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/VILA VILA is a family of open-source vision language models (VLMs) optimized for efficient video and multi-image understanding, spanning edge, d… | 54 | 3865 | active |
| danijar/dreamerv3 A Python/JAX reimplementation of DreamerV3, a model-based reinforcement learning algorithm that learns a world model and trains an actor-cr… | 76 | 3859 | active |
| open-mmlab/mmpretrain MMPretrain is OpenMMLab's PyTorch-based toolbox and benchmark for image classification model pre-training, covering supervised, self-superv… | 23 | 3855 | active |
| thu-ml/TurboDiffusion TurboDiffusion is a Python framework that accelerates end-to-end video diffusion model generation by 100-200x using SageAttention, Sparse-L… | 58 | 3851 | active |
| roboflow/trackers A Python library of clean-room, Apache 2.0 implementations of multi-object tracking algorithms including SORT, ByteTrack, OC-SORT, BoT-SORT… | 85 | 3850 | active |
| MrNeRF/LichtFeld-Studio LichtFeld Studio is a native open-source desktop application for 3D Gaussian Splatting that combines training, real-time inspection, splat … | 96 | 3849 | active |
| Avatarify Avatarify is an open-source application that drives photorealistic avatars in real time for video-conferencing apps like Zoom and Skype, ba… | 23 | 16520 | maintenance |
| mseitzer/pytorch-fid A PyTorch port of the official TensorFlow implementation of the Fréchet Inception Distance (FID), a metric for measuring similarity between… | 23 | 3847 | stable |
| piskvorky/gensim Gensim is a Python library for topic modelling, document indexing, and similarity retrieval over large text corpora. It provides memory-ind… | 43 | 16492 | maintenance |
| google-research/scenic Scenic is a JAX-based library from Google Research focused on attention-based models for computer vision, providing shared lightweight libr… | 76 | 3842 | active |
| shenweichen/GraphEmbedding A Python library providing implementations of classic graph embedding algorithms including DeepWalk, LINE, Node2Vec, SDNE, and Struc2Vec. I… | 64 | 3841 | active |
| benfred/implicit A fast Python library implementing collaborative filtering recommendation algorithms for implicit feedback datasets, including ALS, BPR, lo… | 68 | 3829 | active |
| lightly-ai/lightly LightlySSL is a Python library built on PyTorch for self-supervised learning on images, offering modular implementations of methods like Si… | 91 | 3821 | active |
| google/deepvariant DeepVariant is a deep learning-based genomic variant caller that converts aligned DNA sequencing reads (BAM/CRAM) into pileup image tensors… | 78 | 3818 | stable |
| facebookresearch/map-anything MapAnything is an open-source research framework from Meta and CMU for universal feed-forward metric 3D reconstruction using an end-to-end … | 71 | 3813 | active |
| ddbourgin/numpy-ml numpy-ml is a collection of machine learning models and algorithms implemented exclusively in NumPy and the Python standard library, coveri… | 32 | 16323 | maintenance |
| SandAI-org/MAGI-1 MAGI-1 is an open-source autoregressive video generation model from Sand.ai, released with Apache-2.0 licensed code and weights. It generat… | 56 | 3791 | active |
| meta-llama/codellama Official Meta repository with inference code for the Code Llama family of large language models for code, based on Llama 2. It provides min… | 10 | 16224 | maintenance |
| StuckAtPrototype Racer An open-source hardware and firmware project for a tiny PCB-based RC car built around the ESP32-H2, including KiCad schematics, gerbers, 3D… | 41 | 3786 | active |
| Hunyuan-PromptEnhancer/PromptEnhancer PromptEnhancer is a prompt-rewriting framework from Tencent Hunyuan that uses a Chain-of-Thought rewriter trained via reinforcement learnin… | 59 | 3785 | active |
| AI4Finance-Foundation/FinRL-Trading FinRL-X is an open-source, AI-native modular infrastructure for quantitative trading that unifies data processing, strategy composition, ba… | 76 | 3782 | active |
| IDEA-Research/Grounded-SAM-2 Grounded SAM 2 is a foundation-model pipeline that combines open-set detectors (Grounding DINO, Grounding DINO 1.5/1.6, Florence-2, DINO-X)… | 34 | 3780 | active |
| mathnet/mathnet-numerics Math.NET Numerics is an open-source numerical library for .NET and Mono, providing methods and algorithms for numerical computation in scie… | 33 | 3773 | stable |
| xtensor-stack/xtensor A header-only C++ library for numerical analysis with multi-dimensional array expressions, offering lazy broadcasting and a NumPy-inspired … | 73 | 3766 | active |
| aubio aubio is a C library (with Python bindings and CLI tools) for labeling music and sounds, detecting events such as note onsets, pitch, and t… | 53 | 3765 | stable |
