Open-source deep-learning software
2785 open-source libraries, tools and applications tagged deep-learning, ranked by how closely deep-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.
2785 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| tensorflow/tensorflow TensorFlow is an open‑source end‑to‑end platform for building and deploying machine‑learning models. It provides stable Python and C++ APIs… | 83 | 200740 | active |
| Transformers Hugging Face Transformers is a Python library that serves as the model-definition framework for state-of-the-art machine learning models ac… | 95 | 167798 | stable |
| Stable Diffusion web UI Stable Diffusion Web UI is a Python‑based web application that lets you run Stable Diffusion locally through an interactive Gradio interfac… | 51 | 165213 | active |
| ComfyUI ComfyUI is a modular, node‑based visual interface and inference engine for generative AI. It lets users chain multiple models, adjust every… | 95 | 138077 | active |
| pytorch/pytorch PyTorch is an open-source Python library for tensor computation and deep neural networks with strong GPU acceleration. It provides a dynami… | 95 | 104835 | active |
| deepseek-ai/DeepSeek-V3 Official repository for DeepSeek-V3, a 671B-parameter Mixture-of-Experts language model (37B activated per token) with open weights, infere… | 26 | 104498 | active |
| deepseek-ai/DeepSeek-R1 DeepSeek-R1 is a family of open-weight large language models trained with large-scale reinforcement learning for reasoning, including DeepS… | 21 | 91900 | active |
| OpenCV OpenCV is an open‑source computer vision and machine learning library written in C++. It provides over 2,500 optimized algorithms for image… | 85 | 90950 | active |
| tensorflow/models The TensorFlow Model Garden is a repository of official and community implementations of state-of-the-art machine learning models built wit… | 82 | 77653 | active |
| Keras Keras is a high‑level, multi‑backend deep learning library for Python. It provides a user‑friendly API that works with TensorFlow, JAX, PyT… | 96 | 64373 | active |
| openpilot openpilot is an open-source operating system that provides advanced driver assistance features for supported vehicles. It runs on comma har… | 89 | 63922 | active |
| Ultralytics YOLO Ultralytics provides a Python library implementing the YOLO family of models for object detection, segmentation, classification, pose estim… | 96 | 62597 | active |
| Ultralytics YOLO Ultralytics YOLO is a Python package and CLI providing a family of real-time computer vision models (YOLO26, YOLO11, YOLOv8) for object det… | 96 | 62597 | active |
| karpathy/nanochat nanochat is a minimal, hackable full-stack LLM training harness that covers tokenization, pretraining, finetuning, evaluation, and inferenc… | 59 | 58750 | active |
| ultralytics/yolov5 Ultralytics YOLOv5 is a PyTorch‑based library for real‑time object detection, instance segmentation, and image classification. It provides … | 66 | 58103 | active |
| Faceswap FaceSwap is an open‑source Python application that uses deep learning to detect and swap faces in images and videos. It provides both a gra… | 78 | 57578 | active |
| Faceswap Faceswap is a free, open-source, multi-platform deepfakes tool that uses deep learning to recognize and swap faces in pictures and videos. … | 78 | 57578 | active |
| roboflow/supervision Supervision is an open‑source Python library that provides reusable utilities for building computer‑vision applications, from dataset handl… | 97 | 51063 | active |
| ray-project/ray Ray is a unified open-source framework for scaling AI and Python applications, consisting of a core distributed runtime (tasks, actors, obj… | 99 | 44057 | stable |
| DeepSpeed DeepSpeed is an open‑source deep learning optimization library that enables efficient distributed training and inference of large models. I… | 98 | 43216 | active |
| hpcaitech/ColossalAI ColossalAI is a Python library that provides efficient parallelization techniques for training large deep learning models. It supports data… | 75 | 41430 | active |
| BitNet bitnet.cpp is Microsoft's official inference framework for 1-bit large language models (BitNet b1.58), providing optimized CPU kernels with… | 62 | 40295 | active |
| google-research/bert Google's BERT repository provides TensorFlow implementations and pre‑trained checkpoints of the Bidirectional Encoder Representations from … | 10 | 40038 | active |
| RVC-Project/Retrieval-based-Voice-Conversion-WebUI A WebUI-based framework for training and running retrieval-based voice conversion (RVC) models, letting users clone a voice timbre from as … | 77 | 38553 | active |
