domain: machine-learning
3991 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| ovg-project/kvcached kvcached is a Python library that brings OS-style virtual memory abstraction to KV cache management for LLM serving and training on shared … | 74 | 1143 | active |
| IDEA-Research/Grounding-DINO-1.5-API Python examples and API client for Grounding DINO 1.5/1.6, IDEA Research's open-world (open-set) object detection model series hosted on De… | 25 | 1143 | active |
| chrishayuk/larql LARQL decompiles transformer models into a queryable 'vindex' (vector index) format and provides LQL, a SQL-like query language, to browse,… | 82 | 1142 | active |
| nnaisense/evotorch EvoTorch is an open-source evolutionary computation library built on top of PyTorch, developed at NNAISENSE. It provides distribution-based… | 78 | 1142 | active |
| facebookresearch/StarSpace StarSpace is a general-purpose neural model from Facebook Research that learns entity embeddings for classification, retrieval, ranking, an… | 10 | 3952 | maintenance |
| HengyiWang/spann3r Spann3R is a transformer-based model for dense 3D reconstruction from ordered or unordered image collections, built on the DUSt3R paradigm.… | 26 | 1141 | active |
| cvg/glue-factory Glue Factory is a PyTorch-based library for training and evaluating deep neural networks that detect and match local visual features (point… | 69 | 1140 | active |
| Tavish9/any4lerobot Any4LeRobot is a curated collection of Python utilities for the Hugging Face LeRobot robotics ecosystem, including dataset conversion scrip… | 64 | 1140 | active |
| THUMNLab/AutoGL AutoGL is an autoML framework and toolkit for machine learning on graphs, built on PyTorch with PyTorch Geometric and DGL backends. It prov… | 47 | 1140 | active |
| rohitgandikota/sliders Official implementation of Concept Sliders, LoRA adaptors that enable precise, plug-and-play control of attributes in diffusion models like… | 52 | 1139 | active |
| andabi/deep-voice-conversion A TensorFlow implementation of deep neural networks for voice conversion (voice style transfer) that converts a source speaker's voice into… | 32 | 3938 | maintenance |
| xzf-thu/Mega-ASR Mega-ASR is a foundation automatic speech recognition model trained on 2.6M samples spanning 7 atomic acoustic conditions and 54 compound r… | 59 | 1136 | active |
| vec2text/vec2text A Python library for text embedding inversion: training and running models that reconstruct text sequences from their sentence embeddings. … | 57 | 1136 | active |
| horseee/LLM-Pruner LLM-Pruner is a PyTorch library implementing structural pruning of large language models based on gradient information, as published at Neu… | 29 | 1136 | active |
| Dao-AILab/quack QuACK is a collection of high-performance GPU kernels (RMSNorm, LayerNorm, softmax, cross-entropy, GEMM with epilogues) written in NVIDIA's… | 85 | 1135 | active |
| Kiteretsu77/APISR APISR is a deep-learning based super-resolution tool that restores and enhances low-quality, low-resolution anime images and videos using t… | 37 | 1135 | active |
| aliyun/SimAI SimAI is a large-scale network simulation toolkit from Alibaba Cloud for modeling AI training and inference workloads on GPU clusters, publ… | 66 | 1133 | active |
| huawei-noah/trustworthyAI A collection of trustworthy AI projects from Huawei Noah's Ark Lab, centered on gCastle, a causal structure learning toolchain with many gr… | 61 | 1132 | active |
| FlagOpen/RoboBrain2.5 RoboBrain 2.5 is an open-source embodied AI foundation model from BAAI that combines multimodal large language model capabilities with 3D s… | 50 | 1132 | active |
| sooftware/conformer An unofficial PyTorch implementation of the Conformer architecture (convolution-augmented Transformer) from the INTERSPEECH 2020 paper, tar… | 72 | 1131 | active |
