Open-source machine-learning software
4007 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.
4007 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| marimo marimo is a reactive Python notebook stored as pure Python files, where running a cell automatically re-runs dependent cells to keep code a… | 90 | 22981 | active |
| jundot/omlx oMLX is a macOS‑native LLM inference server that runs on Apple Silicon and provides continuous batching and tiered KV caching. It can be ma… | 79 | 22914 | active |
| Video2X Video2X is a machine learning-based video super-resolution and frame interpolation framework written in C/C++. It upscales videos and image… | 62 | 22307 | 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 |
| huggingface/datasets 🤗 Datasets is a Python library that provides one‑line loading of thousands of public datasets and powerful tools for preprocessing and stre… | 99 | 22061 | active |
| recommenders-team/recommenders A Python library and collection of Jupyter notebooks with best practices for building, evaluating, and operationalizing recommendation syst… | 66 | 21919 | active |
| 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 |
| huggingface/peft 🤗 PEFT is a Python library that provides state‑of‑the‑art parameter‑efficient fine‑tuning methods for large pretrained models. It integrate… | 95 | 21795 | 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 |
| Machine Learning for Trading Machine Learning for Trading is an open‑source Python ecosystem that provides end‑to‑end tools for quantitative finance, from market data a… | 94 | 21452 | active |
| AI4Finance-Foundation/FinGPT FinGPT is an open-source financial large language model project from the AI4Finance Foundation, providing domain-tuned models, fine-tuning … | 76 | 21352 | 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 … | 74 | 21182 | 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… | 75 | 21085 | 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 |
| 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… | 58 | 20001 | active |
| ML-Agents Unity ML‑Agents is an open‑source toolkit that lets developers use Unity environments to train intelligent agents with deep reinforcement a… | 66 | 19717 | active |
| ML-Agents The Unity Machine Learning Agents Toolkit (ML-Agents) lets Unity games and simulations serve as environments for training intelligent agent… | 66 | 19717 | active |
| fengdu78/lihang-code A collection of Jupyter Notebook implementations of the algorithms described in Li Hang's "Statistical Learning Methods" textbook. The repo… | 76 | 19606 | 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 |
| openai/evals OpenAI Evals is a Python framework for evaluating large language models and LLM-based systems, with an open-source registry of benchmark ev… | 63 | 19500 | active |
| Taipy Taipy is an open-source Python framework that turns data and AI algorithms into production-ready web applications, combining a Markdown/Pyt… | 86 | 19438 | active |
| huggingface/sentence-transformers Sentence Transformers is a Python library for computing dense vector embeddings from text, images, audio, and video. It also provides tools… | 98 | 19183 | 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 |
| lightgbm-org/LightGBM LightGBM is a high‑performance gradient boosting framework written in C++ with bindings for Python and R. It supports fast training, low me… | 84 | 18893 | active |
| 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 |
| 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 | 18733 | active |
| Qbot Qbot is an AI-powered quantitative investment platform that enables automated trading strategies with local deployment. It provides tools f… | 51 | 18568 | active |
| Qbot Qbot is an AI-powered automated quantitative investment and trading research platform that runs fully locally. It combines machine learning… | 51 | 18568 | active |
| meta-llama/llama-cookbook The Llama Cookbook is a collection of Jupyter notebooks and scripts that demonstrate how to use Meta's Llama models for inference, fine‑tun… | 54 | 18559 | 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 |
| microsoft/agent-lightning Agent Lightning is a lightweight (~3,500-line) agentic reinforcement learning framework from Microsoft for training LLM-powered agents with… | 82 | 18410 | 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 |
