domain: machine-learning
3991 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| albertan017/LLM4Decompile LLM4Decompile is an open-source series of large language models (1.3B to 33B) trained to decompile binary code back into readable, executab… | 55 | 7020 | active |
| PaddlePaddle/models PaddlePaddle's officially maintained industry-grade model repository containing 600+ models across computer vision, NLP, speech, recommenda… | 23 | 6933 | active |
| open-mmlab/mmdetection3d MMDetection3D is OpenMMLab's next-generation platform for general 3D object detection, built on PyTorch. It provides a modular toolbox with… | 23 | 6524 | active |
| mindee/doctr docTR is a Python OCR library that extracts text from documents and images using a two-stage deep learning approach: text detection followe… | 91 | 6336 | active |
| flashinfer-ai/flashinfer FlashInfer is a GPU kernel library and kernel generator for LLM inference, providing unified APIs for attention, GEMM, and MoE operations w… | 92 | 6326 | active |
| om-ai-lab/VLM-R1 VLM-R1 is a framework for training R1-style large vision-language models using reinforcement learning (GRPO) on top of Qwen2.5-VL. It provi… | 63 | 6018 | active |
| AgentOps-AI/agentops AgentOps is a Python SDK and observability platform for monitoring, debugging, and evaluating AI agents and LLM applications. It auto-instr… | 71 | 5810 | active |
| aidlearning/AidLearning-FrameWork AidLux (originally AidLearning) is an AIoT development platform that runs a native Ubuntu Linux environment with GUI, deep learning tooling… | 69 | 5801 | active |
| open-mmlab/OpenPCDet OpenPCDet is a PyTorch-based open-source toolbox for LiDAR-based 3D object detection. It provides official implementations of models like P… | 52 | 5699 | active |
| lemonade-sdk/lemonade Lemonade is a local AI server that runs optimized LLMs (plus image, speech, and embedding models) on your own GPU and NPU, exposing OpenAI-… | 82 | 5604 | active |
| Vision-CAIR/MiniGPT-4 Official code for MiniGPT-4 and MiniGPT-v2, vision-language models that align a frozen visual encoder with a frozen LLM (Vicuna) via a sing… | 30 | 25619 | maintenance |
| newton-physics/newton Newton is an open-source, GPU-accelerated physics simulation engine built on NVIDIA Warp, targeting roboticists and simulation researchers.… | 87 | 5578 | active |
| karpathy/minGPT A minimal, clean PyTorch re-implementation of OpenAI's GPT covering both training and inference in roughly 300 lines of code. It is designe… | 32 | 24862 | maintenance |
| googleapis/google-cloud-python The official monorepo of idiomatic Python client libraries for Google Cloud Platform services, covering APIs like BigQuery, Storage, AI Pla… | 96 | 5378 | stable |
| ai-dawang/PlugNPlay-Modules A curated collection of plug-and-play deep learning modules (convolutions, attention mechanisms, downsampling, and feature fusion blocks) i… | 38 | 5105 | active |
| harbor-framework/harbor Harbor is a Python framework from the creators of Terminal-Bench for evaluating and optimizing AI agents and language models in containeriz… | 85 | 4905 | active |
| open-mmlab/mmocr MMOCR is OpenMMLab's PyTorch-based toolbox for text detection, recognition, and key information extraction. It provides a model zoo of OCR … | 23 | 4752 | active |
| PrimeIntellect-ai/verifiers verifiers is a Python library for creating environments to train and evaluate large language models with reinforcement learning. It integra… | 88 | 4587 | active |
| TencentARC/InstantMesh InstantMesh is a feed-forward framework for generating 3D meshes from a single image using sparse-view large reconstruction models (LRM/Ins… | 25 | 4516 | active |