| noahcao/OC_SORT OC-SORT is a pure motion-model-based multi-object tracker for video, improving on SORT by fixing Kalman filter limitations to handle occlus… | 67 | 1131 | stable |
| yohanshin/WHAM WHAM is the official PyTorch implementation of the CVPR 2024 paper 'Reconstructing World-grounded Humans with Accurate 3D Motion'. It estim… | 26 | 1130 | active |
| Lingua Lingua is a language detection library for Python (with a Rust core) that identifies which of 75 languages a text is written in. It is desi… | 87 | 1129 | active |
| PriesiaMioShirakana/DragonianVoice A C++ inference library for running ONNX-based TTS, SVC (singing voice conversion), and SVS (singing voice synthesis) models, supporting ar… | 40 | 1129 | active |
| ikostrikov/pytorch-a2c-ppo-acktr-gail A PyTorch implementation of several deep reinforcement learning algorithms: A2C, PPO, ACKTR, and GAIL (imitation learning). It works with O… | 32 | 3903 | maintenance |
| Dobiasd/frugally-deep frugally-deep is a lightweight header-only C++ library for running inference (forward passes) on Keras/TensorFlow models without linking ag… | 85 | 1128 | active |
| uncomplicate/neanderthal Neanderthal is a fast Clojure library for matrix and linear algebra computations built on optimized native BLAS and LAPACK routines, suppor… | 76 | 1128 | active |
| open-mmlab/mmtracking MMTracking is OpenMMLab's PyTorch-based toolbox for video perception tasks, unifying video object detection, multiple object tracking, sing… | 23 | 3897 | maintenance |
| NovaSearch-Team/RAG-Retrieval A Python library and toolkit for unified fine-tuning, inference, and distillation of RAG retrieval models, including embedding models, ColB… | 60 | 1127 | active |
| BeingBeyond/Being-H Being-H is a family of human-centric embodied foundation models, including VLA models (Being-H0.5, Being-H0) and latent world-action models… | 63 | 1126 | active |
| googlecolab/google-colab-cli A Python-based command-line interface for Google Colab that lets users provision CPU, GPU, and TPU runtimes, execute local scripts and note… | 59 | 1126 | active |
| espressif/esp-dl ESP-DL is Espressif's lightweight neural network inference framework for ESP-series chips, with a custom .espdl model format, quantization … | 72 | 1125 | active |
| OpenGVLab/VideoMamba VideoMamba is a state space model (Mamba-based) architecture for efficient video understanding, released with code and pretrained models fr… | 25 | 1125 | active |
| hijohnnylin/neuronpedia Neuronpedia is an open source AI interpretability platform for exploring, visualizing, and steering the internals of language models. It ho… | 92 | 1124 | active |
| wandb/weave Weave is a Python/TypeScript toolkit by Weights & Biases for developing AI-powered applications, providing LLM tracing, agent observability… | 92 | 1124 | active |
| NVIDIA/cuda-quantum NVIDIA's CUDA-Q platform providing C++ and Python tools for programming heterogeneous quantum-classical workflows across QPUs, GPUs, and CP… | 91 | 1124 | active |
| geopavlakos/hamer HaMeR (Hand Mesh Recovery) is a transformer-based model that reconstructs 3D hand meshes from single monocular images using the MANO parame… | 56 | 1124 | active |
| OpenDriveLab/UniVLA UniVLA is an open-source framework for training cross-embodiment vision-language-action (VLA) robot policies using task-centric latent acti… | 43 | 1124 | active |
| THUDM/SwissArmyTransformer SwissArmyTransformer (sat) is a PyTorch library for developing custom Transformer model variants where models like BERT, GPT, T5, GLM, and … | 23 | 1121 | active |
| FlagAI-Open/FlagAI FlagAI is a Python toolkit for training, fine-tuning, and deploying large-scale AI models across NLP, CV, and vision-language tasks. It int… | 64 | 3869 | maintenance |
