domain: machine-learning
3991 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| rhymes-ai/Aria Aria is an open multimodal native Mixture-of-Experts (MoE) model with 25.3B total parameters (3.9B activated per token) and a 64K multimoda… | 23 | 1087 | active |
| ndif-team/nnsight nnsight is a Python library for interpreting and intervening on the internals of deep learning models, built on PyTorch. It lets researcher… | 88 | 1085 | active |
| microsoft/TimeCraft TimeCraft is a diffusion model-based framework for generating high-quality synthetic time series data across domains. It uses learned seman… | 64 | 1085 | active |
| DSE-MSU/DeepRobust DeepRobust is a PyTorch library for adversarial robustness research, providing implementations of attack and defense methods for both image… | 45 | 1085 | active |
| GraphSAGE Reference implementation of the GraphSAGE algorithm for inductive representation learning on large graphs using stochastic graph convolutio… | 32 | 3719 | maintenance |
| bytedance/byteps BytePS is a high-performance parameter server framework for distributed deep neural network training, supporting TensorFlow, Keras, PyTorch… | 10 | 3717 | maintenance |
| GAIR-NLP/LIMO LIMO is a research project and training framework demonstrating that large language models can achieve strong mathematical reasoning with o… | 36 | 1083 | active |
| nihui/rife-ncnn-vulkan A command-line tool implementing RIFE (Real-Time Intermediate Flow Estimation) for video frame interpolation using the ncnn neural network … | 23 | 1083 | active |
| vladmandic/face-api FaceAPI is a JavaScript library built on TensorFlow/JS that provides AI-powered face detection, rotation tracking, face description and rec… | 10 | 1083 | active |
| agi-brain/xuance XuanCe is an open-source Python library of deep reinforcement learning (DRL) and multi-agent reinforcement learning (MARL) algorithm implem… | 95 | 1082 | active |
| google/fully-homomorphic-encryption Google's repository of demos for fully homomorphic encryption (FHE), originally a C++ transpiler and now showcasing the HEIR MLIR-based FHE… | 86 | 3708 | maintenance |
| mlr mlr/mlr3 is a machine learning framework for R providing a unified, object-oriented interface to many learning algorithms. It supports resa… | 95 | 1080 | active |
| GradientHQ/symphony-coord Symphony-Coord is a decentralized multi-agent framework that treats agent selection as an online multi-armed bandit problem, allowing roles… | 54 | 1080 | active |
| charlesq34/pointnet2 Official TensorFlow implementation of PointNet++, a deep neural network that learns hierarchical features on 3D point clouds using metric-s… | 32 | 3700 | maintenance |
| Stonesjtu/pytorch_memlab A Python library providing line-level CUDA memory profiling and tensor inspection tools for PyTorch. It helps debug out-of-memory errors by… | 94 | 1077 | active |
| Geekgineer/YOLOs-CPP YOLOs-CPP is a production-ready, cross-platform C++ inference library for the YOLO model family (v5 through YOLO26), built on ONNX Runtime … | 88 | 1076 | active |
| autonomousvision/navsim NAVSIM is a data-driven pseudo-simulation framework and benchmark for autonomous vehicle planning, evaluating driving agents non-reactively… | 50 | 1076 | active |
| lasgroup/SDPO SDPO (Self-Distilled Policy Optimization) is a research library implementing a reinforcement learning framework for post-training large lan… | 56 | 1075 | active |
| trailofbits/anamorpher Anamorpher is a tool for crafting and visualizing image scaling attacks that hide multi-modal prompt injections in images, revealed only wh… | 55 | 1075 | active |
| openai/glide-text2im Official codebase for GLIDE, a diffusion-based text-conditional image synthesis model from OpenAI. It provides pretrained models and notebo… | 10 | 3684 | maintenance |
| facebookresearch/hiera Hiera is the official PyTorch implementation of a hierarchical vision transformer from Meta AI (ICML 2023 Oral). It achieves state-of-the-a… | 20 | 1074 | active |
| ARM-software/CMSIS-DSP CMSIS-DSP is ARM's optimized embedded compute library providing DSP and math kernels for Cortex-M and Cortex-A processors, including FFT, f… | 96 | 1073 | stable |
| meta-pytorch/monarch Monarch is a distributed programming framework for PyTorch built on scalable actor messaging, with actors grouped into meshes, supervision-… | 80 | 1073 | active |
| OranAi-Ltd/oransim Oransim is an open-source causal digital twin engine for marketing, simulating a large virtual consumer society with LLM-backed personas to… | 56 | 1073 | active |
| zju3dv/InfiniDepth InfiniDepth is a CVPR 2026 research library for monocular depth estimation that represents depth as neural implicit fields, allowing depth … | 53 | 1073 | active |
