function: machine-learning
5378 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| Tencent/ncnn ncnn is a high-performance neural network inference framework written in C++ and optimized for mobile, embedded, and desktop deployment. It… | 86 | 23753 | stable |
| facebookresearch/audiocraft A PyTorch library from Meta for audio processing and generation with deep learning, featuring the EnCodec neural audio codec and generative… | 61 | 23586 | 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… | 78 | 23511 | active |
| graphdeco-inria/gaussian-splatting The official reference implementation of 3D Gaussian Splatting, a method for real-time radiance field rendering that reconstructs scenes fr… | 50 | 23425 | 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 | 23348 | active |
| serengil/deepface DeepFace is a lightweight Python library for face recognition and facial attribute analysis, wrapping state-of-the-art models like VGG-Face… | 89 | 23340 | stable |
| verl-project/verl verl (Volcano Engine Reinforcement Learning) is a flexible, production-ready RL post-training library for large language models, open-sourc… | 84 | 23145 | active |
| mlc-ai/mlc-llm MLC LLM is a machine learning compiler and high-performance deployment engine for large language models, built on TVM-based ML compilation.… | 64 | 23095 | active |
| QwenAudio/CosyVoice CosyVoice is a multilingual large voice generation model (TTS) with full-stack inference, training, and deployment support. It offers zero-… | 61 | 22925 | active |
| microsoft/unilm Microsoft's collection of large-scale self-supervised pre-trained models spanning tasks, 100+ languages, and modalities (text, image, layou… | 67 | 22194 | active |
| trycua/cua Cua is an open-source framework for computer-use agents, providing background desktop drivers, disposable GUI sandboxes, cross-OS fleets (L… | 83 | 21922 | active |
| huggingface/datasets Hugging Face Datasets is a Python library providing one-line access to hundreds of thousands of public datasets on the Hugging Face Hub acr… | 98 | 21870 | stable |
| recommenders-team/recommenders A Python library and collection of Jupyter notebooks with best practices for building, evaluating, and operationalizing recommendation syst… | 67 | 21864 | active |
| microsoft/onnxruntime ONNX Runtime is a cross-platform, high-performance machine-learning accelerator for running inference and training on ONNX models. It suppo… | 99 | 21654 | stable |
| huggingface/peft PEFT is a Python library from Hugging Face providing state-of-the-art parameter-efficient fine-tuning methods (LoRA, adapters, soft prompts… | 93 | 21598 | stable |
| Zeyi-Lin/HivisionIDPhotos HivisionIDPhotos is a lightweight AI tool that generates standard ID/passport photos from user images using offline matting models that run… | 71 | 21420 | 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… | 92 | 21366 | stable |
| datalab-to/surya Surya is a 650M parameter OCR toolkit from Datalab providing state-of-the-art text recognition, layout analysis, reading order detection, a… | 86 | 21318 | active |
| bloc97/Anime4K Anime4K is a set of open-source, high-quality real-time anime upscaling and denoising algorithms implemented as GLSL shaders, primarily for… | 23 | 21295 | stable |
| k4yt3x/video2x Video2X is a machine learning-based video super-resolution and frame interpolation framework written in C/C++. It upscales videos and image… | 66 | 21263 | active |
| AI4Finance-Foundation/FinGPT FinGPT is an open-source financial large language model project from the AI4Finance Foundation, providing domain-tuned models, fine-tuning … | 77 | 21154 | active |
| 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 … | 73 | 20955 | active |
| w-okada/voice-changer VCClient is a real-time AI voice changer application that converts microphone input using models like RVC and Beatrice v2. It ships as preb… | 65 | 20864 | active |
| openai/gpt-oss OpenAI's gpt-oss repository hosts reference implementations and tooling for two open-weight language models, gpt-oss-120b and gpt-oss-20b, … | 71 | 20347 | stable |
| modelscope/FunASR FunASR is an industrial end-to-end speech recognition toolkit built on PyTorch, offering ASR, VAD, punctuation restoration, speaker diariza… | 99 | 20036 | 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… | 28 | 20028 | active |
