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 |
|---|---|---|---|
| NVlabs/InstantSplat InstantSplat is a research framework for photorealistic 3D scene reconstruction from extremely sparse image views using Gaussian Splatting,… | 30 | 1704 | active |
| ethanjlimgit/android-action-kernel An open-source Python library that lets AI agents control native Android apps, enabling automation of mobile-first workflows like logistics… | 42 | 1703 | active |
| PaddlePaddle/PaddleVideo PaddleVideo is a video understanding toolkit built on PaddlePaddle, offering state-of-the-art models for action recognition, temporal actio… | 23 | 1702 | active |
| lucidrains/alphafold3-pytorch A PyTorch implementation of Google DeepMind's Alphafold 3 model for protein and molecular structure prediction. It is a research-oriented r… | 67 | 1699 | active |
| MLRun MLRun is an open-source MLOps and AI orchestration framework for building, training, deploying, and monitoring machine learning and generat… | 92 | 1697 | active |
| scvi-tools scvi-tools is a Python library for deep probabilistic modeling and analysis of single-cell and spatial omics data, built on PyTorch, PyTorc… | 92 | 1697 | stable |
| shubham-goel/4D-Humans 4DHumans is a Python research codebase implementing HMR 2.0, a transformer-based model for 3D human mesh recovery from single images, plus … | 56 | 1695 | active |
| stephansturges/WALDO WALDO is an open-source object detection model based on a YOLOv8 backbone, trained with a synthetic data pipeline to detect people, vehicle… | 32 | 1695 | active |
| sedthh/pyxelate Pyxelate is a Python library and CLI tool that converts images into 8-bit pixel art by downsampling and learning a reduced color palette. I… | 47 | 1694 | active |
| tensorly/tensorly TensorLy is a Python library for tensor learning, providing tensor decomposition, tensor algebra, and tensor regression with a simple API. … | 64 | 1693 | stable |
| TensorPack Tensorpack is a high-level neural network training interface built on graph-mode TensorFlow, focused on training speed and flexibility for … | 23 | 6284 | maintenance |
| elixir-nx/axon Axon is a neural network library for Elixir built on top of Nx numerical definitions. It provides a functional API, a high-level model crea… | 89 | 1692 | active |
| espressif/esp-csi Espressif's official examples and tools for Wi-Fi Channel State Information (CSI) on ESP32-series chips, enabling non-contact wireless sens… | 64 | 1691 | active |
| py-why/causal-learn causal-learn is a Python library for causal discovery, implementing classical and state-of-the-art algorithms to recover causal structure f… | 87 | 1689 | active |
| intelligent-machine-learning/dlrover DLRover is an automatic distributed deep learning system that manages training of large AI models on Kubernetes and Ray clusters. It provid… | 80 | 1689 | active |
| hecomi/uLipSync uLipSync is a Unity plug-in that performs lip-sync by analyzing audio in real time or pre-baked, extracting MFCC features via the Job Syste… | 46 | 1688 | active |
| pytorch-tabular/pytorch_tabular PyTorch Tabular is a Python library providing a unified, high-level interface for deep learning models on tabular data, built on PyTorch an… | 73 | 1686 | active |
| Anemll/Anemll ANEMLL is an open-source Python library and toolchain for converting and running large language models on the Apple Neural Engine (ANE) via… | 70 | 1686 | active |
| ckiplab/ckiptagger CkipTagger is a Python library implementing neural CKIP-style Chinese NLP tools for word segmentation, part-of-speech tagging, and named en… | 33 | 1686 | stable |
| takuseno/d3rlpy d3rlpy is a Python library for offline and online deep reinforcement learning built on PyTorch, offering state-of-the-art algorithms throug… | 45 | 1684 | active |
| kijai/ComfyUI-FramePackWrapper A ComfyUI custom node wrapper for FramePack, enabling next-frame video generation from images using HunyuanVideo-based diffusion models. It… | 44 | 1683 | active |
| franciszzj/Leffa Leffa is a diffusion-based framework for controllable person image generation, supporting virtual try-on and pose transfer via a regulariza… | 37 | 1683 | active |
| bytedance/Sa2VA Sa2VA is a family of research models and codebases from ByteDance that combine SAM-2 with multimodal LLMs for pixel-level grounded understa… | 67 | 1682 | active |
| williamyang1991/DualStyleGAN Official PyTorch implementation of DualStyleGAN, a CVPR 2022 model for exemplar-based high-resolution (1024px) portrait style transfer. It … | 32 | 1682 | stable |
| explosion/sense2vec A Python library implementing sense2vec, contextually-keyed word vectors that learn embeddings for multi-word phrases and part-of-speech-di… | 52 | 1681 | stable |
