Open-source machine-learning software
4007 open-source libraries, tools and applications tagged machine-learning, ranked by how closely machine-learning is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
4007 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| google/XNNPACK XNNPACK is a highly optimized C library of floating-point neural network inference operators for ARM, x86, WebAssembly, and RISC-V platform… | 77 | 2481 | active |
| chemprop/chemprop Chemprop is a Python package implementing message passing neural networks (MPNNs) for predicting molecular and reaction properties. It prov… | 88 | 2480 | active |
| Lightning-AI/torchmetrics TorchMetrics is a PyTorch-native library of machine learning metrics that work in distributed and scalable training pipelines. It provides … | 87 | 2477 | stable |
| roboflow/inference Roboflow Inference is a Python library and self-hostable inference server for deploying computer vision models on any computer or edge devi… | 91 | 2474 | active |
| jadore801120/attention-is-all-you-need-pytorch A PyTorch implementation of the Transformer model from the paper 'Attention Is All You Need', including training and translation scripts fo… | 32 | 9816 | maintenance |
| inference-labs-inc/subnet-2 Subnet 2 on the Bittensor network implements a Proof-of-Inference system that uses zero-knowledge machine learning (zk-ML) to cryptographic… | 86 | 2462 | active |
| Farama-Foundation/Arcade-Learning-Environment The Arcade Learning Environment (ALE) is a framework built on the Stella Atari 2600 emulator that lets researchers and hobbyists develop an… | 92 | 2458 | stable |
| sqliteai/warp WARP is a dependency-free, embeddable C inference engine that runs trillion-parameter mixture-of-experts models like Kimi K3 by streaming a… | 77 | 2457 | active |
| metarank/metarank Metarank is an open-source, low-code Learning-to-Rank service that personalizes search results, listings, and recommendations using real-ti… | 85 | 2454 | active |
| google-parfait/tensorflow-federated TensorFlow Federated (TFF) is an open-source Python framework for machine learning and other computations on decentralized data. It provide… | 67 | 2454 | active |
| tracel-ai/cubecl CubeCL is a Rust language extension, JIT compiler, and runtime set for writing high-performance GPU compute kernels in plain Rust. A single… | 88 | 2453 | active |
| lupinemachines/lupine LUPINE is a GPU-over-IP bridge that lets machines without local GPUs attach NVIDIA GPUs running on remote servers over the network. It expo… | 90 | 2452 | active |
| Unakar/Logic-RL Logic-RL is a research framework that reproduces R1-Zero-style LLM reasoning via rule-based reinforcement learning (GRPO) on logic puzzles,… | 23 | 2452 | active |
| AI-Hypercomputer/maxtext MaxText is a high-performance, scalable open-source LLM training library written in pure Python/JAX, targeting Google Cloud TPUs and GPUs. … | 98 | 2446 | active |
| TorchIO-project/torchio TorchIO is a Python library for loading, augmenting, and processing 3D medical images (MRI, CT) within PyTorch deep learning pipelines. It … | 91 | 2446 | active |
| skfolio/skfolio skfolio is a Python library for portfolio optimization, factor model construction, and risk management built on top of scikit-learn. It pro… | 88 | 2446 | active |
| BeyondMimic Motion Tracking BeyondMimic's official motion tracking training code, a humanoid control framework built on Isaac Lab that trains sim-to-real-ready whole-b… | 10 | 2444 | active |
| nv-tlabs/3dgrut NVIDIA's official implementations of 3D Gaussian Ray Tracing (3DGRT) and 3D Gaussian Unscented Transform (3DGUT), which render volumetric G… | 68 | 2441 | active |
| hitsz-ids/synthetic-data-generator SDG (Synthetic Data Generator) is a Python framework for generating high-quality synthetic structured tabular data using deep learning, GAN… | 75 | 2440 | active |
| omry/omegaconf OmegaConf is a hierarchical Python configuration library that merges configs from YAML files, dataclasses/objects, and CLI arguments behind… | 95 | 2438 | stable |
| NovaSky-AI/SkyRL SkyRL is a modular full-stack reinforcement learning library for post-training large language models, combining a training framework (skyrl… | 83 | 2436 | active |
| shenweichen/DeepMatch DeepMatch is a Python library of deep matching models for recommendations and advertising, built on TensorFlow/Keras. It lets users train m… | 65 | 2435 | active |
| resemble-ai/resemble-enhance Resemble Enhance is an AI-powered Python tool that improves speech quality through denoising and enhancement, using a denoiser module and a… | 18 | 2434 | active |