| facebookresearch/CutLER CutLER is a research codebase from Meta FAIR for training object detection and instance segmentation models without human annotations, usin… | 66 | 1072 | active |
| open-gigaai/giga-train GigaTrain is an efficient and scalable Python training framework for large AI models, supporting distributed multi-GPU/multi-node execution… | 62 | 1072 | active |
| mert-kurttutan/torchview torchview is a Python library that visualizes PyTorch models as visual graphs, showing tensors, modules, torch functions, and input/output … | 54 | 1072 | active |
| ufal/whisper_streaming A Python library that turns Whisper-like speech recognition models into a real-time streaming transcription and translation system using a … | 53 | 3672 | maintenance |
| NVIDIA-Merlin/HugeCTR HugeCTR is a GPU-accelerated deep learning framework from NVIDIA designed for training and inference of large recommender models, especiall… | 77 | 1071 | active |
| LucasAlegre/sumo-rl SUMO-RL is a Python library that provides Gymnasium and PettingZoo-compatible reinforcement learning environments for traffic signal contro… | 55 | 1071 | active |
| sipeed/TinyMaix TinyMaix is a tiny neural network inference library for microcontrollers (TinyML), with core code under 400 lines and a .text section under… | 34 | 1071 | active |
| juntang-zhuang/Adabelief-Optimizer AdaBelief is a deep learning optimizer that adapts step sizes based on the 'belief' in observed gradients, combining Adam's fast convergenc… | 32 | 1070 | stable |
| google-research/football Google Research Football is a reinforcement learning environment based on the open-source Gameplay Football game, created by the Google Bra… | 10 | 3661 | maintenance |
| RL-VIG/LibFewShot LibFewShot is a comprehensive PyTorch library for few-shot learning, implementing many fine-tuning, meta-learning, and metric-learning meth… | 54 | 1069 | active |
| facebookresearch/LASER LASER is a Python library from Facebook Research for computing multilingual, language-agnostic sentence embeddings supporting 200+ language… | 10 | 3660 | maintenance |
| luxonis/depthai DepthAI is Luxonis's Python library and SDK for developing with Luxonis OAK camera hardware, enabling spatial AI and computer vision on emb… | 65 | 1068 | active |
| Fannovel16/ComfyUI-Frame-Interpolation A set of custom nodes for ComfyUI that perform video frame interpolation using models like RIFE, FILM, GMFSS, and others. It lets users gen… | 52 | 1068 | active |
| latorc/MahjongCopilot A desktop AI assistant application for the Majsoul online mahjong game, built on the Mortal model via the MJAI protocol. It provides real-t… | 21 | 1068 | active |
| princeton-nlp/SimCSE SimCSE is a Python library and research codebase implementing simple contrastive learning for sentence embeddings, with pre-trained unsuper… | 23 | 3654 | maintenance |
| guochengqian/PointNeXt PointNeXt is the official PyTorch implementation of the NeurIPS'22 paper that improves PointNet++ via better training and model scaling str… | 93 | 1067 | stable |
| microsoft/Biodiversity Microsoft AI for Good Lab's biodiversity research hub providing open-source AI models and tools for wildlife monitoring and conservation, i… | 88 | 1066 | active |
| IAHispano/Applio Applio is an open-source, MIT-licensed voice conversion suite built on RVC that lets users convert audio into other voices, train custom vo… | 90 | 3644 | maintenance |
| abizovnuralem/go2_omniverse A Python library providing Unitree Go2 and G1 robot support for NVIDIA Isaac Lab / Isaac Sim, enabling simulation of these quadruped and hu… | 56 | 1064 | active |
| gangweix/pixel-perfect-depth Pixel-Perfect Depth is a monocular depth estimation model based on pixel-space diffusion transformers that produces flying-pixel-free depth… | 49 | 1064 | active |
| lucidrains/mlp-mixer-pytorch A PyTorch implementation of Google AI's MLP-Mixer, an all-MLP architecture for image classification that uses neither convolutions nor atte… | 48 | 1064 | active |
| abertsch72/unlimiformer Unlimiformer is a method and official implementation for augmenting pretrained encoder-decoder transformers with retrieval-based attention,… | 30 | 1062 | stable |
| NVlabs/SegFormer Official PyTorch implementation of SegFormer, a transformer-based semantic segmentation framework with a hierarchical encoder and lightweig… | 32 | 3629 | maintenance |
| InternRobotics/InternNav InternNav is an open-source PyTorch-based toolbox for building embodied navigation foundation models, supporting vision-language navigation… | 58 | 1061 | active |
| NVIDIA/DreamDojo NVIDIA's official PyTorch codebase for DreamDojo, a generalist robot world model pretrained on 44k hours of human egocentric video and post… | 48 | 1059 | active |