| 0x90d/videoduplicatefinder A cross-platform application that finds duplicate video and image files based on visual similarity, including duplicates with different res… | 97 | 3759 | active |
| HazyResearch/ThunderKittens ThunderKittens is a C++/CUDA framework of tile-based primitives for writing fast deep learning GPU kernels. It embeds natively into CUDA so… | 68 | 3754 | active |
| HeartMuLa HeartMuLa is a family of open-source music foundation models that generate music conditioned on lyrics and tags with multilingual support. … | 60 | 3753 | active |
| genmoai/mochi Mochi 1 is Genmo's open-source, state-of-the-art text-to-video generation model released under Apache 2.0, with a Python API, CLI, and Grad… | 67 | 3750 | active |
| fudan-generative-vision/hallo2 Hallo2 is a Python research library from Fudan University that animates a single portrait image using audio input, producing long-duration … | 23 | 3746 | active |
| starVLA/starVLA StarVLA is an open-source, Lego-like modular codebase for developing Vision-Language-Action (VLA) models for generalist robots. It unifies … | 67 | 3745 | active |
| ferdous-alam/GenCAD GenCAD is a research codebase for image-conditioned CAD model generation using transformer-based contrastive representations (CCIP) and dif… | 33 | 3744 | active |
| DLR-RM/BlenderProc BlenderProc is a procedural Python pipeline built on Blender for generating photorealistic synthetic training images with ground-truth anno… | 59 | 3740 | active |
| borglab/gtsam GTSAM is a C++ library implementing smoothing and mapping (SAM) for robotics and vision using factor graphs and Bayes networks as its core … | 93 | 3734 | active |
| MTG/essentia Essentia is an open-source C++ library for audio analysis and music information retrieval, offering a large collection of reusable DSP algo… | 66 | 3733 | stable |
| xinyu1205/recognize-anything Recognize Anything is a collection of open-source image recognition foundation models, including RAM, RAM++, and Tag2Text, that perform ima… | 31 | 3728 | active |
| ant-research/MagicQuill MagicQuill is an intelligent interactive image editing system from a CVPR 2025 paper, combining a brush-based UI with AI-powered suggestion… | 43 | 3690 | active |
| MashiroSaber03/Saber-Translator Saber-Translator is an AI-powered manga translation application that detects speech bubbles, OCRs Japanese text, translates it, inpaints th… | 84 | 3687 | active |
| microsoft/Bringing-Old-Photos-Back-to-Life The official PyTorch implementation of 'Bringing Old Photos Back to Life' (CVPR 2020 Oral), a deep learning model that restores old photos … | 10 | 15704 | maintenance |
| Stability-AI/StableLM StableLM is Stability AI's repository of open-weight decoder-only transformer language models, including the 3B-parameter StableLM-3B-4E1T … | 30 | 15671 | maintenance |
| PAIR-code/lit The Learning Interpretability Tool (LIT) is a visual, interactive web-based tool for understanding and debugging ML model behavior across t… | 72 | 3667 | active |
| NVlabs/GR00T-WholeBodyControl NVIDIA's unified platform for developing, training, and deploying whole-body controllers for humanoid robots, including the decoupled WBC m… | 60 | 3654 | active |
| facebookresearch/sam-audio SAM-Audio is Meta's foundation model for isolating any sound in audio using text, visual, or temporal prompts. This repository provides inf… | 52 | 3654 | active |
| DI-engine DI-engine is an open-source reinforcement learning framework from OpenDILab that provides comprehensive implementations of deep RL algorith… | 44 | 3647 | active |
| zai-org/ChatGLM2-6B ChatGLM2-6B is an open-source bilingual (Chinese-English) 6B-parameter conversational large language model built on the GLM architecture. I… | 29 | 15505 | maintenance |
| kaldi-asr/kaldi Kaldi is a C++ toolkit for speech recognition research and development, including acoustic modeling, feature extraction, decoding, and spea… | 48 | 15502 | maintenance |
| mit-han-lab/llm-awq AWQ is a Python library implementing Activation-aware Weight Quantization for compressing large language models to low-bit (INT3/4) weights… | 41 | 3638 | active |
| NExT-GPT/NExT-GPT NExT-GPT is an end-to-end any-to-any multimodal large language model that accepts and generates arbitrary combinations of text, image, vide… | 34 | 3638 | active |
| meta-pytorch/botorch BoTorch is a Python library for Bayesian Optimization research built on top of PyTorch, part of the PyTorch ecosystem. It provides modular,… | 89 | 3632 | active |
| ploomber/ploomber Ploomber is a Python framework for building maintainable data pipelines from scripts and Jupyter notebooks, with iterative local developmen… | 10 | 3621 | active |