| trymirai/uzu Uzu is a high-performance inference engine written in Rust for running AI models directly on-device, with Python, TypeScript, and Swift bin… | 87 | 2423 | active |
| tflearn/tflearn TFLearn is a modular deep learning library providing a higher-level, Keras-like API on top of TensorFlow for building and training neural n… | 23 | 9570 | maintenance |
| Olive Olive is Microsoft's AI model optimization toolkit for the ONNX Runtime, automating finetuning, conversion, quantization, and compression o… | 89 | 2402 | active |
| ailia models A collection of 400+ pre-trained state-of-the-art AI models (object detection, pose estimation, speech recognition, LLMs, image generation,… | 76 | 2393 | active |
| zai-org/GLM-V GLM-V is the open-source repository for Zhipu AI's GLM-4.6V, GLM-4.5V, and GLM-4.1V-Thinking vision-language models, which perform versatil… | 63 | 2393 | active |
| akfamily/akquant AKQuant is a high-performance quantitative research and backtesting framework with a Rust core engine and Python interface for strategy dev… | 76 | 2392 | active |
| NVlabs/ProtoMotions ProtoMotions is a GPU-accelerated simulation and reinforcement learning framework for training physically simulated digital humans and huma… | 66 | 2392 | active |
| sjwhitworth/golearn GoLearn is a 'batteries included' machine learning library for Go with a scikit-learn-style Fit/Predict interface. It provides data loading… | 32 | 9436 | maintenance |
| langfengQ/verl-agent verl-agent is an extension of the veRL framework for training LLM and VLM agents via reinforcement learning, featuring step-independent mul… | 51 | 2388 | active |
| AminHP/gym-anytrading gym-anytrading is a collection of OpenAI Gym environments for developing and testing reinforcement learning-based trading algorithms in FOR… | 23 | 2386 | stable |
| google/neural-tangents Neural Tangents is a Python library built on JAX for defining, training, and evaluating neural networks of both finite and infinite width. … | 10 | 2385 | stable |
| facebookresearch/perception_models Meta's Perception Models repository hosting state-of-the-art image, video, and audio encoders (Perception Encoder, PE) and a multimodal lan… | 51 | 2382 | active |
| jik876/hifi-gan The official PyTorch implementation of HiFi-GAN, a generative adversarial network that converts mel-spectrograms into high-fidelity 22.05 k… | 32 | 2377 | stable |
| apple/axlearn AXLearn is a Python deep learning library built on JAX and XLA for developing and training large-scale models, with an object-oriented conf… | 69 | 2375 | active |
| XiaomiMiMo/MiMo Xiaomi's MiMo is a 7B-parameter reasoning language model trained from pretraining through posttraining with reinforcement learning, release… | 28 | 2373 | active |
| FMInference/FlexLLMGen FlexLLMGen is a high-throughput generation engine for running large language models on a single GPU with limited memory. It uses IO-efficie… | 10 | 9346 | maintenance |
| fastino-ai/GLiNER2 GLiNER2 is a Python library for schema-based information extraction and text classification, supporting named entity recognition, structure… | 85 | 2369 | active |
| VexDB-THU/VexDB-Lite VexDB-Lite is a cross-platform vector similarity search engine implemented as plugins for PostgreSQL, DuckDB, and SQLite, sharing a graph i… | 74 | 2366 | active |
| uptrain-ai/uptrain UpTrain is an open-source Python platform for evaluating and improving LLM applications, offering 20+ preconfigured evaluation checks cover… | 23 | 2366 | active |
| EasyRec EasyRec is a TensorFlow-based framework from Alibaba for building large-scale deep learning recommendation models covering matching, rankin… | 59 | 2361 | active |
| NVIDIA-NeMo/DataDesigner NeMo Data Designer is an open-source Python orchestration framework from NVIDIA for generating high-quality synthetic datasets from scratch… | 85 | 2357 | active |
| Neural Circuit Policies (ncps) A Python package providing PyTorch and TensorFlow/Keras implementations of Neural Circuit Policies (NCPs), including liquid time-constant (… | 23 | 2351 | active |
| google-deepmind/optax Optax is a gradient processing and optimization library for JAX, offering composable building blocks like optimizers and loss functions. It… | 80 | 2350 | stable |
| ComflowySpace ComflowySpace is an open-source desktop application that wraps ComfyUI/Stable Diffusion into a friendlier, app-like interface for generatin… | 18 | 2346 | active |
| maitrix-org/llm-reasoners LLM Reasoners is a Python library that provides a standardized modular framework for advanced LLM reasoning, implementing algorithms like M… | 28 | 2345 | active |