| Project-HAMi/HAMi HAMi (Heterogeneous AI Computing Virtualization Middleware) is a CNCF Incubating, Kubernetes-native GPU virtualization and scheduling middl… | 95 | 4492 | active |
| richzhang/PerceptualSimilarity A PyTorch library implementing the LPIPS (Learned Perceptual Image Patch Similarity) metric, which measures perceptual distance between ima… | 23 | 4274 | stable |
| h2oai/wave H2O Wave is a software stack for building realtime, browser-based web applications and dashboards entirely in Python (and R) without HTML, … | 100 | 4253 | active |
| isaac-sim/IsaacSim NVIDIA Isaac Sim is an open-source robotics simulation application built on NVIDIA Omniverse for developing, simulating, and testing AI-dri… | 74 | 4011 | active |
| StuckAtPrototype/Racer An open-source hardware and firmware project for a tiny PCB-based RC car built around the ESP32-H2, including KiCad schematics, gerbers, 3D… | 46 | 3766 | active |
| shitagaki-lab/see-through A research framework from a SIGGRAPH 2026 paper that decomposes a single anime character illustration into up to 23 fully inpainted, semant… | 57 | 3751 | active |
| xinyu1205/recognize-anything Recognize Anything is a collection of open-source image recognition foundation models, including RAM, RAM++, and Tag2Text, that perform ima… | 33 | 3712 | active |
| ZhaoJ9014/face.evoLVe A high-performance face recognition library built on PaddlePaddle and PyTorch, providing comprehensive tools for face-related analytics and… | 37 | 3591 | active |
| AiuniAI/Unique3D Unique3D is the official implementation of a NeurIPS 2024 paper that generates high-quality textured 3D meshes from a single image in about… | 38 | 3582 | active |
| zhaoyingjun/chatbot A Chinese chatbot project that trains conversational models (Seq2Seq and GPT-style, including small SLM variants) on custom corpora with lo… | 52 | 3581 | active |
| alibaba/GraphScope GraphScope is a unified distributed graph computing platform from Alibaba that combines graph analytics (GRAPE), interactive graph queries … | 73 | 3556 | active |
| unitreerobotics/unitree_rl_gym A reinforcement learning gym environment for training locomotion policies on Unitree robots (Go2, H1, H1_2, G1) using Isaac Gym and Mujoco.… | 42 | 3529 | active |
| cszn/KAIR A PyTorch image restoration toolbox providing training and testing code for many restoration models including DnCNN, FFDNet, SRMD, USRNet, … | 23 | 3523 | active |
| NVlabs/Eagle Eagle is NVIDIA's family of frontier vision-language models (Eagle, Eagle 2, Eagle 2.5) built with data-centric training strategies, plus L… | 63 | 3519 | active |
| autorope/donkeycar Donkeycar is an open-source Python library and hardware platform for building small-scale self-driving RC cars with Raspberry Pi or Jetson … | 88 | 3501 | active |
| xororz/local-dream A free, open-source Android app for running Stable Diffusion locally with Snapdragon NPU acceleration, also supporting CPU/GPU inference. I… | 82 | 3414 | active |
| luigifreda/pyslam pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras with a wide range of local and global fe… | 76 | 3404 | active |
| Farama-Foundation/HighwayEnv HighwayEnv is a collection of Gymnasium environments for autonomous driving and tactical decision-making tasks, covering scenarios like hig… | 94 | 3302 | active |
| root-project/root ROOT is a C++ data analysis framework developed at CERN for storing, processing, and visualizing large scientific datasets, with a columnar… | 100 | 3292 | stable |
| mani-skill/ManiSkill ManiSkill is an open-source GPU-parallelized robotics simulation framework and benchmark built on SAPIEN, focused on manipulation skills. I… | 91 | 3286 | active |
| lakesoul-io/LakeSoul LakeSoul is a cloud-native, real-time lakehouse framework with a Rust-native core providing ACID table format, concurrent upserts, incremen… | 100 | 3249 | active |
