based video frame interpolation, supporting RIFE (Pytorch & NCNN), DAIN (NCNN), and FLAVR (P… | 70 | 2030 | active |
| noamgat/lm-format-enforcer A Python library that enforces output formats like JSON Schema or regex on language models by filtering allowed tokens at each generation s… | 64 | 2029 | active |
| tensorflow/recommenders TensorFlow Recommenders is a Python library for building recommender system models on top of TensorFlow and Keras. It covers the full workf… | 84 | 2027 | active |
| tensorflow/privacy TensorFlow Privacy is a Python library providing TensorFlow optimizers for training machine learning models with differential privacy. It i… | 67 | 2026 | active |
| 0xShug0/audio.cpp audio.cpp is a pure C++ inference engine for audio models built on ggml, supporting TTS, STT, VAD, voice conversion, music generation, and … | 80 | 2022 | active |
| juanmc2005/diart Diart is a Python framework for building AI-powered real-time audio applications, best known for state-of-the-art streaming speaker diariza… | 62 | 2022 | active |
| NUS-HPC-AI-Lab/VideoSys VideoSys is an open-source Python library providing easy and efficient infrastructure for video generation, supporting training, inference,… | 45 | 2022 | active |
| deepmodeling/deepmd-kit DeePMD-kit is a deep learning package for building many-body potential energy representations and running molecular dynamics simulations. I… | 95 | 2021 | stable |
| SakanaAI/continuous-thought-machines The Continuous Thought Machine (CTM) is a neural network architecture from Sakana AI that uses neuron-level temporal dynamics and neural sy… | 46 | 2019 | active |
| tdrussell/diffusion-pipe A Python training script for fine-tuning diffusion models (image and video generation) using DeepSpeed pipeline parallelism across multiple… | 67 | 2015 | active |
| cambrian-mllm/cambrian Cambrian-1 is a fully open family of vision-centric multimodal large language models (MLLMs) from NYU's VISIONx group, with training and ev… | 47 | 2013 | active |
| philipperemy/keras-tcn A Keras/TensorFlow implementation of Temporal Convolutional Networks (TCN) with dilated causal convolutions, usable as a drop-in layer alte… | 62 | 2012 | active |
| tatsu-lab/alpaca_eval AlpacaEval is an LLM-based automatic evaluation framework for instruction-following language models, producing win rates against a GPT-4 ba… | 36 | 2012 | active |
| uncertainty-toolbox/uncertainty-toolbox A Python library for predictive uncertainty quantification, providing metrics, visualizations, and recalibration procedures for regression … | 27 | 2012 | active |
| lyhue1991/torchkeras torchkeras is a lightweight PyTorch model training template library that brings Keras-style compile/fit/evaluate APIs to PyTorch. Its core … | 55 | 2009 | active |
| AntixK/PyTorch-VAE A collection of Variational Autoencoder (VAE) model implementations in PyTorch, including Beta-VAE, VQ-VAE, IWAE, WAE, and others, with a f… | 38 | 7665 | maintenance |
| kohya-ss/musubi-tuner Musubi Tuner is a set of Python scripts for training LoRA (Low-Rank Adaptation) adapters for video and image generation model architectures… | 85 | 2002 | active |
| bytetriper/RAE Official PyTorch implementation of 'Diffusion Transformers with Representation Autoencoders' (RAE), a two-stage image generation pipeline u… | 48 | 2001 | active |
| apple/coreai-models Apple's repository of model export recipes, Python primitives, and Swift runtime utilities for building on-device AI with the Core AI frame… | 67 | 1999 | active |
| mil-tokyo/webdnn WebDNN is a framework for running deep neural network inference directly in the web browser, accepting ONNX models without Python preproces… | 65 | 1999 | active |
| DEIM DEIMv2 is a real-time object detection framework that extends the DEIM DETR family with DINOv3-pretrained and distilled backbones plus a Sp… | 62 | 1999 | active |
| jianchang512/vocal-separate A minimal local web-based tool for separating vocals from background music in audio or video files, using Spleeter 2stems/4stems/5stems mod… | 10 | 1998 | active |
| elyra-ai/elyra Elyra is a set of AI-centric extensions for JupyterLab, including a visual pipeline editor for building and executing notebook-based pipeli… | 68 | 1996 | active |
| clementchadebec/benchmark_VAE Pythae is a PyTorch library that unifies implementations of many Variational Autoencoder (VAE) variants under a common interface, enabling … | 23 | 1995 | active |
| facebookresearch/dino PyTorch implementation of DINO, a self-supervised learning method for training Vision Transformers, with pretrained model weights. It is th… | 10 | 7611 | maintenance |
| lightseekorg/tokenspeed TokenSpeed is a high-performance LLM inference engine designed for agentic workloads, aiming for TensorRT-LLM-level performance with vLLM-l… | 68 | 1989 | active |
| Morizeyao/GPT2-Chinese A Python library providing GPT-2 training and text generation code tailored for Chinese, built on HuggingFace Transformers with BERT or BPE… | 32 | 7597 | maintenance |