| 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… | 65 | 17965 | active |
| 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 |
| rocketride-org/rocketride-server RocketRide is an open-source AI pipeline engine with a high-throughput C++ runtime and 100+ Python-extensible nodes for building, debugging… | 82 | 17760 | 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… | 31 | 17758 | active |
| NVlabs/instant-ngp NVIDIA's implementation of instant neural graphics primitives, training NeRFs, signed distance functions, neural images, and neural volumes… | 48 | 17557 | 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… | 57 | 17244 | active |
| Waifu2x-Extension-GUI A Windows GUI application for upscaling images, GIFs, and videos using multiple AI super-resolution engines (Waifu2x, Real-ESRGAN, Real-CUG… | 98 | 17089 | active |
| argoproj/argo-workflows Argo Workflows is an open-source, container-native workflow engine for orchestrating parallel jobs on Kubernetes, implemented as a Kubernet… | 93 | 17024 | stable |
| wanshuiyin/Auto-claude-code-research-in-sleep ARIS is a collection of lightweight Markdown-only skills that turn LLM coding agents (Claude Code, Codex, Cursor, etc.) into autonomous ML … | 81 | 16907 | 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 | 16896 | active |
| Elysia Weaviate is an open-source, cloud-native vector database written in Go that stores both objects and vector embeddings, combining vector sim… | 94 | 16860 | stable |
| 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… | 23 | 16595 | stable |
| FinRL FinRL is the first open-source deep reinforcement learning framework for financial markets, providing end-to-end pipelines to build, train,… | 77 | 16558 | 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 |
| wkentaro/labelme Labelme is a graphical image annotation tool written in Python with a Qt interface, supporting polygon, rectangle, oriented rectangle, circ… | 98 | 16211 | active |
| MNN MNN is a lightweight, high-performance deep learning inference engine developed by Alibaba, supporting LLMs, vision, audio, and multimodal … | 90 | 16188 | active |
| raga-ai-hub/RagaAI-Catalyst RagaAI Catalyst is a Python SDK for observability, monitoring, and evaluation of LLM and agentic AI applications, with tracing of agents, L… | 52 | 16164 | 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 | 16161 | 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 |
| GraphScope Zvec is an open-source, in-process vector database by Alibaba that embeds directly into applications with no server or daemon required. It … | 80 | 16070 | active |
| 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 |
| vibrantlabsai/ragas Ragas is a Python library for evaluating LLM applications with objective, LLM-driven metrics and systematic experiment loops. It also gener… | 66 | 15901 | active |
| DVC DVC (Data Version Control) is an open-source command line tool and VS Code extension for versioning data and models, building lightweight M… | 88 | 15892 | 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… | 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 |
| MuJoCo MuJoCo (Multi-Joint dynamics with Contact) is a general-purpose physics engine for fast and accurate simulation of articulated structures i… | 100 | 15719 | 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 |
| 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… | 84 | 15313 | active |
| Vosk Vosk is an offline open source speech recognition toolkit supporting 20+ languages with small models and a streaming API. It provides bindi… | 62 | 15164 | stable |
| vosen/ZLUDA ZLUDA is a drop-in replacement layer for CUDA that lets unmodified CUDA applications run on non-NVIDIA GPUs with near-native performance. I… | 83 | 15103 | active |
| ConardLi/easy-dataset Easy Dataset is a self-hosted web application for building high-quality structured datasets for LLM fine-tuning, RAG, and model evaluation.… | 66 | 14989 | 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 |
| TensorFlow.js A collection of pre-trained machine learning models ported to TensorFlow.js, published as npm packages for use in JavaScript projects. Mode… | 59 | 14812 | active |
| k2-fsa/OmniVoice OmniVoice is a massively multilingual zero-shot text-to-speech model supporting 600+ languages, built on a diffusion language model-style a… | 77 | 14762 | active |