| clovaai/stargan-v2 The official PyTorch implementation of StarGAN v2, a CVPR 2020 paper on diverse image-to-image translation across multiple domains using a … | 32 | 3617 | maintenance |
| mgsalem/Tensorflow-Project-Template A Python project template that provides a recommended folder structure and object-oriented skeleton (base model, base trainer, data loader,… | 32 | 3616 | maintenance |
| bigcode-project/bigcode-evaluation-harness A framework for evaluating autoregressive code generation language models on benchmarks like HumanEval, MBPP, MultiPL-E, and HumanEvalPack.… | 38 | 1058 | active |
| YunYang1994/tensorflow-yolov3 A TensorFlow 1.x implementation of the YOLOv3 real-time object detector, reproducing the 'YOLOv3: An Incremental Improvement' paper. It sup… | 23 | 3614 | maintenance |
| pytorch/torchchat torchchat is a compact PyTorch-native codebase for running large language models locally via Python, a C/C++ runner on desktop/server, or o… | 10 | 3612 | maintenance |
| sb-ai-lab/EmotiEffLib EmotiEffLib (formerly HSEmotion) is a lightweight library for facial emotion and engagement recognition in photos and videos, available in … | 65 | 1057 | active |
| open-gigaai/giga-models GigaModels is an open-source Python framework providing pipelines for training, inference, deployment, and compression of multi-modal, gene… | 62 | 1057 | active |
| henry123-boy/SpaTracker SpatialTracker is the official PyTorch implementation of a CVPR 2024 Highlight paper that tracks any 2D pixels in 3D space from RGB or RGBD… | 41 | 1057 | active |
| alibaba/Alink Alink is a machine learning algorithm platform built on Apache Flink, developed by Alibaba's PAI team. It provides a large library of batch… | 23 | 3611 | maintenance |
| XYZ-AI-Lab/axrl AxisRL is an agentic reinforcement learning post-training framework for large language models, built on SGLang for high-throughput rollout … | 55 | 1056 | active |
| X-LANCE/SLAM-LLM SLAM-LLM is a deep learning toolkit for training custom multimodal large language models focused on speech, language, audio, and music proc… | 55 | 1056 | active |
| apache/singa Apache SINGA is a distributed deep learning platform for training neural networks across multiple devices and machines. It provides a C++ c… | 64 | 3606 | maintenance |
| TeleHuman/PBHC Official implementation of KungfuBot, a physics-based humanoid whole-body control framework for learning highly-dynamic skills like kungfu … | 59 | 1055 | active |
| PreferredAI/cornac Cornac is a Python framework for building and comparing multimodal recommender systems, with convenient support for auxiliary data such as … | 96 | 1053 | active |
| Tencent-Hunyuan/HunyuanVideo-Foley HunyuanVideo-Foley is a multimodal diffusion model from Tencent Hunyuan that generates high-fidelity Foley sound effects synchronized with … | 37 | 1052 | active |
| nmslib/nmslib NMSLIB is a cross-platform C++ similarity search library with Python bindings for efficient k-nearest-neighbor search in generic and non-me… | 57 | 3588 | maintenance |
| cjlin1/liblinear LIBLINEAR is a C++ library and CLI toolset for training large-scale regularized linear classifiers, regressors, and one-class SVMs. It ship… | 59 | 1051 | stable |
| openai/retro Gym Retro is a Python library that turns classic video games into Gym environments for reinforcement learning research, with integrations f… | 10 | 3585 | maintenance |
| drprojects/superpoint_transformer Official PyTorch implementation of Superpoint Transformer (ICCV'23), SuperCluster (3DV'24), and EZ-SP (ICRA'26) for efficient semantic and … | 64 | 1049 | active |
| NeuroTechX/moabb MOABB (Mother of All BCI Benchmarks) is a Python library for reproducible benchmarking of machine-learning algorithms on EEG-based brain-co… | 96 | 1048 | active |
| anuragxel/salt SALT is a Python-based image labeling tool built on Meta AI's Segment Anything Model, providing a barebones GUI for annotating images with … | 30 | 1048 | active |
| RUC-NLPIR/Arbor Arbor is a generalist autonomous research agent that takes a benchmark and a goal, then proposes hypotheses, edits code, and runs real expe… | 78 | 1047 | active |
| arcee-ai/DistillKit DistillKit is an open-source Python toolkit for knowledge distillation of large language models, supporting both online and offline distill… | 60 | 1047 | active |
| onnx/onnx-mlir ONNX-MLIR is a compiler infrastructure built on LLVM/MLIR that lowers ONNX neural network graphs into executable code, MLIR files, LLVM byt… | 86 | 1046 | active |
| Xilinx/finn FINN is an open-source dataflow compiler from AMD/Xilinx that generates highly efficient FPGA accelerators for quantized neural network (QN… | 68 | 1046 | active |