| ALOHA ALOHA is an open-source hardware and software system for low-cost bimanual robot teleoperation and demonstration data collection, built on … | 31 | 2336 | active |
| vearch/vearch Vearch is a cloud-native distributed vector database for efficient similarity search of embedding vectors, supporting hybrid vector and sca… | 76 | 2331 | active |
| refuel-ai/autolabel Autolabel is a Python library for labeling, cleaning, and enriching text datasets using large language models like GPT-4, Claude, and open-… | 22 | 2330 | active |
| facebookresearch/schedule_free A PyTorch library implementing schedule-free optimizers (SGD, AdamW, RAdam variants) that remove the need for learning rate schedules or sp… | 64 | 2329 | active |
| LabML A Python library for tracking and monitoring deep learning experiments, with a self-hostable server app for viewing metrics and hardware us… | 26 | 2327 | active |
| LabML A curated collection of over 60 PyTorch implementations of deep learning papers, complete with side‑by‑side explanatory notes. It serves as… | 26 | 2327 | active |
| ufoym/imbalanced-dataset-sampler A PyTorch dataset sampler (ImbalancedDatasetSampler, pip package torchsampler) that rebalances class distributions during training by overs… | 60 | 2326 | stable |
| YvanYin/Metric3D Metric3D is the official PyTorch implementation of Metric3Dv1 and Metric3Dv2, monocular geometric foundation models that predict metric dep… | 31 | 2326 | active |
| Picotron Picotron is a minimalist, hackable distributed training framework for pre-training Llama-like large language models using 4D parallelism (d… | 37 | 2325 | active |
| iver56/audiomentations Audiomentations is a Python library for audio data augmentation with an API inspired by albumentations. It provides fast CPU-based waveform… | 61 | 2323 | stable |
| Cadene/pretrained-models.pytorch A Python library providing pretrained ConvNet models (ResNet, ResNeXt, InceptionV4, Xception, NASNet, SENet, DPN, etc.) for PyTorch behind … | 32 | 9101 | maintenance |
| facebookresearch/ImageBind A PyTorch library from Meta AI implementing ImageBind, a model that learns a joint embedding space across six modalities: images, text, aud… | 51 | 9076 | maintenance |
| OpenHelix-Team/VLA-Adapter VLA-Adapter is the official implementation of a tiny-scale vision-language-action model that bridges vision-language representations to rob… | 47 | 2313 | active |
| LAION-AI/CLAP CLAP (Contrastive Language-Audio Pretraining) is a Python library from LAION that learns joint audio and text embeddings using contrastive … | 38 | 2312 | stable |
| IDEA-Research/detrex detrex is an open-source PyTorch-based research platform and toolbox for DETR-style Transformer detection algorithms, built on top of Detec… | 38 | 2311 | active |
| apache/mahout Apache Mahout is an Apache Software Foundation project providing Qumat, a high-level Python library for quantum computing with a unified AP… | 84 | 2310 | active |
| frgfm/torch-cam TorchCAM is a Python library that extracts class activation maps (CAMs) from PyTorch CNN classifiers, supporting many CAM variants such as … | 88 | 2307 | active |
| claimed-framework/claimed CLAIMED (C3) is a component compiler that turns Jupyter notebooks, Python scripts, and R scripts into portable containerized AI components.… | 82 | 2305 | active |
| Neroued/ninfer NInfer is a from-scratch C++/CUDA inference engine optimized for maximum single-GPU performance on a narrow, explicitly registered set of Q… | 57 | 2305 | active |
| levy-street/world-of-claudecraft World of ClaudeCraft is a free, open-source classic-style browser MMO built in TypeScript with Three.js, playable online with persistent ch… | 77 | 2302 | active |
| emgucv/emgucv Emgu CV is a cross-platform .NET wrapper for the OpenCV image processing library, allowing OpenCV functions to be called from .NET-compatib… | 90 | 2300 | active |
| NVlabs/nvdiffrec nvdiffrec is NVIDIA's official implementation of a CVPR 2022 oral paper that jointly optimizes triangular 3D meshes, PBR materials, and lig… | 72 | 2298 | stable |
| codeplea/genann Genann is a minimal, well-tested C99 library for training and running feedforward artificial neural networks. It is contained in a single s… | 91 | 2293 | stable |
| fairlearn/fairlearn Fairlearn is a Python package for assessing and mitigating fairness issues in machine learning models. It provides fairness metrics for eva… | 91 | 2293 | active |
| feature-engine/feature_engine Feature-engine is a Python library for feature engineering and feature selection with transformers that follow scikit-learn's fit/transform… | 82 | 2290 | stable |