| RWKV RWKV is a novel language model architecture that combines RNN efficiency (linear time, constant memory, no KV-cache) with transformer-level… | 66 | 14744 | active |
| NLTK NLTK is a leading open-source Python library for natural language processing, providing interfaces to over 50 corpora and lexical resources… | 95 | 14732 | stable |
| FreeToken FreeToken is an edge-native Mixture-of-Experts (MoE) LLM serving engine that runs frontier-scale open-weight models on consumer hardware by… | 79 | 14561 | 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 … | 55 | 14499 | active |
| dlib Dlib is a modern C++ toolkit containing machine learning algorithms, deep learning tools, computer vision, linear algebra, and general-purp… | 84 | 14458 | stable |
| PaddlePaddle/PaddleDetection PaddleDetection is an object detection toolkit built on the PaddlePaddle deep learning framework. It provides implementations of detection,… | 67 | 14431 | active |
| 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… | 48 | 14392 | active |
| spotify/annoy Annoy is a C++ library with Python (and other language) bindings for approximate nearest neighbor search over high-dimensional vectors. It … | 41 | 14304 | 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, … | 34 | 14281 | stable |
| Eclipse Deeplearning4j Eclipse Deeplearning4J is an open-source deep learning framework and ecosystem for the JVM, including the ND4J linear algebra library, the … | 76 | 14269 | 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… | 91 | 14198 | active |
| unifyai/ivy Ivy is a Python library that transpiles machine learning code, models, and libraries between frameworks such as PyTorch, TensorFlow, JAX, a… | 10 | 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… | 80 | 14157 | active |
| Open3D Open3D is an open-source C++ and Python library for 3D data processing, offering data structures, algorithms, and pipelines for point cloud… | 86 | 14097 | active |
| Physical-Intelligence/openpi Open-source repository from Physical Intelligence containing vision-language-action (VLA) models for robotics, including π₀, π₀-FAST, and π… | 64 | 13991 | active |
| RL Baselines3 Zoo Stable Baselines3 is a Python library providing reliable, well-tested PyTorch implementations of reinforcement learning algorithms with a u… | 86 | 13883 | stable |
| apache/tvm Apache TVM is an open machine learning compiler framework that takes pre-trained models and compiles them into optimized, deployable module… | 95 | 13840 | active |
| Lightning-AI/litgpt LitGPT is a Python library providing from-scratch, hackable implementations of 20+ open-source large language models with recipes for pretr… | 87 | 13718 | active |
| CompVis/stable-diffusion The original reference implementation of Stable Diffusion, a latent text-to-image diffusion model trained on LAION-5B data with a CLIP text… | 32 | 73487 | maintenance |
| microsoft/TRELLIS TRELLIS is Microsoft's large-scale 3D asset generation model that creates high-quality 3D assets from text or image prompts. It uses a unif… | 58 | 13679 | active |
| NVIDIA/TensorRT NVIDIA TensorRT is an SDK for high-performance deep learning inference on NVIDIA GPUs, comprising an inference compiler that converts train… | 93 | 13362 | stable |
| modelscope/DiffSynth-Studio DiffSynth-Studio is an open-source diffusion model engine from the ModelScope community that integrates mainstream image, video, and audio … | 77 | 13229 | active |
| lllyasviel/stable-diffusion-webui-forge A fork/platform built on top of AUTOMATIC1111's Stable Diffusion WebUI that optimizes resource management, speeds up inference, and adds ex… | 29 | 13071 | active |
| ACE-Step ACE-Step 1.5 is an open-source music generation foundation model combining a language model planner with a Diffusion Transformer to create … | 77 | 13070 | active |
| jacobgil/pytorch-grad-cam A PyTorch library providing state-of-the-art pixel attribution (saliency) methods like GradCAM, ScoreCAM, and AblationCAM for explainable A… | 72 | 13002 | active |
| Orchestra-Research/AI-Research-SKILLs An open-source library of ~98 packaged 'skills' (knowledge modules) that turn AI coding agents like Claude Code, Codex, or Gemini into auto… | 69 | 12991 | active |
| PaddlePaddle/PaddleFormers PaddleFormers is a Transformers-style library built on PaddlePaddle providing a model zoo of 100+ large language models and vision-language… | 88 | 12983 | active |