| facebookresearch/pytorchvideo PyTorchVideo is a deep learning library from Facebook Research focused on video understanding research, built on PyTorch. It provides reusa… | 59 | 3566 | maintenance |
| nv-tlabs/PiD PiD is a plug-and-play pixel diffusion decoder from NVIDIA that replaces VAE/RAE decoders, decoding latent representations directly into hi… | 56 | 1045 | active |
| k2-fsa/ZipVoice ZipVoice is a series of fast, high-quality zero-shot text-to-speech models based on flow matching, with a compact 123M-parameter Zipformer-… | 43 | 1045 | active |
| limbo018/DREAMPlace DREAMPlace is a GPU-accelerated VLSI placement tool that reformulates placement as a deep-learning-like optimization using PyTorch. It supp… | 74 | 1044 | active |
| airbnb/chronon Chronon is an open-source data platform from Airbnb for computing, backfilling, and serving ML features. It handles batch and streaming fea… | 75 | 1043 | active |
| Shawn1993/cnn-text-classification-pytorch A PyTorch implementation of Kim's CNN architecture for sentence classification, reproducing results from the paper 'Convolutional Neural Ne… | 65 | 1043 | active |
| ZhengYinan-AIR/Diffusion-Planner Official PyTorch implementation of Diffusion Planner, an ICLR 2025 Oral paper using a DiT-based diffusion model for closed-loop autonomous … | 53 | 1043 | active |
| scrya-com/rotorquant RotorQuant is a KV cache compression method for LLM inference that replaces full d×d orthogonal rotations with block-diagonal Clifford roto… | 50 | 1043 | active |
| jiachenzhu/DyT Official PyTorch implementation of DynamicTanh (DyT), a learnable element-wise tanh operation that replaces normalization layers in Transfo… | 26 | 1043 | active |
| zju3dv/EfficientLoFTR Efficient LoFTR is a PyTorch implementation of a semi-dense local feature matching model that matches keypoints between image pairs with sp… | 40 | 1042 | active |
| PetarV-/GAT Reference implementation of Graph Attention Networks (GAT), the ICLR 2018 model by Veličković et al., written in TensorFlow 1.x with a mini… | 32 | 3548 | maintenance |
| thuiar/MMSA MMSA is a unified Python framework for multimodal sentiment analysis, supporting 15 MSA models and datasets like MOSI, MOSEI, and CH-SIMS. … | 23 | 1041 | active |
| ml-tooling/ml-workspace ML Workspace is an all-in-one web-based IDE Docker image specialized for machine learning and data science. It bundles Jupyter, JupyterLab,… | 23 | 3544 | maintenance |
| tonbistudio/turboquant-pytorch A from-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) algorithm for compressing LLM key-value caches, including an impro… | 50 | 1040 | active |
| tensorflow/minigo Minigo is an open-source, minimalist implementation of the AlphaGo Zero algorithm for the game of Go, built on TensorFlow. It provides a re… | 10 | 3542 | maintenance |
| datamllab/rlcard RLCard is a Python toolkit for reinforcement learning research in card games, providing environments for Blackjack, Leduc Hold'em, Texas Ho… | 23 | 3540 | maintenance |
| cvxopt/cvxopt CVXOPT is a free Python package for convex optimization, providing dense and sparse matrix classes, interfaces to BLAS/LAPACK/FFTW, and sol… | 64 | 1039 | stable |
| lkeab/gaussian-grouping Gaussian Grouping extends 3D Gaussian Splatting to jointly reconstruct and segment open-world 3D scenes by lifting 2D SAM masks into per-Ga… | 27 | 1039 | stable |
| NVIDIA/raft NVIDIA RAFT (Reusable Accelerated Functions and Tools) is a C++/Python library of CUDA-accelerated algorithms and primitives for machine le… | 94 | 1038 | active |
| allenv0/AirPosture AirPosture is an open-source iOS app that turns AirPods (and compatible Beats) with dynamic head tracking into a real-time posture coach, s… | 60 | 1037 | active |
| TorchEnsemble-Community/Ensemble-Pytorch A unified ensemble learning framework for PyTorch that implements strategies like voting, bagging, and gradient boosting to improve deep le… | 23 | 1037 | active |
| pytorch/tensordict TensorDict is a PyTorch library providing a batched, nested dict-like tensor container where operations like slicing, stacking, and arithme… | 99 | 1036 | active |
| google/ml_collections ML Collections is a Python library providing dict-like data structures (ConfigDict and FrozenConfigDict) for managing ML experiment and mod… | 67 | 1036 | stable |
| TIGER-AI-Lab/verl-tool VerlTool is a unified, extensible framework built on verl for training LLM agents with tool use via reinforcement learning. It decouples ac… | 66 | 1036 | active |
| Justin62628/Squirrel-RIFE A Chinese-language Windows GUI application for video frame interpolation based on the RIFE algorithm, with NCNN/Vulkan GPU acceleration. It… | 23 | 3526 | maintenance |