| Hyperopt Hyperopt is a Python library for distributed asynchronous hyperparameter optimization over search spaces with real-valued, discrete, and co… | 86 | 7592 | maintenance |
| chaidiscovery/chai-lab Chai-1 is a state-of-the-art multi-modal foundation model for biomolecular structure prediction, handling proteins, small molecules, DNA, R… | 65 | 1986 | active |
| featureform/featureform Featureform is a virtual feature store that sits atop your existing data infrastructure and orchestrates it to define, manage, and serve ML… | 36 | 1985 | active |
| antirez/iris.c Iris is a pure C inference pipeline that generates images from text prompts using open-weights diffusion transformer models like FLUX.2 Kle… | 46 | 1983 | active |
| hkchengrex/XMem XMem is a PyTorch model for semi-supervised video object segmentation that tracks objects through long videos using an Atkinson-Shiffrin-in… | 23 | 1983 | stable |
| kwuking/TimeMixer Official PyTorch implementation of TimeMixer, an ICLR 2024 model for time series forecasting using decomposable multiscale mixing. It has s… | 46 | 1981 | active |
| davda54/sam An unofficial PyTorch implementation of Sharpness-Aware Minimization (SAM) and its adaptive variant ASAM, provided as an optimizer wrapper … | 32 | 1980 | stable |
| patrikhuber/eos A lightweight, header-only 3D Morphable Face Model (3DMM) fitting library written in modern C++11/14, with Python bindings. It provides mod… | 31 | 1980 | active |
| cloneofsimo/lora A Python library for applying Low-Rank Adaptation (LoRA) to quickly fine-tune text-to-image diffusion models like Stable Diffusion. It prod… | 22 | 7550 | maintenance |
| adobe-research/custom-diffusion Custom Diffusion is a research codebase for efficiently fine-tuning text-to-image diffusion models like Stable Diffusion on a few example i… | 69 | 1978 | stable |
| Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB An ultra-lightweight face detection model (~1MB FP32, ~300KB quantized) designed for edge computing devices, with slim and RFB variants tra… | 32 | 7542 | maintenance |
| PrimeIntellect-ai/prime-rl prime-rl is a Python framework for large-scale, fully asynchronous reinforcement learning training of language models, built on FSDP2 for t… | 87 | 1975 | active |
| haykgrigo3/TimeCapsuleLLM TimeCapsuleLLM is a research project training language models from scratch (and fine-tuning small base models) exclusively on text from spe… | 75 | 1975 | active |
| showlab/Show-o Show-o is a research repository implementing a unified transformer model that combines autoregressive and discrete diffusion modeling for m… | 50 | 1973 | active |
| WassimTenachi/PhySO PhySO is a Python library for physical symbolic optimization that uses deep reinforcement learning to discover analytical physical laws fro… | 52 | 1971 | active |
| FireRedTeam/FireRedASR FireRedASR is a family of open-source industrial-grade automatic speech recognition models supporting Mandarin, Chinese dialects, and Engli… | 52 | 1971 | active |
| meta-recsys/generative-recommenders Meta's research library implementing HSTU and M-FALCON from the ICML'24 paper 'Actions Speak Louder than Words: Trillion-Parameter Sequenti… | 69 | 1966 | active |
| fluid-cloudnative/fluid Fluid is a Kubernetes-native distributed dataset orchestrator and accelerator for data-intensive applications such as big data and AI workl… | 79 | 1965 | active |
| Netflix/void-model VOID (Video Object and Interaction Deletion) is a research model from Netflix that removes objects from videos along with the physical inte… | 54 | 1965 | active |
| NVIDIA-NeMo/RL NeMo RL is NVIDIA's open-source post-training library for scaling reinforcement learning methods (GRPO, PPO, DPO, SFT, distillation) on LLM… | 81 | 1961 | active |
| OpenMotionLab/MotionGPT MotionGPT is a unified motion-language model that treats 3D human motion as a foreign language by converting motion into discrete motion to… | 32 | 1961 | active |
| 2U1/Qwen-VL-Series-Finetune An open-source Python repository providing training scripts for fine-tuning Alibaba's Qwen-VL series of vision-language models (Qwen2-VL, Q… | 67 | 1960 | active |
| CannyLab/tsne-cuda A CUDA-accelerated implementation of the FIt-SNE t-SNE algorithm with Python bindings, offering up to 1200x speedup over scikit-learn. It e… | 95 | 1957 | stable |
| kadirnar/whisper-plus A Python library wrapping OpenAI Whisper-family models (including distil-whisper and MLX variants) for fast speech-to-text transcription wi… | 60 | 1956 | active |
| alibaba/EasyCV EasyCV is an all-in-one PyTorch-based computer vision toolkit from Alibaba covering self-supervised learning, vision transformers, and majo… | 32 | 1954 | active |
| eriklindernoren/PyTorch-YOLOv3 A minimal PyTorch implementation of YOLOv3 supporting training, inference, and evaluation, with compatibility for YOLOv4 and YOLOv7 weights… | 32 | 7440 | maintenance |