Open-source machine-learning software
5374 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.
5374 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| luo3300612/Visualizer A lightweight Python library that extracts attention maps and other local variables from deep inside PyTorch models for visualization. It w… | 32 | 1272 | stable |
| NVlabs/stylegan2-ada-pytorch Official PyTorch implementation of StyleGAN2-ADA, a generative adversarial network with adaptive discriminator augmentation for training wi… | 32 | 4487 | maintenance |
| aiming-lab/Agent0 Agent0 Series is a research framework for training self-evolving LLM agents from zero external data via tool-integrated reasoning and co-ev… | 55 | 1271 | active |
| stardist/stardist StarDist is a Python library for object detection and instance segmentation in 2D and 3D microscopy images using star-convex shapes, built … | 54 | 1271 | stable |
| microsoft/BioGPT BioGPT is Microsoft's domain-specific generative Transformer language model pre-trained on biomedical text, with implementation code and pr… | 10 | 4486 | maintenance |
| withoutbg/withoutbg-python A Python SDK (pip install withoutbg) for removing image backgrounds, offering a free local open-weights ONNX model and an optional paid clo… | 79 | 1270 | active |
| leoxiaobin/deep-high-resolution-net.pytorch Official PyTorch implementation of HRNet (Deep High-Resolution Representation Learning for Human Pose Estimation, CVPR 2019), which maintai… | 32 | 4478 | maintenance |
| water8394/flink-recommandSystem-demo A real-time product recommendation system built on Apache Flink, demonstrating streaming computation of product popularity, user profiles, … | 32 | 4475 | maintenance |
| ICT-FinD-Lab/alphagen AlphaGen is a Python research library that automatically generates formulaic alpha (predictive) stock factors using reinforcement learning,… | 67 | 1268 | active |
| amaiya/ktrain ktrain is a lightweight Python wrapper around TensorFlow Keras that provides pre-canned, low-code models for text, vision, graph, and tabul… | 23 | 1268 | active |
| tensorflow/model-analysis TensorFlow Model Analysis (TFMA) is a Python library for evaluating TensorFlow models on large datasets in a distributed manner. It compute… | 77 | 1267 | active |
| meta-pytorch/data TorchData is a PyTorch library providing scalable, performant data loading utilities, including StatefulDataLoader, a drop-in replacement f… | 72 | 1267 | active |
| rlawjdghek/StableVITON StableVITON is the official PyTorch implementation of a CVPR 2024 paper that performs image-based virtual try-on using a pre-trained latent… | 44 | 1267 | stable |
| Bjarten/early-stopping-pytorch A small PyTorch utility package providing an EarlyStopping class that monitors validation loss during training and stops when it stops impr… | 34 | 1267 | stable |
| lucidrains/flamingo-pytorch A PyTorch implementation of DeepMind's Flamingo visual language model architecture, providing the Perceiver Resampler and Gated Cross-Atten… | 23 | 1267 | active |
| OpenNRE OpenNRE is an open-source Python toolkit for neural relation extraction, extracting relation triples between entities from plain text. It u… | 32 | 4467 | maintenance |
| facebookresearch/DrQA DrQA is a PyTorch implementation of a system for open-domain question answering that combines document retrieval over Wikipedia with a neur… | 10 | 4467 | maintenance |
| XPixelGroup/HYPIR Official PyTorch implementation of HYPIR, a SIGGRAPH 2025 method that harnesses diffusion-yielded score priors for image restoration. It pr… | 36 | 1266 | active |
| ToniRV/NeRF-SLAM NeRF-SLAM is a real-time dense monocular SLAM system that combines neural radiance fields (Instant-NGP) with probabilistic volumetric fusio… | 32 | 1266 | active |
| pymc-labs/pymc-marketing PyMC-Marketing is a Python library of Bayesian marketing analytics models built on PyMC, including Marketing Mix Modeling (MMM), Customer L… | 95 | 1265 | active |
| metadriverse/metadrive MetaDrive is an open-source, lightweight driving simulator built for AI and autonomy research, supporting compositional scene synthesis and… | 67 | 1265 | active |
| fastgs/FastGS FastGS is a general acceleration framework for 3D Gaussian Splatting that trains scenes in roughly 100 seconds using multi-view consistent … | 46 | 1265 | active |
| JonathonLuiten/TrackEval TrackEval is a Python library for evaluating multi-object tracking (MOT) algorithms, implementing metrics such as HOTA, CLEARMOT, IDF1, VAC… | 32 | 1265 | stable |
| Deformable 3D Gaussians Official PyTorch implementation of the CVPR 2024 paper 'Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction'. … | 19 | 1264 | stable |