| facebookresearch/detr DETR is Facebook Research's PyTorch implementation of Detection Transformer, an end-to-end object detection model that replaces hand-crafte… | 10 | 15352 | maintenance |
| nv-tlabs/kimodo Kimodo is NVIDIA's official implementation of a kinematic motion diffusion model trained on 700 hours of motion capture data to generate hi… | 58 | 3615 | active |
| edtechre/pybroker PyBroker is a Python framework for developing algorithmic trading strategies with a focus on machine learning. It provides a fast NumPy/Num… | 92 | 3611 | active |
| SAM 3D SAM 3D Body is a promptable model for single-image full-body 3D human mesh recovery (HMR), estimating body, feet, and hand pose using the M… | 46 | 3610 | active |
| Albumentations Albumentations is a fast, flexible Python image augmentation library for computer vision, supporting images, masks, bounding boxes, keypoin… | 10 | 15309 | maintenance |
| OpenArm OpenArm is a fully open-source 7DOF humanoid robot arm (hardware, firmware, and software) designed for physical AI research and deployment … | 67 | 3605 | active |
| Qwen3-ASR Qwen3-ASR is a family of open-source speech recognition models from Alibaba's Qwen team, supporting ASR and language identification across … | 52 | 3605 | active |
| pytorch/rl TorchRL is a PyTorch-native library of composable primitives for building reinforcement learning systems, including environments, policies,… | 99 | 3603 | active |
| NVlabs/Eagle Eagle is NVIDIA's family of frontier vision-language models (Eagle, Eagle 2, Eagle 2.5) built with data-centric training strategies, plus L… | 61 | 3599 | active |
| RDKit RDKit is an open-source cheminformatics toolkit written in C++ with Python, Java, C#, and JavaScript wrappers. It provides core data struct… | 95 | 3597 | stable |
| ZhaoJ9014/face.evoLVe A high-performance face recognition library built on PaddlePaddle and PyTorch, providing comprehensive tools for face-related analytics and… | 34 | 3594 | active |
| AiuniAI/Unique3D Unique3D is the official implementation of a NeurIPS 2024 paper that generates high-quality textured 3D meshes from a single image in about… | 35 | 3589 | active |
| NVlabs/FoundationPose FoundationPose is NVIDIA's unified foundation model for 6D object pose estimation and tracking of novel objects, supporting both model-base… | 59 | 3587 | active |
| zhaoyingjun/chatbot A Chinese chatbot project that trains conversational models (Seq2Seq and GPT-style, including small SLM variants) on custom corpora with lo… | 49 | 3582 | active |
| NVIDIA/TransformerEngine Transformer Engine is an NVIDIA library for accelerating Transformer model training and inference on NVIDIA GPUs using low-precision format… | 99 | 3576 | active |
| sdv-dev/SDV SDV (Synthetic Data Vault) is a Python library for generating synthetic tabular data using machine learning models ranging from GaussianCop… | 98 | 3572 | stable |
| pathwaycom/bdh BDH (Dragon Hatchling) is a biologically inspired large language model architecture that bridges deep learning and neuroscience, implemente… | 51 | 3571 | active |
| SkalskiP/make-sense makesense.ai is a free, browser-based tool for labeling photos to prepare datasets for computer vision projects. It runs entirely client-si… | 23 | 3571 | active |
| Soul-AILab/SoulX-Podcast SoulX-Podcast is the official inference codebase for a text-to-speech model that generates long-form, multi-turn, multi-speaker podcast-sty… | 39 | 3561 | active |
| GraphScope GraphScope is a unified distributed graph computing platform from Alibaba that combines graph analytics (GRAPE), interactive graph queries … | 77 | 3558 | active |
| Kosinkadink/ComfyUI-AnimateDiff-Evolved A ComfyUI custom node pack providing an improved AnimateDiff integration plus advanced 'Evolved Sampling' options for animated video genera… | 67 | 3557 | active |
| ToTheBeginning/PuLID PuLID is the official PyTorch implementation of a NeurIPS 2024 method for inserting a specific person's identity into text-to-image generat… | 37 | 3556 | active |
| microsoft/hummingbird Hummingbird is a Microsoft library that compiles trained traditional ML models (decision trees, random forests, XGBoost, LightGBM) into ten… | 65 | 3554 | active |
| Vision Transformer Google Research's official Jax/Flax codebase for training large-scale vision models such as Vision Transformer, SigLIP, MLP-Mixer, and LiT … | 39 | 3551 | active |
| guandeh17/Self-Forcing Official implementation of Self Forcing, a training method for autoregressive video diffusion models that simulates inference during traini… | 34 | 3551 | active |