| QwenLM/Qwen3-VL Qwen3-VL is a series of open-weight multimodal vision-language models from Alibaba's Qwen team, available in Dense and MoE architectures wi… | 52 | 19847 | active |
| facebookresearch/sam2 Official code for Meta's Segment Anything Model 2 (SAM 2), a foundation model for promptable visual segmentation in images and videos. It i… | 61 | 19770 | active |
| Unity-Technologies/ml-agents The Unity Machine Learning Agents Toolkit (ML-Agents) lets Unity games and simulations serve as environments for training intelligent agent… | 69 | 19647 | 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… | 43 | 19378 | active |
| huggingface/trl TRL is a Hugging Face library for post-training transformer language models with techniques like Supervised Fine-Tuning (SFT), GRPO, DPO, K… | 99 | 19155 | active |
| tensorflow/tfjs TensorFlow.js is a hardware-accelerated JavaScript library for training and deploying machine learning models in the browser and Node.js. I… | 69 | 19134 | stable |
| huggingface/sentence-transformers Sentence Transformers (SBERT) is a Python library for computing, using, and training state-of-the-art embedding, reranker, sparse encoder, … | 99 | 19036 | stable |
| KlingAIResearch/LivePortrait LivePortrait is a Python-based portrait animation tool from Kuaishou Technology that synthesizes lifelike videos from a single source image… | 62 | 18969 | active |
| state-spaces/mamba Mamba is a PyTorch library implementing the selective state space model (SSM) architecture for linear-time sequence modeling, with hardware… | 85 | 18783 | active |
| lightgbm-org/LightGBM LightGBM is a fast, distributed, high-performance gradient boosting framework based on decision tree algorithms, with APIs for Python, R, C… | 86 | 18714 | stable |
| WebLLM WebLLM is a high-performance in-browser LLM inference engine that runs language models entirely client-side using WebGPU hardware accelerat… | 85 | 18603 | active |
| UFund-Me/Qbot Qbot is an AI-powered automated quantitative investment and trading research platform that runs fully locally. It combines machine learning… | 54 | 18394 | active |
| NVIDIA-NeMo/Speech NVIDIA NeMo Speech is an open-source Python framework for building, training, and deploying speech, audio, and multimodal language models, … | 98 | 18337 | active |
| sczhou/CodeFormer CodeFormer is a PyTorch-based blind face restoration model using a codebook lookup transformer, published at NeurIPS 2022. It restores and … | 46 | 18117 | stable |
| google/magika Magika is an AI-powered file content type detection tool that uses a small, highly optimized deep learning model to identify 200+ file type… | 88 | 17971 | stable |
| apple/ml-stable-diffusion Apple's official tooling for running Stable Diffusion on Apple Silicon using Core ML. It includes a Python package for converting PyTorch m… | 36 | 17968 | active |
| pytorch/vision torchvision is the official PyTorch companion library providing datasets, model architectures, and image/video transformations for computer… | 93 | 17885 | stable |
| confident-ai/deepeval DeepEval is an open-source Python framework for evaluating LLM applications with pytest-style unit tests and 50+ research-backed metrics in… | 95 | 17882 | active |
| Mikubill/sd-webui-controlnet A WebUI extension that adds ControlNet and other injection-based controls to AUTOMATIC1111's Stable Diffusion web UI. It allows on-the-fly … | 31 | 17845 | active |
| deepseek-ai/Janus Janus-Series is DeepSeek's family of unified multimodal models (Janus, Janus-Pro, JanusFlow) that combine multimodal understanding and imag… | 24 | 17757 | active |
| IDEA-Research/Grounded-Segment-Anything Grounded-Segment-Anything (Grounded SAM) combines Grounding DINO with Segment Anything to detect and segment arbitrary objects from text pr… | 30 | 17710 | active |
| NVIDIA/Megatron-LM NVIDIA's GPU-optimized library for training large transformer models at scale, comprising Megatron-LM (reference training scripts) and Mega… | 99 | 17615 | active |