| benedekrozemberczki/karateclub Karate Club is a Python library of unsupervised machine learning algorithms for graph-structured data, built as an extension of NetworkX. I… | 23 | 2290 | stable |
| facebookresearch/fairchem FAIR Chemistry's centralized Python library of machine learning models, datasets, and applications for materials science and quantum chemis… | 98 | 2289 | active |
| hkchengrex/MMAudio MMAudio is a PyTorch-based model for generating synchronized audio from video and/or text inputs, using multimodal joint training across au… | 39 | 2287 | active |
| Liuziyu77/Visual-RFT Official research code for Visual-RFT and Visual-ARFT, applying GRPO-based reinforcement fine-tuning with rule-based verifiable rewards to … | 39 | 2280 | active |
| dstack dstack is an open-source, vendor-agnostic control plane for GPU provisioning and orchestration that works across GPU clouds, Kubernetes, an… | 95 | 2277 | active |
| opendatalab/DocLayout-YOLO DocLayout-YOLO is a real-time YOLO-v10-based model for detecting document layout elements (text blocks, tables, figures, etc.) in diverse d… | 26 | 2277 | active |
| OlafenwaMoses/ImageAI ImageAI is a Python library that lets developers add computer vision capabilities like image classification, object detection, and video ob… | 23 | 8888 | maintenance |
| ermig1979/Simd Simd Library is a free open-source C++ image processing and machine learning library with a C API and Python wrapper. Its algorithms are ha… | 98 | 2272 | active |
| RosettaCommons/RoseTTAFold RoseTTAFold is the official implementation of a deep learning system for predicting protein structures and interactions using a three-track… | 23 | 2269 | stable |
| Amazon SageMaker Containers & SDK The SageMaker Python SDK is an open-source Python library for training and deploying machine learning models on Amazon SageMaker. It suppor… | 94 | 2268 | active |
| 666DZY666/micronet micronet is a Python library for deep neural network model compression and deployment built on PyTorch. It provides quantization (QAT, PTQ,… | 38 | 2265 | active |
| yemount/pose-animator Pose Animator is a browser-based tool that animates 2D SVG vector characters in real time using pose and face keypoints detected by PoseNet… | 32 | 8851 | maintenance |
| galilai-group/stable-worldmodel A Python library providing a unified platform for reproducible world model research, covering data collection, training, and evaluation via… | 78 | 2260 | active |
| TuringLang/Turing.jl Turing.jl is a probabilistic programming library in Julia for Bayesian inference. Models are defined with an @model macro resembling mathem… | 93 | 2258 | active |
| facebookresearch/fvcore fvcore is a lightweight Python core library providing common functionality shared across FAIR's computer vision frameworks such as Detectro… | 73 | 2254 | stable |
| MinishLab/model2vec Model2Vec is a Python library that distills any sentence transformer into a tiny, fast static embedding model by computing one fixed vector… | 91 | 2251 | active |
| CoinCheung/pytorch-loss A PyTorch library providing a collection of loss functions (focal loss, triplet loss, AMSoftmax, label-smooth CE, dice loss, lovasz-softmax… | 32 | 2251 | 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… | 74 | 2250 | active |
| kubeflow/trainer Kubeflow Trainer is a Kubernetes-native platform for distributed AI model training and LLM fine-tuning across frameworks like PyTorch, JAX,… | 92 | 2249 | 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… | 35 | 2247 | active |
| 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 … | 87 | 2246 | active |
| Accenture/AmpliGraph AmpliGraph is a Python library built on TensorFlow 2 for representation learning on knowledge graphs. It provides neural models (TransE, Di… | 78 | 2242 | active |
| Raster Vision Raster Vision is an open source Python library and low-code framework for building computer vision models on satellite, aerial, and other l… | 57 | 2241 | active |
| rapidsai/cugraph cuGraph is NVIDIA's RAPIDS collection of GPU-accelerated graph analytics libraries, offering Python, C, and C++ APIs for building graphs an… | 90 | 2237 | active |
| tensorchord/envd envd is a command-line tool that creates reproducible, container-based development environments for AI/ML work using a simple Python-like b… | 97 | 2236 | active |
| ellisdg/3DUnetCNN A PyTorch library for building, training, and applying 3D U-Net convolutional neural networks for medical image segmentation. It provides c… | 42 | 2235 | active |
| PyGAD PyGAD is an open-source Python 3 library for implementing the genetic algorithm to optimize single- and multi-objective problems. It can al… | 90 | 2230 | active |