| prs-eth/Marigold Marigold is a family of diffusion-based models and a fine-tuning protocol that adapts pretrained latent diffusion models like Stable Diffus… | 51 | 3203 | active |
| nesaorg/nesa Nesa is a privacy-preserving AI inference platform that runs models like Llama, Mistral, and Stable Diffusion with end-to-end encryption us… | 23 | 3165 | active |
| megvii-research/NAFNet NAFNet is the official PyTorch implementation of a state-of-the-art image restoration network that removes nonlinear activation functions. … | 32 | 3151 | stable |
| fbdesignpro/sweetviz Sweetviz is a Python library that generates high-density HTML visualizations for exploratory data analysis in just a couple of lines of cod… | 82 | 3122 | active |
| junyanz/CycleGAN A Torch (Lua) implementation of CycleGAN and pix2pix for unpaired image-to-image translation using cycle-consistent adversarial networks. I… | 32 | 12869 | maintenance |
| alldatacenter/alldata AllData is a definable data platform (数据中台) that integrates open-source components like DolphinScheduler, DataX, SeaTunnel, OpenMetadata, a… | 86 | 3087 | active |
| yuyuyzl/EasyVtuber EasyVtuber is a Python-based VTubing application built on the Talking Head Anime model that turns a single anime character illustration int… | 62 | 3058 | active |
| deepnote/deepnote Deepnote is an open-source, AI-first drop-in replacement for Jupyter notebooks with a human-readable YAML format, block-based architecture … | 79 | 3000 | active |
| mujocolab/mjlab mjlab is a Python framework that combines Isaac Lab's manager-based API with MuJoCo Warp, a GPU-accelerated version of MuJoCo, for reinforc… | 85 | 2980 | active |
| mitsuba-renderer/mitsuba3 Mitsuba 3 is a research-oriented, retargetable rendering system for forward and inverse light transport simulation, written in C++17 on top… | 94 | 2906 | active |
| bytedeco/javacpp-presets JavaCPP Presets provides Java bindings for commonly used native C++ libraries such as OpenCV, FFmpeg, and many others, built on the JavaCPP… | 86 | 2850 | active |
| RoboTwin-Platform/RoboTwin RoboTwin 2.0 is a scalable benchmark and data-generation platform for bimanual (dual-arm) robotic manipulation, built on simulated digital … | 69 | 2808 | active |
| ideogram-oss/ideogram4 Ideogram 4 is an open-weight text-to-image foundation model trained from scratch, with inference code and weights released in Python. It fe… | 54 | 2801 | active |
| microsoft/promptflow Prompt flow is a suite of Python SDK, CLI, and VS Code extension tools for the end-to-end development of LLM-based AI applications, linking… | 75 | 11234 | maintenance |
| bmild/nerf The official TensorFlow implementation of NeRF (Neural Radiance Fields), the ECCV 2020 paper representing scenes as neural radiance fields … | 39 | 10930 | maintenance |
| HiLab-git/SSL4MIS A benchmark and code collection of semi-supervised learning methods for medical image segmentation, re-implementing approaches like Mean Te… | 43 | 2683 | active |
| phillipi/pix2pix The original Torch (Lua) implementation of pix2pix, a conditional GAN for image-to-image translation tasks such as synthesizing photos from… | 32 | 10654 | maintenance |
| Slicer/Slicer 3D Slicer is a free, open-source desktop platform for visualization, processing, segmentation, registration, and analysis of medical and bi… | 68 | 2612 | stable |
| luca-medeiros/lang-segment-anything A Python library combining Meta's Segment Anything Model 2 with GroundingDINO to generate segmentation masks for objects in images specifie… | 42 | 2598 | active |
| ARISE-Initiative/robosuite robosuite is a modular simulation framework powered by the MuJoCo physics engine for robot learning, offering standardized benchmark enviro… | 71 | 2590 | active |