| bryandlee/animegan2-pytorch A PyTorch implementation of AnimeGANv2, a GAN-based image-to-image style transfer model that converts photos into anime-style images. It pr… | 32 | 4457 | maintenance |
| MyoHub/myosuite MyoSuite is a collection of musculoskeletal environments and tasks simulated with the MuJoCo physics engine and wrapped in the OpenAI gym A… | 95 | 1263 | active |
| mjpost/sacrebleu SacreBLEU is a Python library and CLI tool for computing shareable, comparable, and reproducible BLEU, chrF, and TER scores for machine tra… | 70 | 1263 | active |
| MemeMeow-Studio/MemeMeow MemeMeow is a self-hosted meme/sticker management and retrieval application that lets users find images by describing the desired scene in … | 66 | 1263 | active |
| Francis-Rings/StableAvatar StableAvatar is an end-to-end video diffusion transformer that generates infinite-length, high-quality talking avatar videos from a referen… | 62 | 1263 | active |
| cvg/depthsplat DepthSplat is a PyTorch research library implementing a CVPR 2025 model that connects Gaussian splatting with single/multi-view depth estim… | 52 | 1262 | active |
| meta-pytorch/attention-gym Attention Gym is a collection of tools, examples, and reference implementations for working with PyTorch's FlexAttention API. It provides a… | 91 | 1260 | active |
| PyDMD/PyDMD PyDMD is a Python package implementing Dynamic Mode Decomposition (DMD) and its many variants (mrDMD, HODMD, etc.) for extracting spatiotem… | 56 | 1260 | active |
| Fictionarry/ER-NeRF ER-NeRF is the official PyTorch implementation of an ICCV 2023 paper on region-aware Neural Radiance Fields for high-fidelity talking portr… | 21 | 1259 | stable |
| nv-tlabs/GET3D GET3D is NVIDIA's PyTorch implementation of a generative model that synthesizes high-quality 3D textured meshes (cars, chairs, animals, bui… | 32 | 4433 | maintenance |
| plurai-ai/intellagent IntellAgent is a Python framework for diagnosing and optimizing conversational LLM agents through simulated, realistic synthetic user inter… | 55 | 1258 | active |
| thu-ml/SpargeAttn SpargeAttn is the official implementation of a training-free sparse and quantized attention method that accelerates inference for language,… | 48 | 1257 | active |
| martinpacesa/BindCraft BindCraft is a Python-based computational pipeline for de novo protein binder design that combines AlphaFold2 backpropagation, ProteinMPNN,… | 70 | 1256 | active |
| Roblox/cube Cube is Roblox's open-source family of foundation models for 3D intelligence, including text-to-3D shape generation and part-controllable m… | 55 | 1256 | active |
| Maia Chess Maia is a collection of human-like neural network chess engines trained on millions of human games, targeting skill levels from ELO 1100 to… | 57 | 1255 | active |
| unum-cloud/UForm UForm is a compact multimodal AI library providing tiny image-text embedding models (64-768 dimensions, Matryoshka-style) and small generat… | 50 | 1254 | active |
| Equim-chan/mjai-reviewer A Rust CLI tool that reviews riichi mahjong game logs using mjai-compatible AI engines such as Mortal and akochan. It fetches logs from Ten… | 23 | 1254 | active |
| automl/SMAC3 SMAC3 is a Python library for Bayesian Optimization used to tune hyperparameters of machine learning algorithms and configure arbitrary alg… | 89 | 1253 | active |
| zinggAI/zingg Zingg is an ML-based tool for scalable master data management, entity resolution, identity resolution, and record deduplication. It runs on… | 82 | 1253 | active |
| VainF/pytorch-msssim A PyTorch library providing fast, differentiable SSIM and MS-SSIM image quality metrics using separable Gaussian filtering for speed. It ca… | 23 | 1253 | stable |
| facebookresearch/llm-transparency-tool An interactive toolkit from Meta Research for analyzing the internal workings of Transformer-based language models. It visualizes contribut… | 10 | 1253 | active |
| sentinel-hub/eo-learn eo-learn is a collection of open-source Python packages for accessing and processing spatio-temporal satellite imagery, built around modula… | 65 | 1251 | active |
| 3DTopia/OpenLRM OpenLRM is an open-source PyTorch implementation of Large Reconstruction Models (LRM) that reconstruct 3D objects (meshes and rendered vide… | 18 | 1250 | active |
| google-deepmind/android_env AndroidEnv is a Python library from DeepMind that exposes an Android device (real or emulated) as a Reinforcement Learning environment. Age… | 83 | 1249 | active |
| wannesm/dtaidistance A Python library for computing time series distances, most notably Dynamic Time Warping (DTW), with a fast C implementation exposed via Cyt… | 84 | 1248 | stable |