| OpenBMB/VoxCPM VoxCPM is a tokenizer-free text-to-speech system built on a diffusion autoregressive architecture that generates continuous speech represen… | 74 | 37924 | active |
| huggingface/pytorch-image-models timm (PyTorch Image Models) is a Python library that provides a large collection of state‑of‑the‑art vision models, utilities, and training… | 94 | 37222 | active |
| jax-ml/jax JAX is a Python library that provides composable transformations such as automatic differentiation, JIT compilation, and vectorization for … | 98 | 36460 | active |
| facebookresearch/detectron2 Detectron2 is Facebook AI Research's PyTorch-based library for state-of-the-art object detection, instance/panoptic segmentation, and other… | 66 | 34897 | stable |
| huggingface/diffusers Hugging Face Diffusers is a Python library providing state-of-the-art pretrained diffusion models for generating images, videos, and audio … | 95 | 34736 | stable |
| OpenPose OpenPose is an open‑source C++ library that provides real‑time multi‑person keypoint detection for body, face, hands, and feet. It leverage… | 23 | 34493 | active |
| openai/CLIP OpenAI's CLIP is a PyTorch library providing pretrained contrastive language-image models that encode images and text into a shared embeddi… | 62 | 34362 | stable |
| tinygrad/tinygrad tinygrad is a small, hackable deep learning framework providing a PyTorch-like tensor library with autograd, plus a visible IR and compiler… | 88 | 33740 | active |
| lutzroeder/netron Netron is a visualizer for neural network, deep learning, and machine learning models, rendering model graphs and layer details. It support… | 100 | 33596 | active |
| Fish Speech Fish Speech is an open-source state-of-the-art text-to-speech system (Fish Audio S2) trained on over 10 million hours of audio across ~50 l… | 70 | 33062 | active |
| open-mmlab/mmdetection MMDetection is OpenMMLab's PyTorch-based toolbox and benchmark for object detection and instance/panoptic segmentation. It provides a large… | 23 | 32955 | stable |
| Lightning-AI/pytorch-lightning PyTorch Lightning is a deep learning framework that organizes PyTorch code to eliminate boilerplate for training, finetuning, and scaling A… | 93 | 31417 | stable |
| karpathy/llm.c llm.c is a pure C/CUDA implementation for training large language models like GPT-2 and GPT-3, with no dependency on PyTorch or Python. It … | 34 | 31176 | active |
| FaceFusion FaceFusion is a Python‑based command‑line application for AI‑powered face manipulation, including swapping faces in images and videos with … | 95 | 30263 | active |
| FaceFusion FaceFusion is an open-source face manipulation platform for face swapping and lip syncing in images and videos, built in Python with GPU ac… | 95 | 30263 | active |
| hpcaitech/Open-Sora Open-Sora is an open-source initiative for efficiently producing high-quality videos from text prompts using deep learning models. It provi… | 47 | 29872 | active |
| MLX MLX is an array computation framework for machine learning on Apple silicon, developed by Apple ML research. It offers NumPy-like Python AP… | 95 | 28839 | active |
| LeRobot LeRobot is Hugging Face's PyTorch library for real-world robotics, providing a hardware-agnostic Python interface for controlling robots, a… | 90 | 28232 | active |
| fastai fastai is an open‑source deep learning library built on PyTorch that provides high‑level components for rapid model development. It offers … | 92 | 28224 | active |
| fastai fastai is a deep learning library built on PyTorch that offers high-level components for quickly achieving state-of-the-art results in visi… | 92 | 28224 | stable |
| Stability-AI/generative-models Stability AI's official repository of generative diffusion models, including Stable Diffusion, Stable Video, and SV4D 2.0 for image, video,… | 42 | 27300 | active |
| baidu/Unlimited-OCR Baidu's Unlimited-OCR is an open vision-language OCR model for one-shot long-horizon document parsing, extending DeepSeek-OCR. It provides … | 53 | 26763 | active |
| resemble-ai/chatterbox Chatterbox is a family of state-of-the-art open-source text-to-speech models by Resemble AI, including multilingual and low-latency Turbo v… | 49 | 26574 | active |
| huggingface/open-r1 Open R1 is Hugging Face's fully open reproduction of the DeepSeek-R1 training pipeline, providing scripts for supervised fine-tuning, GRPO … | 65 | 26481 | active |
| black-forest-labs/flux Official minimal inference code from Black Forest Labs for running FLUX.1 open-weight image generation and editing models. It supports text… | 35 | 26009 | active |