| NVlabs/instant-ngp NVIDIA's implementation of instant neural graphics primitives, training NeRFs, signed distance functions, neural images, and neural volumes… | 52 | 17535 | 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… | 50 | 17291 | active |
| karpathy/micrograd A tiny scalar-valued autograd engine implementing reverse-mode automatic differentiation over a dynamically built DAG, with a small PyTorch… | 75 | 17273 | stable |
| lllyasviel/FramePack FramePack is a next-frame-prediction video diffusion framework and desktop application that generates long videos progressively while compr… | 31 | 17229 | active |
| microsoft/data-formulator Data Formulator is an AI-powered interactive data analysis and visualization application from Microsoft that lets users connect data source… | 86 | 17011 | active |
| AaronFeng753/Waifu2x-Extension-GUI A Windows GUI application for upscaling images, GIFs, and videos using multiple AI super-resolution engines (Waifu2x, Real-ESRGAN, Real-CUG… | 97 | 16920 | 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.… | 58 | 16705 | active |
| cvat-ai/cvat CVAT (Computer Vision Annotation Tool) is an open-source, self-hosted platform for annotating images, videos, and 3D point clouds to build … | 95 | 16600 | active |
| lukas-blecher/LaTeX-OCR pix2tex (LaTeX-OCR) is a PyTorch-based vision transformer model that converts images of math formulas into LaTeX code. It ships as a pip-in… | 24 | 16547 | stable |
| RyanCodrai/turbovec turbovec is a Rust vector index with Python bindings implementing Google's TurboQuant algorithm for 2-4 bit vector quantization with SIMD-a… | 59 | 16441 | active |
| official-stockfish/Stockfish Stockfish is a free, open-source UCI chess engine that analyzes positions and computes optimal moves using alpha-beta search with NNUE neur… | 77 | 16419 | active |
| KindXiaoming/pykan Pykan is a Python library implementing Kolmogorov-Arnold Networks (KANs), an alternative to multi-layer perceptrons with learnable activati… | 27 | 16334 | active |
| huggingface/transformers.js Transformers.js is a JavaScript library that lets you run Hugging Face Transformers pretrained models directly in the browser (or Node.js) … | 91 | 16270 | active |
| LibreTranslate/LibreTranslate LibreTranslate is a free and open source machine translation API that is fully self-hosted and offline capable, powered by the Argos Transl… | 95 | 16136 | stable |
| wkentaro/labelme Labelme is a graphical image annotation tool written in Python with a Qt interface, supporting polygon, rectangle, oriented rectangle, circ… | 99 | 16130 | active |
| FinRL FinRL is the first open-source deep reinforcement learning framework for financial markets, providing end-to-end pipelines to build, train,… | 76 | 16108 | 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 | 16051 | stable |
| alibaba/MNN MNN is a lightweight, high-performance deep learning inference engine developed by Alibaba, supporting LLMs, vision, audio, and multimodal … | 93 | 15973 | active |
| kubeflow/kubeflow Kubeflow is a CNCF-graduated, Kubernetes-native toolkit for building AI/ML platforms, comprising subprojects like Pipelines, Notebooks, Tra… | 84 | 15832 | 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… | 89 | 15816 | active |
| vibrantlabsai/ragas Ragas is a Python library for evaluating LLM applications with objective, LLM-driven metrics and systematic experiment loops. It also gener… | 71 | 15485 | active |
| KittenML/KittenTTS KittenTTS is an open-source, ultra-lightweight text-to-speech library built on ONNX, with models ranging from 15M to 80M parameters (25-80 … | 66 | 15403 | 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 | 15236 | stable |
| SWivid/F5-TTS F5-TTS is the official implementation of a fully non-autoregressive text-to-speech system based on flow matching with a Diffusion Transform… | 85 | 15167 | active |
| 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… | 54 | 15164 | active |
| Vosk Vosk is an offline open source speech recognition toolkit supporting 20+ languages with small models and a streaming API. It provides bindi… | 66 | 15077 | stable |
| scipy/scipy SciPy is an open-source Python library providing fundamental algorithms for scientific computing, including optimization, integration, inte… | 95 | 14954 | stable |
| 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 | 14861 | active |