| facebookresearch/home-robot HomeRobot is an open-source robotics stack from Meta AI for mobile manipulation tasks on low-cost hardware like the Hello Robot Stretch. It… | 23 | 1247 | active |
| LTH14/fractalgen A PyTorch implementation of Fractal Generative Models (FractalGen), enabling pixel-by-pixel high-resolution image generation. It includes p… | 21 | 1247 | active |
| abewley/sort SORT is a barebones Python implementation of a simple online and realtime multiple object tracking algorithm for 2D video sequences, based … | 32 | 4386 | maintenance |
| Acly/comfyui-inpaint-nodes A set of custom nodes for ComfyUI that improve image inpainting and outpainting workflows. It integrates the Fooocus inpaint model for SDXL… | 70 | 1246 | active |
| marian42/mesh_to_sdf A Python library that computes approximate signed distance fields (SDFs) for arbitrary triangle meshes, including non-watertight, self-inte… | 32 | 1246 | stable |
| NVlabs/alpasim AlpaSim is an open-source, Python-based autonomous vehicle simulation platform for developing and testing end-to-end AV policies in closed … | 72 | 1245 | active |
| ZHKKKe/MODNet MODNet is a deep learning model for real-time portrait matting (background removal) that requires only an RGB image as input, with no trima… | 32 | 4376 | maintenance |
| HJYao00/Mulberry Mulberry is a research implementation of an o1-like multimodal large language model (MLLM) that performs step-by-step reasoning and reflect… | 46 | 1244 | active |
| Audio Webui An all-in-one web UI for audio-related neural networks, bundling text-to-speech (Bark), voice conversion/cloning (RVC), and text-to-audio/m… | 27 | 1244 | active |
| alibaba/Tora Tora is Alibaba's official implementation of a trajectory-oriented Diffusion Transformer (DiT) for controllable video generation, integrati… | 61 | 1243 | active |
| FenTechSolutions/CausalDiscoveryToolbox A Python library for causal inference in graphs and pairwise settings, implementing many algorithms for graph structure recovery from obser… | 49 | 1242 | active |
| showlab/Tune-A-Video Tune-A-Video is the official PyTorch implementation of an ICCV 2023 paper that fine-tunes pre-trained text-to-image diffusion models (like … | 32 | 4363 | maintenance |
| Brian Brian2 is a free, open-source, clock-driven simulator for spiking neural networks written in Python. It lets scientists define neuron and s… | 76 | 1241 | stable |
| declare-lab/tango Tango is a family of latent diffusion models for text-to-audio generation, with Tango 2 improving prompt alignment via DPO-based fine-tunin… | 42 | 1241 | active |
| pythongosssss/ComfyUI-WD14-Tagger A ComfyUI custom node extension that interrogates images to extract booru-style tags using WD 1.4 tagger models (ONNX-based). It integrates… | 40 | 1241 | active |
| bowang-lab/MedRAX MedRAX is a medical reasoning agent framework that integrates chest X-ray analysis tools (segmentation, grounding, report generation, disea… | 40 | 1241 | active |
| jcjohnson/fast-neural-style A Torch (Lua) implementation of feedforward neural style transfer from the ECCV 2016 paper 'Perceptual Losses for Real-Time Style Transfer … | 32 | 4362 | maintenance |
| mrousavy/react-native-fast-tflite A high-performance TensorFlow Lite library for React Native built on Nitro Modules, using the low-level C/C++ TFLite core API with zero-cop… | 80 | 1240 | active |
| apchenstu/TensoRF TensoRF is a PyTorch implementation of the ECCV 2022 paper 'TensoRF: Tensorial Radiance Fields', which models and reconstructs radiance fie… | 41 | 1239 | stable |
| zai-org/SCAIL-2 Official implementation of SCAIL-2, an open-source model for end-to-end controlled character animation that drives character videos from re… | 55 | 1238 | active |
| facebookresearch/deit Official PyTorch repository for DeiT and related vision transformer architectures (CaiT, ResMLP, PatchConvnet, DeiT III), providing trainin… | 10 | 4348 | maintenance |
| bytedance/USO USO is ByteDance's open-source unified style- and subject-driven image generation model based on diffusion (FLUX), combining any subject wi… | 33 | 1237 | active |
| sh-lee-prml/HierSpeechpp Official PyTorch implementation of HierSpeech++, a fast zero-shot speech synthesizer for text-to-speech and voice conversion based on hiera… | 29 | 1237 | active |
| pytorch/serve TorchServe is a flexible, production-ready model server for serving, optimizing, and scaling PyTorch models over HTTP with support for CPU,… | 10 | 4344 | maintenance |
| ZED SDK The ZED SDK is a cross-platform spatial perception library for Stereolabs ZED stereo cameras, providing depth sensing, SLAM, 3D reconstruct… | 84 | 1236 | active |
| ElectricAlexis/NotaGen NotaGen is a symbolic music generation model that produces high-quality classical sheet music using LLM-style training paradigms: pre-train… | 29 | 1236 | active |