| PRIME-RL/TTRL TTRL is an open-source implementation of Test-Time Reinforcement Learning, a method for training LLMs with RL on unlabeled data using major… | 51 | 1120 | active |
| blackjax-devs/blackjax BlackJAX is a library of fast, modular MCMC samplers (NUTS, HMC, and more) built on JAX, running on CPU, GPU, and TPU. It is not a full pro… | 89 | 1119 | active |
| princeton-vl/RAFT-Stereo RAFT-Stereo is a PyTorch implementation of a deep learning model for stereo matching that estimates disparity maps from stereo image pairs … | 75 | 1119 | stable |
| PaddlePaddle/PaddleHelix PaddleHelix is a bio-computing platform built on PaddlePaddle featuring large-scale representation learning and multi-task deep learning fo… | 57 | 1119 | active |
| yangxue0827/RotationDetection AlphaRotate is a TensorFlow-based benchmark and toolbox for rotated (oriented) object detection, implementing detectors such as R2CNN, Reti… | 23 | 1118 | active |
| Lasagne/Lasagne Lasagne is a lightweight Python library for building and training neural networks on top of Theano. It supports feed-forward, convolutional… | 23 | 3857 | maintenance |
| HarryR/z80ai Z80-μLM is a 2-bit quantized micro language model designed to run on 8-bit Z80 processors with only 64KB of RAM, exportable as ~40KB CP/M .… | 51 | 1117 | active |
| datadreamer-dev/DataDreamer DataDreamer is an open-source Python library for prompting LLMs, generating synthetic datasets, and training or aligning models in reproduc… | 33 | 1117 | active |
| microsoft/onnxruntime-genai ONNX Runtime GenAI is a C++ library with Python, C#, C/C++, and Java APIs for running generative AI models (LLMs, Whisper, vision-language … | 93 | 1116 | active |
| red-data-tools/pycall.rb PyCall.rb is a Ruby library that lets Ruby code directly call Python functions and interoperate with Python modules via the CPython C API. … | 87 | 1116 | active |
| yahoo/TensorFlowOnSpark TensorFlowOnSpark is a Python library that lets existing TensorFlow programs run distributed training and inference on Apache Spark and Had… | 23 | 3845 | maintenance |
| openai/improved-diffusion The official codebase for OpenAI's Improved Denoising Diffusion Probabilistic Models paper, providing a Python package for training and sam… | 32 | 3844 | maintenance |
| XYZ-AI-Lab/AxisAgentic AxisAgentic is an extensible Python runtime for long-horizon AI agents that handles multi-turn execution, tool orchestration, context manag… | 55 | 1114 | active |
| ZiwenZhuang/parkour Official code for 'Robot Parkour Learning' (CoRL 2023), a reinforcement learning system that trains quadrupedal robots to perform vision-ba… | 50 | 1114 | active |
| tonybaloney/CSnakes CSnakes is a .NET source generator and runtime library for embedding Python code and libraries directly into C# .NET applications via the C… | 70 | 1113 | active |
| AdaptiveMotorControlLab/CEBRA CEBRA is a Python library for self-supervised learning of consistent latent embeddings from high-dimensional time-series recordings, using … | 86 | 1111 | active |
| baofff/U-ViT U-ViT is the official PyTorch implementation of a ViT-based backbone architecture for diffusion models from the CVPR 2023 paper 'All are Wo… | 32 | 1110 | stable |
| amazon-science/RAGChecker RAGChecker is an automatic evaluation framework for diagnosing Retrieval-Augmented Generation (RAG) systems. It provides holistic and diagn… | 25 | 1110 | active |
| RUC-NLPIR/ARPO ARPO (Agentic Reinforced Policy Optimization) is a reinforcement learning algorithm and training framework for LLM agents, published at ICL… | 54 | 1109 | active |
| unitreerobotics/unifolm-world-model-action UnifoLM-WMA-0 is Unitree's open-source world-model-action framework for general-purpose robot learning across multiple robotic embodiments.… | 50 | 1109 | active |