| petercorke/robotics-toolbox-python A Python library providing tools for robot manipulator kinematics, dynamics, Jacobians, and trajectory generation, built on NumPy and SciPy… | 99 | 3549 | active |
| pomegranate Pomegranate is a Python library for fast and flexible probabilistic modeling, built on PyTorch. It supports distributions, mixture models, … | 23 | 3546 | active |
| MNE-Python MNE-Python is an open-source Python library for exploring, visualizing, and analyzing human neurophysiological data such as MEG, EEG, sEEG,… | 93 | 3540 | stable |
| fnnx-ai/scikit-llm Scikit-LLM is a Python library that integrates large language models like GPT into scikit-learn workflows as estimators. It enables tasks s… | 72 | 3533 | active |
| Anttwo/SuGaR SuGaR is the official PyTorch implementation of a CVPR 2024 method that extracts accurate, editable meshes from 3D Gaussian Splatting recon… | 27 | 3525 | active |
| cszn/KAIR A PyTorch image restoration toolbox providing training and testing code for many restoration models including DnCNN, FFDNet, SRMD, USRNet, … | 23 | 3525 | active |
| google-deepmind/alphafold Open-source implementation of the AlphaFold 2 inference pipeline for predicting protein structures from amino acid sequences, including Alp… | 54 | 14887 | maintenance |
| neonbjb/tortoise-tts Tortoise TTS is a multi-voice text-to-speech library built on PyTorch that prioritizes highly realistic prosody and intonation. It combines… | 32 | 14877 | maintenance |
| EverMind-AI/MSA MSA (Memory Sparse Attention) is a Python framework for end-to-end trainable sparse latent-memory attention that scales LLM context to 100M… | 50 | 3520 | active |
| MooreThreads/Moore-AnimateAnyone An open-source reproduction of AnimateAnyone that animates a character from a single reference image using pose sequences from a driving vi… | 27 | 3517 | active |
| helblazer811/ManimML ManimML is a Python library built on the Manim Community Library for creating animations and visualizations of machine learning concepts li… | 23 | 3517 | active |
| visionml/pytracking PyTracking is a PyTorch-based framework for visual object tracking and video object segmentation, providing official implementations of tra… | 23 | 3516 | active |
| autorope/donkeycar Donkeycar is an open-source Python library and hardware platform for building small-scale self-driving RC cars with Raspberry Pi or Jetson … | 85 | 3515 | active |
| google-ai-edge/LiteRT LiteRT is Google's successor to TensorFlow Lite, an on-device runtime for high-performance ML and GenAI inference on edge platforms. It pro… | 86 | 3514 | active |
| ob-f/OpenBot OpenBot is an open-source project that turns Android smartphones into the brains of low-cost robots, paired with a ~$50 electric vehicle bo… | 64 | 3505 | active |
| PKU-YuanGroup/Video-LLaVA Video-LLaVA is a large vision-language model that aligns image and video representations into a unified visual space before projection into… | 28 | 3504 | active |
| huggingface/optimum Optimum is a Hugging Face library that extends Transformers, Diffusers, timm, and Sentence Transformers with hardware-specific optimization… | 91 | 3503 | active |
| imgaug imgaug is a Python library for augmenting images in machine learning experiments, converting a small set of input images into a much larger… | 23 | 14744 | maintenance |
| vietanhdev/anylabeling AnyLabeling is a desktop image annotation tool that combines LabelImg/Labelme-style manual labeling with AI-assisted auto-labeling. It runs… | 92 | 3491 | active |
| borisdayma/dalle-mini DALL·E Mini is a Python library and model that generates images from a text prompt, available via pip and hosted on Hugging Face Model Hub.… | 23 | 14724 | maintenance |
| Tencent-Hunyuan/Hunyuan3D-1 Tencent Hunyuan3D-1.0 is an open-source two-stage diffusion-based model for generating 3D assets from text prompts or images. It provides i… | 42 | 3489 | active |
| facebookresearch/ijepa Official PyTorch implementation of I-JEPA, a self-supervised learning method that predicts latent representations of image regions from oth… | 10 | 3488 | active |
| POSTECH-CVLab/PyTorch-StudioGAN PyTorch-StudioGAN is a PyTorch library providing unified implementations of representative GAN architectures (BigGAN, StyleGAN2/3, etc.) fo… | 23 | 3483 | stable |
| Docta-ai/docta Docta is a Python library for data-centric AI that diagnoses and fixes issues in datasets such as label errors, noise, and misannotations. … | 66 | 3479 | active |
| PennyLaneAI/pennylane PennyLane is a cross-platform Python library for quantum computing, quantum machine learning, and quantum chemistry. It lets users build an… | 88 | 3476 | stable |