| advimman/lama LaMa is a PyTorch-based image inpainting model that fills large missing regions in images using fast Fourier convolutions, generalizing wel… | 34 | 10244 | maintenance |
| AIGC-Audio/AudioGPT AudioGPT is a Python framework that wraps multiple audio foundation models (for speech, singing, sound, and talking-head tasks) behind a GP… | 30 | 10168 | maintenance |
| X-PLUG/mPLUG-Owl mPLUG-Owl is a family of open-source multimodal large language models that combine visual encoders with LLMs (built on LLaMA) for image and… | 36 | 2539 | active |
| xuebinqin/U-2-Net Official PyTorch implementation of U^2-Net, a nested U-structure deep network for salient object detection, published in Pattern Recognitio… | 32 | 9856 | maintenance |
| mirage-project/mirage Mirage Persistent Kernel (MPK) is a compiler and runtime that transforms multi-GPU LLM inference into a single fused megakernel, reducing i… | 83 | 2474 | active |
| wgsxm/PartCrafter PartCrafter is a structured 3D generative model that jointly generates multiple semantically meaningful 3D mesh parts and objects from a si… | 53 | 2472 | active |
| TrashUwU/PokeAssistant A Discord assistant bot for the Pokétwo game that automatically identifies Pokémon from spawn images using AI, pings roles or users when le… | 10 | 2469 | active |
| facebookresearch/pifuhd PIFuHD is a PyTorch implementation of a CVPR 2020 research model that reconstructs high-resolution 3D human body meshes from a single 2D im… | 10 | 9736 | maintenance |
| openlake-project/openlake OpenLake is a high-performance distributed storage engine written in Rust (built on io_uring, RDMA, and GPUDirect) designed to feed GPUs du… | 81 | 2405 | active |
| gkamradt/needle-in-a-haystack A benchmarking tool (niah / needlehaystack) that pressure-tests LLM long-context retrieval by sweeping context length x needle depth cells … | 72 | 2380 | active |
| MouseLand/cellpose Cellpose is a generalist deep learning algorithm for cellular and nucleus segmentation in microscopy images, with human-in-the-loop capabil… | 85 | 2338 | active |
| GoogleCloudPlatform/gcsfuse Cloud Storage FUSE (gcsfuse) is a user-space FUSE file system that mounts Google Cloud Storage buckets as local directories with standard f… | 95 | 2307 | stable |
| traveller59/spconv SpConv is a spatially sparse convolution library for deep learning on 3D point clouds and sparse tensors, distributed as PyPI packages with… | 32 | 2293 | active |
| nv-tlabs/lyra Project Lyra is NVIDIA's open series of generative 3D world models, including Lyra 1.0 for feed-forward 3D/4D scene generation from a singl… | 59 | 2279 | active |
| ashawkey/stable-dreamfusion A PyTorch implementation of Dreamfusion that generates 3D models from text prompts or images using NeRF combined with Stable Diffusion guid… | 23 | 8854 | maintenance |
| vaexio/vaex Vaex is a high-performance Python DataFrame library for lazy, out-of-core processing of large tabular datasets, using memory mapping and ze… | 56 | 8508 | maintenance |
| TimmyOVO/deepseek-ocr.rs A Rust implementation of the DeepSeek-OCR inference stack with multiple OCR/VLM backends (DeepSeek-OCR, PaddleOCR-VL, DotsOCR), DSQ quantiz… | 60 | 2184 | active |
| learnsyslab/gym-pybullet-drones A Python library providing PyBullet-based Gymnasium environments for simulating quadcopter control in single- and multi-agent reinforcement… | 67 | 2121 | active |
| LeCAR-Lab/ASAP ASAP is a two-stage framework for training agile humanoid whole-body skills by aligning simulation and real-world physics. It pre-trains mo… | 47 | 2107 | active |
| Open-Reasoner-Zero/Open-Reasoner-Zero Open-Reasoner-Zero is an open-source implementation of large-scale reinforcement learning training for reasoning-oriented language models, … | 31 | 2100 | active |