| THU-MIG/RepViT Official PyTorch implementation of RepViT, a family of lightweight CNNs designed by integrating efficient ViT architectural designs into Mo… | 19 | 1108 | stable |
| gxtrobot/bustag Bustag is a self-hosted web application that periodically scrapes new media title (番号) listings, lets users tag items as liked or disliked,… | 23 | 3814 | maintenance |
| spytensor/prepare_detection_dataset A collection of Python scripts that convert object detection datasets between common annotation formats, including CSV, LabelMe JSON, COCO,… | 66 | 1107 | active |
| prometheus-eval/prometheus-eval Prometheus-Eval is a Python library for evaluating LLM generation outputs using the Prometheus family of open evaluator models and GPT-4 as… | 23 | 1107 | active |
| grf-labs/grf GRF is an R package (with C++ core) for forest-based statistical estimation and inference, providing non-parametric methods for heterogeneo… | 68 | 1106 | stable |
| OpenMOSS/MOVA MOVA is an open-source foundation model and toolkit for joint video-audio generation, synthesizing synchronized video and audio in a single… | 60 | 1106 | active |
| szymanowiczs/splatter-image Official PyTorch implementation of 'Splatter Image: Ultra-Fast Single-View 3D Reconstruction' (CVPR 2024), which uses an image-to-image net… | 26 | 1106 | active |
| google-research/multinerf Google Research's official code release for three NeRF papers: Mip-NeRF 360, Ref-NeRF, and RawNeRF, written in JAX. It trains neural radian… | 10 | 3808 | maintenance |
| AnswerDotAI/fastcore fastcore is a Python utility library that extends the language with features inspired by Ruby, Haskell, and NumPy, including an enhanced li… | 96 | 1105 | active |
| rusty1s/pytorch_sparse A PyTorch extension library providing optimized sparse matrix operations (coalesce, transpose, sparse-dense and sparse-sparse multiplicatio… | 61 | 1104 | active |
| yangheng95/PyABSA PyABSA is a PyTorch-based library providing state-of-the-art models for aspect-based sentiment analysis, including aspect term extraction, … | 67 | 1102 | active |
| yzslab/gaussian-splatting-lightning A PyTorch Lightning implementation of 3D Gaussian Splatting with many derived algorithms (Mip-Splatting, LightGaussian, 2DGS, deformable Ga… | 58 | 1101 | active |
| MoonshotAI/MoonEP MoonEP is an Expert Parallelism communication library for Mixture-of-Experts training that keeps token loads perfectly balanced across rank… | 56 | 1101 | active |
| naturomics/CapsNet-Tensorflow A TensorFlow implementation of CapsNet (Capsule Networks) based on Geoffrey Hinton's paper 'Dynamic Routing Between Capsules'. It supports … | 32 | 3786 | maintenance |
| sqliteai/sqlite-vector SQLite-Vector is a cross-platform SQLite extension written in C that adds vector search capabilities to embedded SQLite databases, with SIM… | 86 | 1100 | active |
| yongliang-wu/DFT DFT (Dynamic Fine-Tuning) is the official implementation of an ICLR 2026 paper that improves Supervised Fine-Tuning of LLMs by dynamically … | 61 | 1100 | active |
| lucidrains/stylegan2-pytorch A simple PyTorch implementation of StyleGAN2, a state-of-the-art generative adversarial network, trainable entirely from the command line w… | 23 | 3783 | maintenance |
| Gen-Verse/LatentMAS LatentMAS is a training-free multi-agent reasoning framework that lets LLM agents collaborate in continuous latent space by passing hidden-… | 56 | 1099 | active |
| yandex-research/tabm TabM is a PyTorch-based deep learning model for tabular data that efficiently imitates an ensemble of MLPs through parameter-efficient ense… | 36 | 1099 | active |
| luchris429/purejaxrl PureJaxRL provides end-to-end reinforcement learning training pipelines implemented entirely in JAX, including environments, enabling massi… | 30 | 1099 | active |