| shap/shap SHAP (SHapley Additive exPlanations) is a Python library that provides game‑theoretic explanations for the predictions of any machine‑learn… | 92 | 25783 | active |
| lucidrains/vit-pytorch A PyTorch library implementing the Vision Transformer (ViT) and dozens of ViT variants (NaViT, MaxViT, MobileViT, Dino, masked autoencoders… | 87 | 25551 | active |
| microsoft/JARVIS JARVIS (HuggingGPT) is a system that uses an LLM as a controller to plan tasks and orchestrate numerous expert ML models from the HuggingFa… | 42 | 25307 | active |
| junyanz/pytorch-CycleGAN-and-pix2pix Official PyTorch implementations of CycleGAN and pix2pix for paired and unpaired image-to-image translation. It includes training and testi… | 44 | 25261 | stable |
| Dao-AILab/flash-attention Official implementation of FlashAttention, FlashAttention-2, -3, and -4: fast and memory-efficient exact attention kernels for GPUs. It acc… | 92 | 25116 | active |
| index-tts/index-tts IndexTTS is an industrial-level zero-shot text-to-speech system that clones a voice from a single reference audio clip. The latest IndexTTS… | 76 | 24518 | active |
| PaddlePaddle PaddlePaddle is an open‑source deep learning platform that provides a unified framework for model development, training, and inference. It … | 92 | 24105 | active |
| PaddlePaddle PaddlePaddle is an industrial-grade deep learning framework written in C++ with Python APIs, supporting high-performance single-machine and… | 92 | 24105 | active |
| PyTorch Geometric PyTorch Geometric (PyG) is a Python library built on top of PyTorch for building and training Graph Neural Networks. It provides a unified … | 78 | 24098 | active |
| PyTorch Geometric PyG (PyTorch Geometric) is a Python library built on PyTorch for writing and training Graph Neural Networks on structured and irregular dat… | 78 | 24098 | stable |
| pytorch/examples A curated collection of short, high‑quality PyTorch example projects covering vision, text, reinforcement learning, and more. The repositor… | 46 | 24052 | active |
| deepseek-ai/DeepSeek-OCR DeepSeek-OCR is an open vision-language model from DeepSeek AI that researches 'contexts optical compression' - encoding long text contexts… | 43 | 23965 | active |
| Tencent/ncnn ncnn is a high-performance neural network inference framework written in C++ and optimized for mobile, embedded, and desktop deployment. It… | 83 | 23907 | stable |
| facebookresearch/audiocraft A PyTorch library from Meta for audio processing and generation with deep learning, featuring the EnCodec neural audio codec and generative… | 58 | 23699 | active |
| DeepFace DeepFace is a lightweight Python library for face recognition and facial attribute analysis. It provides pre‑trained models to estimate age… | 93 | 23482 | active |
| Sanster/IOPaint IOPaint is a free, open-source, self-hostable image inpainting and outpainting tool powered by state-of-the-art AI models like LaMa and Sta… | 10 | 23317 | active |
| spmallick/learnopencv LearnOpenCV is a repository of C++ and Python code examples for computer vision, deep learning, and AI. It provides ready‑to‑run notebooks … | 96 | 23170 | active |
| microsoft/unilm Microsoft's collection of large-scale self-supervised pre-trained models spanning tasks, 100+ languages, and modalities (text, image, layou… | 66 | 22219 | active |
| ONNX Runtime ONNX Runtime is a high‑performance, cross‑platform library for executing ONNX machine‑learning models. It supports both inference and train… | 100 | 22115 | active |
| ONNX Runtime ONNX Runtime is a cross-platform, high-performance machine-learning accelerator for running inference and training on ONNX models. It suppo… | 100 | 22115 | stable |
| jina-ai/serve Jina-serve is a Python framework for building and deploying multimodal AI services that communicate via gRPC, HTTP, and WebSockets. It prov… | 36 | 21854 | active |
| onnx/onnx ONNX (Open Neural Network Exchange) is an open standard and Python library for representing machine learning and deep learning models as an… | 95 | 21602 | stable |
| huggingface/candle Candle is a minimalist machine learning framework for Rust focused on performance and ease of use, with CPU and CUDA GPU support. It ships … | 74 | 21182 | active |
| triton-lang/triton Triton is an open‑source programming language and compiler for writing high‑performance custom deep‑learning primitives. It targets GPUs an… | 93 | 20386 | active |
| karpathy/llama2.c A minimal, dependency-free implementation of the Llama 2 LLM architecture that trains in PyTorch and runs inference in a single ~700-line p… | 29 | 20192 | active |
| huggingface/trl TRL is a Python library that enables post‑training of transformer language models with reinforcement‑learning techniques such as SFT, DPO, … | 100 | 19532 | active |