| google/vizier Open Source Vizier is a Python-based service and library for black-box and hyperparameter optimization, based on Google's internal Vizier t… | 79 | 1680 | active |
| absadiki/subsai Subs AI is a subtitles generation tool available as a Web-UI, CLI, and Python package, powered by OpenAI's Whisper and its variants (faster… | 63 | 1680 | active |
| MgArcher/Text_select_captcha A PyTorch-based deep learning system that recognizes click-based (text-select) CAPTCHAs by detecting and ordering Chinese character positio… | 65 | 1678 | active |
| maziarraissi/PINNs The original reference implementation of Physics-Informed Neural Networks (PINNs), which train neural networks to solve and discover nonlin… | 58 | 6217 | maintenance |
| microsoft/Mage Mage is a family of lightweight 4B-parameter multimodal models from Microsoft, including Mage-VL for image and video understanding and Mage… | 55 | 1677 | active |
| elixir-nx/bumblebee Bumblebee is an Elixir library providing pre-trained neural network models built on Axon, with integration for downloading models from Hugg… | 94 | 1674 | active |
| PRML/PRMLT A self-contained MATLAB toolbox implementing the machine learning algorithms from Bishop's textbook 'Pattern Recognition and Machine Learni… | 23 | 6201 | maintenance |
| sunlabuiuc/PyHealth PyHealth is an open-source Python toolkit for clinical deep learning, unifying healthcare datasets (EHRs, physiological signals, medical im… | 95 | 1673 | active |
| Gen-Verse/MMaDA MMaDA is an open-source family of multimodal large diffusion language models that unify textual reasoning, multimodal understanding, and te… | 46 | 1673 | active |
| ZrrSkywalker/Personalize-SAM PerSAM is the official implementation of 'Personalize Segment Anything Model with One Shot', which customizes the Segment Anything Model (S… | 30 | 1673 | active |
| intel/auto-round AutoRound is Intel's advanced quantization toolkit for LLMs and vision-language models, using sign-gradient descent to achieve high accurac… | 94 | 1672 | active |
| meyda/meyda Meyda is a JavaScript audio feature extraction library that computes standard signal features like RMS, spectral centroid, and spectral fla… | 23 | 1672 | stable |
| zihangdai/xlnet XLNet is a generalized autoregressive pretraining method for language representation learning, built on Transformer-XL. This repo provides … | 32 | 6189 | maintenance |
| Tencent/AngelSlim AngelSlim is a Python toolkit from Tencent for compressing large language models and related architectures (VLMs, diffusion, audio models) … | 70 | 1669 | active |
| mit-han-lab/torchquantum TorchQuantum is a PyTorch-based framework for quantum computing simulation, supporting statevector and pulse-level simulation on GPUs with … | 60 | 1669 | active |
| nwojke/deep_sort A Python implementation of Deep SORT, a multi-object tracking algorithm that extends SORT with a deep appearance descriptor for robust data… | 33 | 6179 | maintenance |
| vinhhien112/img2obj img2obj is a Codex plugin that turns an attached object image into a code-only, animation-ready procedural Three.js model. It guides the AI… | 53 | 1668 | active |
| tkarras/progressive_growing_of_gans Official TensorFlow implementation of the ICLR 2018 NVIDIA paper 'Progressive Growing of GANs', which trains generators and discriminators … | 32 | 6176 | maintenance |
| JiuhaiChen/BLIP3o Official implementation of the BLIP3o-Series, a unified autoregressive-plus-diffusion model for text-to-image generation and editing. It co… | 41 | 1667 | active |
| apple/ml-mobileclip Official implementation of Apple's MobileCLIP and MobileCLIP2, fast image-text contrastive (CLIP-style) models optimized for mobile latency… | 68 | 1664 | active |
| Stability-AI/stable-virtual-camera Stable Virtual Camera (SEVA) is a generalist diffusion model for novel view synthesis that generates 3D-consistent views of a scene from an… | 51 | 1664 | active |
| ZJU4HealthCare/HealthGPT HealthGPT is a medical multimodal large language model family unifying medical image comprehension and generation via heterogeneous knowled… | 60 | 1662 | active |
| IPAdapter plus A ComfyUI custom node implementation of IPAdapter models for image-to-image conditioning in Stable Diffusion workflows. It transfers the su… | 32 | 6142 | maintenance |
| thtrieu/darkflow Darkflow is a Python library that translates Darknet's YOLO neural network definitions to TensorFlow, enabling real-time object detection a… | 32 | 6139 | maintenance |
| Data-Centric-AI-Community/fg-data-synthetic A Python library for generating synthetic tabular and time-series data using state-of-the-art generative models such as GANs (including CTG… | 87 | 1659 | active |