| AnswerDotAI/fastprogress fastprogress is a fast and simple Python progress bar library that works in both Jupyter Notebooks and the console. It supports nested prog… | 92 | 1098 | stable |
| fraunhoferportugal/tsfel TSFEL is an open-source Python library for extracting features from time series signals across statistical, temporal, spectral, and fractal… | 53 | 1098 | active |
| LAMDA-CL/PyCIL PyCIL is a PyTorch-based Python toolbox for class-incremental learning, implementing the largest collection of CIL methods for reproducible… | 52 | 1098 | active |
| apache/systemds Apache SystemDS is an open-source machine learning system covering the end-to-end data science lifecycle, from data cleaning and feature en… | 87 | 1097 | active |
| qiskit-community/qiskit-machine-learning Qiskit Machine Learning is an open-source Python library built on the Qiskit SDK that provides building blocks for quantum machine learning… | 90 | 1096 | active |
| waymo-research/waymax Waymax is a lightweight, multi-agent autonomous driving simulator built entirely in JAX, based on the Waymo Open Motion Dataset. It support… | 49 | 1096 | active |
| gunrock/gunrock Gunrock is a CUDA/C++ library for GPU-accelerated graph analytics built on a high-level, data-centric abstraction over vertex and edge fron… | 63 | 1095 | active |
| hkchengrex/Cutie Cutie is a video object segmentation framework with object-level memory reading, a follow-up to XMem offering better consistency, robustnes… | 18 | 1095 | active |
| LujiaJin/One-Pot_Multi-Frame_Denoising Official PyTorch implementation of the One-Pot Multi-frame Denoising (OPD) method published at BMVC 2022 and extended in IJCV. It provides … | 60 | 1094 | stable |
| Emsu/prophet Prophet is a Python microframework for financial markets analysis that lets programmers model trading strategies, manage portfolios, and ru… | 57 | 1093 | active |
| lizhe00/AnimatableGaussians Official PyTorch implementation of the CVPR 2024 paper 'Animatable Gaussians', which learns pose-dependent Gaussian maps for high-fidelity … | 27 | 1093 | active |
| zju3dv/PGSR PGSR is a Python implementation of a planar-based Gaussian Splatting method for efficient, high-fidelity 3D surface reconstruction from mul… | 24 | 1092 | active |
| google-ai-edge/litert-torch LiteRT Torch is a Python library that converts PyTorch models into .tflite format for running with LiteRT on Android, iOS, and IoT devices.… | 87 | 1091 | active |
| lucidrains/tab-transformer-pytorch A PyTorch implementation of the TabTransformer architecture, an attention-based neural network for tabular data, also including the FT Tran… | 70 | 1091 | stable |
| geoopt/geoopt Geoopt is a PyTorch library providing manifold-aware optimizers and manifold tensor containers for Riemannian optimization. It implements R… | 59 | 1091 | active |
| hanruihua/NeuPAN NeuPAN is a real-time, map-free robot motion planner that maps raw obstacle point data directly to control actions using an end-to-end MPC-… | 69 | 1090 | active |
| localai-org/depth-anything.cpp A from-scratch C++17/ggml port of ByteDance's Depth Anything 2 and 3 models for dependency-free monocular metric depth and camera pose infe… | 58 | 1090 | active |
| flagos-ai/FlagGems FlagGems is a high-performance operator library for large language models written in the Triton language, providing backend-neutral GPU ker… | 89 | 1089 | active |
| Toni-SM/skrl skrl is an open-source modular Reinforcement Learning library written in Python, implemented in PyTorch, JAX, and NVIDIA Warp. It supports … | 81 | 1089 | active |
| mymusise/ChatGLM-Tuning A Python toolkit for fine-tuning the ChatGLM-6B large language model using LoRA (Low-Rank Adaptation) with the Alpaca dataset. It provides … | 10 | 3740 | maintenance |