| tensorflow/tfjs-models A collection of pre-trained machine learning models ported to TensorFlow.js, published as npm packages for use in JavaScript projects. Mode… | 63 | 14793 | active |
| HumanAIGC/AnimateAnyone Animate Anyone is the official research implementation of a diffusion-based image-to-video synthesis method that animates a static characte… | 46 | 14791 | active |
| SesameAILabs/csm CSM (Conversational Speech Model) is Sesame's speech generation model that produces conversational audio from text and audio context, using… | 30 | 14720 | active |
| optuna/optuna Optuna is an open-source Python hyperparameter optimization framework with a define-by-run API for dynamically constructing search spaces. … | 90 | 14713 | active |
| nltk/nltk NLTK is a leading open-source Python library for natural language processing, providing interfaces to over 50 corpora and lexical resources… | 98 | 14703 | stable |
| bulletphysics/bullet3 Bullet Physics SDK is a C++ library providing real-time collision detection and rigid/soft body multi-physics simulation, with Python bindi… | 44 | 14700 | stable |
| RWKV RWKV is a novel language model architecture that combines RNN efficiency (linear time, constant memory, no KV-cache) with transformer-level… | 67 | 14683 | active |
| MuJoCo MuJoCo (Multi-Joint dynamics with Contact) is a general-purpose physics engine for fast and accurate simulation of articulated structures i… | 99 | 14680 | active |
| 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… | 43 | 14646 | active |
| ChatterBot ChatterBot is a Python library that provides a machine-learning based conversational dialog engine for building chat bots. It generates res… | 99 | 14508 | 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… | 84 | 14483 | active |
| SakanaAI/AI-Scientist The AI Scientist is a system that uses large language models to autonomously perform end-to-end scientific research, from idea generation a… | 49 | 14449 | active |
| PaddlePaddle/PaddleDetection PaddleDetection is an object detection toolkit built on the PaddlePaddle deep learning framework. It provides implementations of detection,… | 73 | 14389 | active |
| flairNLP/flair Flair is a Python NLP framework built on PyTorch for state-of-the-art natural language processing tasks such as named entity recognition, p… | 52 | 14384 | active |
| microsoft/RD-Agent RD-Agent is a Microsoft open-source framework that uses LLM-powered agents to automate research and development processes such as factor mi… | 75 | 14342 | active |
| carla-simulator/carla CARLA is an open-source simulator for autonomous driving research built on Unreal Engine, providing open digital assets like urban layouts,… | 70 | 14328 | active |
| facebookresearch/vggt VGGT (Visual Geometry Grounded Transformer) is a feed-forward transformer model from Meta AI and Oxford VGG that infers 3D geometry—camera … | 58 | 14292 | active |
| spotify/annoy Annoy is a C++ library with Python (and other language) bindings for approximate nearest neighbor search over high-dimensional vectors. It … | 45 | 14289 | stable |
| dmlc/dgl DGL (Deep Graph Library) is a Python package for deep learning on graph-structured data, built on top of existing frameworks like PyTorch, … | 38 | 14282 | stable |
| Eclipse Deeplearning4J Eclipse Deeplearning4J is an open-source deep learning framework and ecosystem for the JVM, including the ND4J linear algebra library, the … | 77 | 14246 | active |
| unifyai/ivy Ivy is a Python library that transpiles machine learning code, models, and libraries between frameworks such as PyTorch, TensorFlow, JAX, a… | 78 | 14172 | active |
| mlfoundations/open_clip OpenCLIP is an open-source PyTorch implementation of CLIP and related multimodal contrastive models, with many pretrained image/text checkp… | 86 | 14095 | active |
| EleutherAI/lm-evaluation-harness A Python framework for few-shot evaluation of language models across hundreds of standard benchmarks (HellaSwag, MMLU, BIG-Bench, etc.). It… | 89 | 13803 | active |
| DLR-RM/stable-baselines3 Stable Baselines3 is a Python library providing reliable, well-tested PyTorch implementations of reinforcement learning algorithms with a u… | 91 | 13728 | stable |