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 |
|---|---|---|---|
| Tencent/DepthCrafter DepthCrafter is a diffusion-based video depth estimation model from Tencent AI Lab that generates temporally consistent long depth sequence… | 34 | 1590 | active |
| DeepGraphLearning/torchdrug TorchDrug is a PyTorch-based machine learning library for drug discovery, covering graph neural networks, deep generative models, and reinf… | 23 | 1589 | active |
| stanfordnlp/pyreft pyreft is Stanford NLP's Python library for Representation Finetuning (ReFT), which adapts frozen language models by learning task-specific… | 52 | 1587 | active |
| meta-pytorch/torchtune Torchtune is a PyTorch-native library for authoring, post-training, and experimenting with large language models. It provides hackable trai… | 67 | 5819 | maintenance |
| gcorso/DiffDock DiffDock is a deep learning implementation of a diffusion generative model for molecular docking, predicting how small molecule ligands bin… | 28 | 1585 | active |
| CodeReclaimers/neat-python A pure-Python implementation of NEAT (NeuroEvolution of Augmenting Topologies), an algorithm for evolving neural network topologies and wei… | 73 | 1584 | active |
| RWKV/rwkv.cpp A C++ port of the RWKV language model to the ggml tensor library, providing FP32, FP16, and quantized INT4/INT5/INT8 inference focused on C… | 34 | 1583 | active |
| Xilinx/brevitas Brevitas is a PyTorch library for neural network quantization supporting both post-training quantization (PTQ) and quantization-aware train… | 93 | 1582 | active |
| microsoft/MMdnn MMdnn is a Microsoft toolkit for converting, visualizing, and diagnosing deep learning models across frameworks such as TensorFlow, PyTorch… | 35 | 5803 | maintenance |
| google-ai-edge/model-explorer Model Explorer is a model graph visualizer and debugger from Google AI Edge that renders neural network graphs hierarchically with expandab… | 92 | 1581 | active |
| karpathy/arxiv-sanity-preserver A self-hostable web application for browsing, searching, and filtering recent arXiv submissions, with personalized paper recommendations ba… | 32 | 5799 | maintenance |
| DiffEqML/torchdyn Torchdyn is a PyTorch library dedicated to numerical deep learning, providing tools for neural differential equations, implicit models, and… | 23 | 1580 | active |
| tensorflow/model-optimization The TensorFlow Model Optimization Toolkit (tfmot) is a Python library providing tools to optimize machine learning models for deployment, i… | 79 | 1579 | stable |
| evo-design/evo Evo is a 7-billion-parameter DNA foundation model built on the StripedHyena architecture, trained on ~300 billion tokens of prokaryotic who… | 65 | 1576 | active |
| photosynthesis-team/piq PyTorch Image Quality (PIQ) is a collection of measures and metrics for image quality assessment in image-to-image tasks, written in pure P… | 23 | 1576 | stable |
| Layout Parser LayoutParser is a Python toolkit for deep learning based document image analysis, offering unified APIs for layout detection models, layout… | 23 | 5776 | maintenance |
| BloodAxe/pytorch-toolbelt A Python library of PyTorch extensions providing building blocks for fast R&D prototyping, including encoder-decoder architectures, special… | 40 | 1575 | active |
| Flux Zygote.jl is a source-to-source automatic differentiation library for Julia that hooks into the Julia compiler to generate gradient (backwa… | 97 | 1574 | active |
| quixio/quix-streams Quix Streams is a pure Python framework for building real-time data pipelines and event-driven applications on Apache Kafka using a Streami… | 96 | 1574 | active |
| ArztSamuel/Applying_EANNs A 2D Unity simulation where cars learn to navigate courses using a feedforward neural network trained by a modified genetic algorithm. It s… | 39 | 1573 | stable |
| ARISE-Initiative/robomimic robomimic is a modular Python framework for robot learning from demonstration, providing standardized demonstration datasets and offline le… | 65 | 1572 | active |
| RightNow-AI/autokernel AutoKernel is an open-source autoresearch pipeline that takes any PyTorch model, profiles it to find GPU kernel bottlenecks, extracts them … | 44 | 1571 | active |
| MLSysOps/MLE-agent MLE-Agent is an LLM-powered CLI agent that acts as a pairing assistant for machine learning engineers and researchers. It automates ML task… | 53 | 1570 | active |
| ZFTurbo/Music-Source-Separation-Training A Python training framework for music source separation models, supporting many architectures such as MDX23C, Demucs, Band Split RoFormer, … | 87 | 1569 | active |