| thunil/TecoGAN TecoGAN is the official source code for a temporally coherent GAN for video super-resolution, published at SIGGRAPH/ACM TOG. It includes in… | 32 | 6133 | maintenance |
| Robbyant/lingbot-depth LingBot-Depth is a PyTorch-based model and toolkit for masked depth modeling that transforms incomplete, noisy depth sensor data into metri… | 53 | 1655 | active |
| tableau/TabPy TabPy is the Tableau Python Server, an Analytics Extensions implementation that lets Tableau users execute Python scripts and saved functio… | 92 | 1654 | active |
| XueZeyue/DanceGRPO Official implementation of DanceGRPO, a framework applying Group Relative Policy Optimization (GRPO) to fine-tune visual generation models … | 37 | 1654 | active |
| chineseocr A Python OCR toolkit that combines YOLO3-based text detection with CRNN/Dense recognition for Chinese and English text in natural scene ima… | 32 | 6113 | maintenance |
| taki0112/UGATIT Official TensorFlow implementation of U-GAT-IT, an unsupervised image-to-image translation model using attention modules and adaptive layer… | 32 | 6113 | maintenance |
| skrub-data/skrub skrub is a Python library that facilitates machine learning with dataframes, providing preprocessing, encoding, and wrangling tools for tab… | 92 | 1653 | active |
| mhamilton723/FeatUp FeatUp is a model-agnostic framework that upsamples the spatial resolution of deep neural network features by 16-32x without changing their… | 17 | 1653 | active |
| NVIDIAGameWorks/rtx-remix NVIDIA RTX Remix is an open-source platform for remastering classic DirectX 8/9 games with RTX path tracing, DLSS, and AI-upgraded textures… | 75 | 1652 | active |
| GoMLX GoMLX is an accelerated machine learning and math framework for Go, comparable to PyTorch/JAX/TensorFlow. It offers differentiable operator… | 96 | 1651 | active |
| kotaro-kinoshita/yomitoku YomiToku is an AI-powered document image analysis engine specialized for Japanese, providing full-text OCR, layout analysis, table structur… | 88 | 1649 | active |
| InterDigitalInc/CompressAI CompressAI is a PyTorch library and evaluation platform for end-to-end learned data compression research. It provides custom layers, entrop… | 76 | 1648 | active |
| opendilab/LightZero LightZero is a lightweight, open-source Python toolkit that unifies Monte Carlo Tree Search (MCTS) with deep reinforcement learning, implem… | 66 | 1647 | active |
| symforce-org/symforce SymForce is a Python/C++ library for fast symbolic computation, code generation, and tangent-space nonlinear optimization aimed at robotics… | 89 | 1646 | active |
| bowang-lab/scGPT scGPT is a foundation model for single-cell multi-omics built with a generative transformer, providing pretrained checkpoints and a Python … | 64 | 1646 | active |
| bytedance/DreamO DreamO is the official PyTorch implementation of a unified framework for image customization, built on FLUX diffusion models. It supports t… | 33 | 1646 | active |
| JIA-Lab-research/ControlNeXt ControlNeXt is the official implementation of a controllable generation method for images and videos, built on Stable Diffusion XL, Stable … | 24 | 1646 | active |
| TonyJiangWJ/Ant-Forest An AutoJS-based automation script for Android that automatically collects energy in Alipay's Ant Forest feature. It uses image recognition … | 52 | 1645 | active |
| HumanSignal/Adala Adala is a Python framework for building autonomous data labeling agents powered by LLMs. Agents learn skills iteratively from a ground tru… | 63 | 1644 | active |
| RQLuo/MixTeX-Latex-OCR MixTeX is a multimodal OCR application that recognizes LaTeX formulas, tables, and mixed Chinese/English text from images, running entirely… | 19 | 1641 | active |
| Lucchetto/SuperImage SuperImage is an Android application that upscales low-resolution images using a Real-ESRGAN neural network running on-device via the MNN d… | 10 | 1641 | active |
| AnswerDotAI/rerankers A lightweight, dependency-free Python library providing a unified API for using all common reranking and cross-encoder models. It lets deve… | 39 | 1640 | active |
| yenchenlin/nerf-pytorch A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the original paper's results for synthesizing novel views of comp… | 32 | 6052 | maintenance |
| CoinCheung/BiSeNet A PyTorch implementation of the BiSeNet V1 and V2 real-time semantic segmentation models, with pretrained weights for Cityscapes, COCO-Stuf… | 67 | 1639 | active |
| pangxiaobin/image-matting A free open-source desktop AI image tool built with pywebview and Vue that performs local background removal (matting) using the RMBG-1.4 m… | 76 | 1638 | active |