| SciML/NeuralPDE.jl NeuralPDE.jl is a Julia library of physics-informed neural network (PINN) solvers for ordinary, stochastic, and partial differential equati… | 99 | 1235 | active |
| open-mmlab/playground OpenMMLab Playground is a central hub collecting and showcasing community projects that extend OpenMMLab libraries with Segment Anything Mo… | 31 | 1235 | active |
| qualcomm/ai-hub-models Qualcomm AI Hub Models is a curated collection of 300+ state-of-the-art machine learning models (vision, audio, speech, generative AI) pre-… | 90 | 1230 | active |
| OpenTSLM/OpenTSLM OpenTSLM is a family of Time-Series Language Models that integrate time series as a native modality into pretrained LLMs (Llama, Gemma), en… | 58 | 1230 | active |
| lucidrains/deep-daze Deep Daze is a simple command line tool for text-to-image generation that combines OpenAI's CLIP with a Siren implicit neural representatio… | 23 | 4316 | maintenance |
| python-adaptive/adaptive Adaptive is an open-source Python library for parallel active learning of mathematical functions. It intelligently selects the most informa… | 87 | 1229 | active |
| microsoft/MInference MInference is a Microsoft library that accelerates long-context LLM inference using dynamic sparse attention, reducing pre-fill latency by … | 60 | 1229 | active |
| Tencent-Hunyuan/HunyuanCustom HunyuanCustom is a multimodal-driven customized video generation framework built on HunyuanVideo, supporting image, text, audio, and video … | 37 | 1229 | active |
| cp2k/cp2k CP2K is an open-source quantum chemistry and solid state physics package for atomistic simulations of molecular, liquid, periodic, and biol… | 84 | 1228 | stable |
| sgl-project/SpecForge SpecForge is a Python framework from the SGLang team for training speculative decoding models such as EAGLE/EAGLE3 draft heads. Trained mod… | 64 | 1228 | active |
| MotrixLab/SMPLer-X Official code for SMPLer-X, a family of foundation models for expressive human pose and shape estimation (EHPS) that unifies body, hand, an… | 56 | 1228 | stable |
| NVIDIA/BigVGAN BigVGAN is NVIDIA's official PyTorch implementation of a universal neural vocoder (ICLR 2023) that generates high-fidelity raw audio wavefo… | 23 | 1228 | stable |
| datawhalechina/torch-rechub Torch-RecHub is a lightweight PyTorch framework for building recommendation system models with 30+ out-of-the-box algorithms covering ranki… | 96 | 1227 | active |
| zkonduit/ezkl EZKL is a Rust-based library and command-line tool that converts deep learning models and arbitrary computational graphs (exported as ONNX)… | 69 | 1227 | active |
| MoonshotAI/Kimi-VL Kimi-VL is an open-source Mixture-of-Experts vision-language model (VLM) with a 2.8B activated parameter language decoder, offering multimo… | 31 | 1227 | active |
| GuitarML/NeuralPi NeuralPi is a DIY Raspberry Pi 4-based guitar pedal that uses neural networks to emulate real amplifiers and distortion/overdrive pedals in… | 23 | 1227 | active |
| alibaba/x-deeplearning X-DeepLearning (XDL) is an industrial deep learning framework from Alibaba optimized for high-dimension sparse data scenarios such as adver… | 23 | 4301 | maintenance |
| run-house/kubetorch Kubetorch is a Python library that lets you distribute and run ML workloads (training, inference, data processing) on Kubernetes directly f… | 76 | 1225 | active |
| Bolin97/GongBU GongBU is a self-hosted, no-code web platform for fine-tuning, evaluating, and deploying large language models, built on Transformers and P… | 50 | 1225 | active |
| Project-MONAI/research-contributions A collection of peer-reviewed research prototype implementations built on the MONAI framework for medical imaging AI. It serves as a fast-t… | 39 | 1225 | active |
| nfstream/nfstream NFStream is a multiplatform Python framework for fast, flexible network flow data analysis from live interfaces or pcap files. It provides … | 76 | 1224 | stable |
| rohanpsingh/LearningHumanoidWalking A Python research codebase for training humanoid robots to walk using deep reinforcement learning (PPO) in MuJoCo simulation. It provides e… | 66 | 1224 | active |
| mcmonkeyprojects/sd-dynamic-thresholding A Stable Diffusion extension that enables using higher CFG scale values without color artifacts by clamping latents between sampling steps.… | 33 | 1224 | active |
| Truss Truss is a Python CLI and packaging framework for deploying and serving AI/ML models in production, primarily on the Baseten platform. It h… | 96 | 1223 | active |
| FEniCSx DOLFINx is the next-generation computational environment of the FEniCS Project, implemented in C++ with Python bindings, for solving partia… | 93 | 1222 | active |