| sdv-dev/CTGAN CTGAN is a Python library of deep learning based synthetic data generators for single-table tabular data, implementing the CTGAN conditiona… | 76 | 1569 | active |
| K-Dense-AI/karpathy Karpathy is an open-source agentic Machine Learning Engineer that trains state-of-the-art ML models using the Claude Agent SDK and Google A… | 58 | 1566 | active |
| Chinese-Text-Classification-Pytorch A PyTorch-based collection of ready-to-run Chinese text classification models including TextCNN, TextRNN, FastText, TextRCNN, BiLSTM with a… | 32 | 5728 | maintenance |
| google-deepmind/bsuite bsuite (Behaviour Suite for Reinforcement Learning) is a collection of carefully-designed experiments from DeepMind that investigate core c… | 79 | 1564 | stable |
| QuantaAlpha/QuantaAlpha QuantaAlpha is an LLM-driven framework for mining quantitative alpha factors using a trajectory-based self-evolving paradigm. Users describ… | 52 | 1563 | active |
| yeemachine/kalidokit KalidoKit is a TypeScript library that converts 3D landmark outputs from Mediapipe/Tensorflow.js face, pose, and hand tracking models into … | 45 | 5720 | maintenance |
| mosaicml/streaming StreamingDataset is a Python library from MosaicML for fast, accurate streaming of training data from cloud object storage (S3, GCS, Azure,… | 66 | 1560 | active |
| kritiksoman/GIMP-ML GIMP-ML is a set of Python plugins that bring computer vision and deep learning models into the GNU Image Manipulation Program (GIMP). It p… | 23 | 1560 | active |
| fwilliams/point-cloud-utils Point Cloud Utils (pcu) is an easy-to-use Python library for processing and manipulating 3D point clouds and triangle meshes, built on C++ … | 49 | 1557 | active |
| decoderesearch/SAELens SAELens is a Python library for training sparse autoencoders (SAEs) on language model activations and analyzing them for mechanistic interp… | 90 | 1555 | active |
| QwenAudio/Fun-ASR Fun-ASR is a family of open-source LLM-based end-to-end speech recognition models from Tongyi Lab, covering Chinese, dialects, accents, and… | 79 | 1553 | active |
| tianrun-chen/SAM-Adapter-PyTorch A PyTorch library that adapts Meta AI's Segment Anything Model (SAM, SAM2, SAM3) to underperforming downstream segmentation tasks using lig… | 64 | 1553 | active |
| AIDE ML AIDE ML is an open-source Python package implementing an LLM-driven agent that uses agentic tree search to autonomously write, debug, and i… | 60 | 1553 | active |
| ZeyueT/AudioX AudioX is a unified multimodal framework for anything-to-audio generation, producing audio and music conditioned on text, video, image, or … | 49 | 1552 | active |
| nubank/fklearn fklearn is a Python machine learning library from Nubank that applies functional programming principles to build, validate, and deploy mode… | 83 | 1550 | active |
| google/tensorstore TensorStore is a C++ and Python library for reading and writing large multi-dimensional arrays with a uniform API across formats like zarr,… | 77 | 1547 | active |
| yuantianyuan01/FastWAM Official PyTorch codebase for Fast-WAM, a World Action Model for robot manipulation that skips test-time future video imagination and gener… | 56 | 1547 | active |
| hustvl/LightningDiT LightningDiT is a research codebase for latent diffusion models implementing VA-VAE and LightningDiT, achieving FID 1.35 on ImageNet-256 wi… | 44 | 1547 | active |
| NirAharon/BoT-SORT BoT-SORT is a state-of-the-art multi-object tracker that combines motion and appearance information with camera motion compensation and an … | 32 | 1547 | active |
| combust/mleap MLeap is a serialization format (Bundle.ML) and portable execution engine for machine learning pipelines, implemented in Scala with Python … | 98 | 1546 | active |
| tensorflow/gnn TensorFlow GNN is a Python library for building Graph Neural Networks on TensorFlow, including a GraphTensor type for heterogeneous graphs,… | 66 | 1546 | active |
| MoonshotAI/Moonlight Moonlight is a 3B/16B Mixture-of-Experts LLM trained with the Muon optimizer, released by Moonshot AI along with a memory- and communicatio… | 33 | 1546 | active |
| RLHFlow/RLHF-Reward-Modeling A collection of training recipes for reward models used in RLHF, covering Bradley-Terry reward models, pairwise preference models, ArmoRM, … | 30 | 1546 | active |
| UCCL UCCL is a high-performance GPU communication library written in C++ that provides collectives (as a drop-in NCCL/RCCL replacement), P2P tra… | 69 | 1545 | active |
| alibaba/FederatedScope FederatedScope is a comprehensive federated learning platform built on PyTorch with an event-driven architecture. It provides convenient us… | 23 | 1545 | active |