| datamade/usaddress usaddress is a Python library that parses unstructured United States address strings into labeled address components using a conditional ra… | 44 | 1638 | active |
| ShengranHu/ADAS ADAS (Automated Design of Agentic Systems) is the official research code for the ICLR 2025 paper introducing Meta Agent Search, where a met… | 24 | 1638 | active |
| Higgsfield Higgsfield is an open-source GPU orchestration and machine learning framework for fault-tolerant, distributed training of very large models… | 67 | 6047 | maintenance |
| VNCCS VNCCS is a ComfyUI custom node suite providing an end-to-end pipeline for generating visual novel character sprites with consistent appeara… | 84 | 1635 | active |
| luanfujun/deep-painterly-harmonization Research code implementing the 'Deep Painterly Harmonization' algorithm, which seamlessly blends a pasted object into a painting's style us… | 32 | 6033 | maintenance |
| yoshitomo-matsubara/torchdistill torchdistill is a modular, configuration-driven PyTorch framework for knowledge distillation and general deep learning experiments, requiri… | 83 | 1633 | active |
| jeffffffli/HybrIK HybrIK is the official PyTorch implementation of a hybrid analytical-neural inverse kinematics method for 3D human pose and shape estimatio… | 23 | 1632 | stable |
| facebookresearch/DomainBed DomainBed is a PyTorch suite containing benchmark datasets and algorithms for domain generalization research. It implements many algorithms… | 10 | 1632 | active |
| mlcommons/inference Reference implementations of the MLPerf Inference benchmark suite, the industry-standard benchmarks for measuring how fast ML systems run m… | 79 | 1631 | active |
| Fantasy-AMAP/fantasy-talking FantasyTalking is a research codebase and model for generating realistic talking portrait videos from a single image and an audio clip, bui… | 45 | 1631 | active |
| OminousIndustries/PhoneDriver PhoneDriver is a Python-based mobile automation agent that uses Qwen3-VL vision-language models to visually understand and control Android … | 35 | 1630 | active |
| Snorkel Snorkel is a Python library for programmatically building and managing training data using weak supervision, letting users write labeling f… | 65 | 6010 | maintenance |
| SyncTalk SyncTalk is the official PyTorch implementation of a CVPR 2024 paper that synthesizes speech-driven, synchronized talking head videos using… | 43 | 1628 | active |
| scikit-learn-contrib/boruta_py A Python implementation of the Boruta all-relevant feature selection method, built on scikit-learn. It identifies all features carrying pre… | 42 | 1628 | active |
| Picsart-AI-Research/StreamingT2V StreamingT2V is a research codebase (CVPR 2025) implementing an autoregressive technique that turns short text-to-video diffusion models li… | 28 | 1628 | active |
| csinva/imodels A Python package providing scikit-learn-compatible implementations of interpretable machine-learning models such as rule lists, RuleFit, an… | 98 | 1627 | active |
| yossdotpro/removerized Removerized is an open-source, browser-based AI image toolkit for background removal and image upscaling, running entirely client-side via … | 81 | 1627 | active |
| KEV0143/Adaptive-forecasting-of-electricity-consumption-24-168-720-h-with-load-regime-conditioning An open-source tool for adaptive forecasting of hourly electricity consumption over 24, 168, and 720 hour horizons, using load regime condi… | 56 | 1627 | active |
| Meta-Harness Meta-Harness is a Python framework for automated end-to-end search over task-specific model harnesses — the code surrounding a fixed base L… | 57 | 1625 | active |
| pq-yang/MatAnyone MatAnyone is a CVPR 2025 human video matting framework that extracts alpha mattes of target people from video using consistent memory propa… | 51 | 1625 | active |
| pavlin-policar/openTSNE openTSNE is a modular Python library implementing t-Distributed Stochastic Neighbor Embedding (t-SNE) for visualizing high-dimensional data… | 65 | 1624 | stable |
| guochengqian/Magic123 Magic123 is the official PyTorch implementation of an ICLR 2024 paper that generates high-quality textured 3D meshes from a single unposed … | 84 | 1623 | stable |
| clusterzx/paperless-ai A self-hosted web application that automatically analyzes, tags, and classifies documents in Paperless-ngx using LLMs via OpenAI-compatible… | 70 | 5972 | maintenance |
| royshil/obs-localvocal LocalVocal is an OBS Studio plugin that performs real-time, fully local speech recognition and translation using Whisper models running on … | 84 | 1618 | active |
| UbiquitousLearning/mllm MLLM is a fast, lightweight multimodal LLM inference engine written in C++ for mobile and edge devices, with backends for ARM CPU, Qualcomm… | 71 | 1617 | active |