| SUDO-AI-3D/zero123plus Zero123++ is a diffusion base model that generates consistent multi-view images from a single input image, intended as a stepping stone for… | 27 | 2096 | active |
| microsoft/foundry-dev-tools Microsoft Foundry Toolkit (formerly AI Toolkit) is a Visual Studio Code extension for building, testing, and deploying AI agents and models… | 80 | 2050 | active |
| lupantech/AgentFlow AgentFlow is a trainable, tool-integrated agentic framework that coordinates planner, executor, verifier, and generator modules through an … | 46 | 2025 | active |
| google-deepmind/tapnet Google DeepMind's official repository for Tracking Any Point (TAP), containing the TAP-Vid and TAPVid-3D benchmarks, the TAPIR and TAPNext … | 74 | 1973 | active |
| siliconflow/onediff OneDiff is an out-of-the-box acceleration library for diffusion models, providing PyTorch compilation tools and optimized GPU kernels. It i… | 47 | 1964 | active |
| Fafa-DL/Awesome-Backbones A PyTorch-based framework that integrates many deep learning backbone models (CNNs and vision transformers like ResNet, EfficientNet, Swin … | 33 | 1952 | active |
| PixArt-alpha/PixArt-sigma PixArt-Σ is a PyTorch implementation of a diffusion transformer model for high-resolution (up to 4K) text-to-image generation, trained with… | 25 | 1940 | active |
| NVlabs/nvdiffrast Nvdiffrast is a PyTorch library from NVIDIA providing high-performance, GPU-accelerated primitive operations for rasterization-based differ… | 54 | 1912 | stable |
| fan-ziqi/robot_lab robot_lab is a reinforcement learning extension library for robots built on top of NVIDIA IsaacLab, providing preconfigured locomotion envi… | 73 | 1902 | active |
| policy-gradient/GRPO-Zero A minimal from-scratch Python implementation of DeepSeek's GRPO (Group Relative Policy Optimization) algorithm for reinforcement learning t… | 27 | 1899 | active |
| BytedTsinghua-SIA/DAPO DAPO is an open-source reinforcement learning system for large-scale LLM training, released by ByteDance Seed and Tsinghua AIR. It implemen… | 29 | 1864 | active |
| linkedin/greykite Greykite is a Python time series forecasting library from LinkedIn built around its Silverkite algorithm, with support for trend, seasonali… | 26 | 1855 | active |
| NVIDIA/pix2pixHD PyTorch implementation of pix2pixHD, a conditional GAN method for synthesizing and manipulating high-resolution (2048x1024) photorealistic … | 32 | 6924 | maintenance |
| openai/point-e Point-E is OpenAI's official release of models and code for generating 3D point clouds from text prompts or images using diffusion models. … | 32 | 6895 | maintenance |
| zju3dv/4K4D 4K4D is a research implementation of a 4D point cloud representation for real-time dynamic view synthesis at up to 4K resolution, built on … | 27 | 1806 | active |
| dreadl0ck/netcap Netcap is a Go framework that converts network packets into structured, type-safe Protocol Buffer audit records for security monitoring, fo… | 92 | 1803 | active |
| HuangJunJie2017/BEVDet BEVDet is a Python research codebase implementing the BEVDet series of bird's-eye-view (BEV) 3D object detection models for autonomous driv… | 23 | 1802 | active |
| apache/storm Apache Storm is a free and open-source distributed realtime computation system for processing unbounded streams of data, providing primitiv… | 98 | 6697 | maintenance |
| Webreaper/Damselfly Damselfly is a server-based photograph management application designed to index and search very large image collections using metadata such… | 88 | 1784 | active |
| Totoro97/NeuS Official PyTorch implementation of NeuS, a neural implicit surface reconstruction method that learns SDF-based surfaces via volume renderin… | 32 | 1776 | stable |