| facebookresearch/mmf MMF is a modular PyTorch framework for vision and language multimodal research from Facebook AI Research. It ships reference implementation… | 67 | 5637 | maintenance |
| willmiao/ComfyUI-Lora-Manager A ComfyUI extension that provides a web-based manager for organizing, previewing, downloading, and applying LoRA models with metadata and r… | 85 | 1543 | active |
| ROMP ROMP is a PyTorch-based library and pip-installable API (simple-romp) for real-time monocular multi-person 3D human mesh recovery, implemen… | 23 | 1543 | stable |
| microsoft/vscode-jupyter A Visual Studio Code extension that provides Jupyter notebook support, interactive programming, and computing with language kernels, allowi… | 80 | 1542 | active |
| sobri909/LocoKit LocoKit is a Swift framework for iOS that combines Core Location and Core Motion recording with machine learning based activity type detect… | 25 | 1541 | active |
| TransparentLC/realesrgan-gui A cross-platform graphical interface for the Real-ESRGAN AI image upscaler (with Real-CUGAN support), built in Python with tkinter. It wrap… | 55 | 1540 | active |
| KruxAI/ragbuilder RagBuilder is a Python toolkit that automatically builds an optimal, production-ready Retrieval-Augmented Generation (RAG) pipeline for you… | 65 | 1539 | active |
| Shawn-Shan/fawkes Fawkes is a privacy protection tool from University of Chicago researchers that adds imperceptible adversarial perturbations to photos to p… | 23 | 5614 | maintenance |
| skforecast Skforecast is a Python library for time series forecasting that turns any scikit-learn compatible estimator (LightGBM, XGBoost, CatBoost, K… | 92 | 1536 | active |
| Bumblebee Optimus is a Python library for agile data preparation that provides a unified API over pandas, Dask, cuDF, Dask-cuDF, Vaex, and PySpark. I… | 23 | 1535 | active |
| Nativ Nativ is a free, MIT-licensed macOS desktop application for running open AI models locally on Apple Silicon Macs, built on MLX-VLM. It prov… | 81 | 1534 | active |
| SERL HIL-SERL is a Python library suite for training reinforcement learning policies for precise robotic manipulation using human demonstrations… | 41 | 1533 | active |
| allenzren/open-pi-zero An open-source re-implementation of the pi0 vision-language-action (VLA) model from Physical Intelligence, built on a pre-trained PaliGemma… | 24 | 1533 | active |
| azuwis/pianotrans A simple GUI wrapper and packaging for ByteDance's Piano Transcription with Pedals, a PyTorch system that converts piano audio recordings i… | 65 | 1532 | active |
| interpretml/DiCE DiCE is a Python library that generates diverse counterfactual explanations for any machine learning model, showing feature-perturbed versi… | 33 | 1529 | active |
| kyutai-labs/hibiki Hibiki is a decoder-only model for streaming (simultaneous) speech-to-speech translation, built on the multistream Moshi architecture. It p… | 63 | 1527 | active |
| NVIDIA/DLSS NVIDIA DLSS is the public SDK repository for NVIDIA's RTX Deep Learning Super Sampling, a neural network that boosts game frame rates and g… | 91 | 1526 | active |
| tidymodels/broom broom is an R package that converts statistical model objects from 100+ modeling packages into tidy tibbles. It provides three verbs—tidy()… | 76 | 1524 | active |
| Tencent/TFace TFace is a research platform from Tencent Youtu Lab for trusty face analysis, covering face recognition, face security (anti-spoofing), fac… | 54 | 1524 | active |
| beehive-lab/TornadoVM TornadoVM is a Java programming framework that JIT-compiles JVM bytecode into GPU kernels targeting NVIDIA CUDA, OpenCL, and Apple Metal at… | 98 | 1523 | active |
| geomstats/geomstats Geomstats is an open-source Python package for computations, statistics, and machine learning on manifolds with geometric structures. It pr… | 67 | 1523 | active |
| keras-rl/keras-rl A Python library implementing state-of-the-art deep reinforcement learning algorithms (DQN, DDPG, SARSA, and more) that integrates seamless… | 23 | 5549 | maintenance |
| anishathalye/neural-style A Python command-line tool implementing the neural style transfer algorithm (Gatys et al.) in TensorFlow, applying the style of one image t… | 63 | 5547 | maintenance |
| sail-sg/envpool EnvPool is a C++-based batched environment pool with pybind11 bindings and a thread pool for high-performance parallel RL environment execu… | 96 | 1522 | active |
| o19s/elasticsearch-learning-to-rank An Elasticsearch plugin that integrates Learning to Rank (machine-learned relevance) into Elasticsearch. It stores feature query templates,… | 84 | 1521 | active |
| PrathamLearnsToCode/paper2code An agent skill for coding agents like Claude Code that converts an arXiv paper URL into a working Python implementation. It generates citat… | 45 | 1519 | active |