| nari-labs/dia Dia is a 1.6B-parameter open-weight text-to-speech model from Nari Labs that generates ultra-realistic multi-speaker dialogue in a single p… | 40 | 19401 | active |
| TensorFlow.js TensorFlow.js is a hardware‑accelerated JavaScript library for building, training, and running machine‑learning models in the browser and N… | 59 | 19147 | active |
| TensorFlow.js TensorFlow.js is a hardware-accelerated JavaScript library for training and deploying machine learning models in the browser and Node.js. I… | 59 | 19147 | stable |
| state-spaces/mamba Mamba is a PyTorch library implementing the selective state space model (SSM) architecture for linear-time sequence modeling, with hardware… | 80 | 18874 | active |
| NVIDIA-NeMo/Speech NVIDIA NeMo Speech is an open‑source Python toolkit for building, training, and deploying speech AI models such as automatic speech recogni… | 95 | 18521 | active |
| NVIDIA/Megatron-LM NVIDIA's GPU-optimized library for training large transformer models at scale, comprising Megatron-LM (reference training scripts) and Mega… | 100 | 18178 | active |
| sczhou/CodeFormer CodeFormer is a PyTorch-based blind face restoration model using a codebook lookup transformer, published at NeurIPS 2022. It restores and … | 43 | 18167 | stable |
| karpathy/micrograd A tiny scalar-valued autograd engine implementing reverse-mode automatic differentiation over a dynamically built DAG, with a small PyTorch… | 71 | 17953 | stable |
| pytorch/vision torchvision is the official PyTorch companion library providing datasets, model architectures, and image/video transformations for computer… | 92 | 17926 | stable |
| Wan Wan is an open-source family of large-scale video generation models (Wan2.1/Wan2.2) with Python inference code and pretrained weights for t… | 62 | 17695 | active |
| lllyasviel/FramePack FramePack is a next-frame-prediction video diffusion framework and desktop application that generates long videos progressively while compr… | 28 | 17304 | active |
| Robbyant/lingbot-map LingBot-Map is a feed-forward 3D foundation model that reconstructs scenes from streaming image data using a Geometric Context Transformer.… | 57 | 17135 | active |
| Transformers.js Transformers.js is a JavaScript library that lets you run Hugging Face Transformers pretrained models directly in the browser (or Node.js) … | 98 | 16349 | active |
| KindXiaoming/pykan Pykan is a Python library implementing Kolmogorov-Arnold Networks (KANs), an alternative to multi-layer perceptrons with learnable activati… | 16 | 16331 | active |
| MNN MNN is a lightweight, high-performance deep learning inference engine developed by Alibaba, supporting LLMs, vision, audio, and multimodal … | 90 | 16188 | active |
| microsoft/Swin-Transformer Official PyTorch implementation of the Swin Transformer, a hierarchical vision transformer using shifted windows that serves as a general-p… | 32 | 16081 | stable |
| tracel-ai/burn Burn is a Rust-based tensor library and deep learning framework supporting training and inference through a unified API. It JIT-compiles te… | 86 | 16008 | active |
| kubeflow/kubeflow Kubeflow is a CNCF-graduated, Kubernetes-native toolkit for building AI/ML platforms, comprising subprojects like Pipelines, Notebooks, Tra… | 78 | 15915 | stable |
| GeeeekExplorer/nano-vllm A lightweight vLLM-style LLM inference engine implemented from scratch in about 1,200 lines of Python. It offers fast offline inference wit… | 51 | 15834 | active |
| modelscope/ms-swift ms-swift is a ModelScope community framework for fine-tuning, inference, evaluation, quantization, and deployment of 600+ text LLMs and 400… | 90 | 15809 | active |
| ggml-org/ggml ggml is a plain C/C++ tensor library for machine learning with no dependencies, designed to be simple, portable, and efficient. It supports… | 99 | 15480 | stable |
| Tencent-Hunyuan/Hunyuan3D-2 Tencent's open-source Hunyuan3D-2 system for generating high-resolution 3D assets using large-scale diffusion models, supporting image-to-3… | 40 | 14994 | active |
| Optuna Optuna is an open-source Python hyperparameter optimization framework with a define-by-run API for dynamically constructing search spaces. … | 93 | 14894 | active |
| BrainJS/brain.js brain.js is a GPU-accelerated neural network library written in JavaScript/TypeScript that runs in both browsers and Node.js. It supports f… | 23 | 14860 | active |
| NVIDIA/TensorRT-LLM NVIDIA's TensorRT-LLM is a Python library and runtime for defining and serving Large Language Models with state-of-the-art inference optimi… | 83 | 14851 | active |
page 1 / 28 next →