| mattmireles/gemma-tuner-multimodal A Python tool for LoRA fine-tuning of Gemma 4 and 3n models on text, images, and audio using Apple Silicon's Metal Performance Shaders. It … | 60 | 1516 | active |
| k2-fsa/icefall Icefall is a collection of speech recognition (ASR) and TTS training recipes built on the k2 and lhotse libraries, implemented in Python wi… | 67 | 1512 | active |
| open-thought/reasoning-gym Reasoning Gym is a Python library of procedural dataset generators and algorithmically verifiable reasoning environments for training LLMs … | 60 | 1512 | active |
| NaiboWang/CommandlineConfig A Python library that lets users define experiment configurations as Python dicts or JSON and access parameters via dot notation, while all… | 23 | 1511 | active |
| 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 … | 72 | 1509 | active |
| sepandhaghighi/pycm PyCM is a Python library for computing multi-class confusion matrices and a wide range of per-class and overall evaluation statistics. It a… | 77 | 1507 | stable |
| charlesq34/pointnet Reference implementation of PointNet, a neural network architecture that directly consumes unordered 3D point clouds for classification and… | 32 | 5482 | maintenance |
| wb14123/seq2seq-couplet A deep learning project that generates Chinese couplets (对联) using a seq2seq model built with TensorFlow. It includes training scripts, a w… | 32 | 5480 | maintenance |
| czczup/ViT-Adapter Official PyTorch implementation of ViT-Adapter, an ICLR 2023 Spotlight paper introducing a pre-training-free adapter that lets plain Vision… | 30 | 1506 | stable |
| Flashlight wav2letter++ is Facebook AI Research's end-to-end automatic speech recognition (ASR) toolkit written in C++. It has been consolidated into … | 67 | 5476 | maintenance |
| CUT3R/CUT3R CUT3R is the official PyTorch implementation of 'Continuous 3D Perception Model with Persistent State' (CVPR 2025 Oral), a stateful recurre… | 35 | 1499 | active |
| NJU-PCALab/STAR STAR is a research implementation of an ICCV 2025 paper performing real-world video super-resolution using spatial-temporal augmentation wi… | 32 | 1498 | active |
| open-mmlab/mmengine MMEngine is the foundational training engine library for OpenMMLab projects, providing a unified training loop, config system, registry, ho… | 68 | 1496 | active |
| NVlabs/Fast-FoundationStereo Fast-FoundationStereo is NVIDIA's official PyTorch implementation of a real-time zero-shot stereo matching model family, accepted to CVPR 2… | 59 | 1496 | active |
| pygod-team/pygod PyGOD is a Python library for graph outlier detection (anomaly detection) built on PyTorch and PyTorch Geometric. It provides 10+ graph-bas… | 23 | 1495 | active |
| ucb-bar/gemmini Gemmini is Berkeley's open-source generator for parameterizable systolic-array DNN hardware accelerators, written in Chisel (Scala) and int… | 66 | 1493 | active |
| ibab/tensorflow-wavenet A TensorFlow implementation of DeepMind's WaveNet generative neural network architecture for raw audio waveform generation. It provides tra… | 32 | 5422 | maintenance |
| google-deepmind/graph_nets DeepMind's library for building graph networks (graph neural networks) in TensorFlow and Sonnet, based on the 'Relational inductive biases,… | 32 | 5407 | maintenance |
| cheind/py-motmetrics py-motmetrics is a Python library for evaluating multiple object tracking (MOT) results with MOTChallenge-aligned CLEAR MOT, Identity, and … | 61 | 1488 | active |
| ModelOriented/DALEX DALEX (moDel Agnostic Language for Exploration and eXplanation) is a library for exploring, explaining, and visualizing the behavior of pre… | 61 | 1486 | active |
| reczoo/FuxiCTR FuxiCTR is an open-source Python library for click-through rate (CTR) prediction built on PyTorch and TensorFlow. It offers a configurable,… | 75 | 1481 | active |
| SciSharp/NumSharp NumSharp is a .NET library providing NumPy-shaped N-dimensional arrays with broadcasting, slicing views, dtype-aware math, and runtime-gene… | 92 | 1480 | active |
| alxndrTL/mamba.py A simple, readable pure-PyTorch (plus MLX) implementation of the Mamba state-space model architecture with a parallel scan for efficient tr… | 50 | 1480 | active |
| sb-ai-lab/LightAutoML LightAutoML (LAMA) is a Python framework for automatic machine learning model creation (AutoML) supporting tabular, time series, image, and… | 73 | 1479 | active |
| salesforce/CodeTF CodeTF is a Python transformer library for code large language models, providing unified interfaces for training, fine-tuning, and inferenc… | 10 | 1478 | active |