ONNX

YOLOv8ultralytics/ultralytics

A cutting-edge framework for training and deploying state-of-the-art YOLO models for object detection, segmentation, classification, and pose estimation.

Yolov5ultralytics/yolov5

A state-of-the-art PyTorch-based computer vision model for object detection, segmentation, and classification.

cvatopencv/cvat

An industry-leading open-source data engine for interactive video and image annotation to power machine learning.

memvidmemvid/memvid

A single-file memory layer for AI agents, replacing complex RAG pipelines with serverless, instant retrieval and long-term memory.

burntracel-ai/burn

A Rust-based deep learning framework and tensor library optimized for flexibility, efficiency, and cross-platform portability.

TensorRTNVIDIA/TensorRT

NVIDIA's SDK for high-performance deep learning inference optimization and deployment on NVIDIA GPUs.

libfacedetectionShiqiYu/libfacedetection

A high-performance CNN-based face detection library written in pure C++ with SIMD optimizations, achieving up to 1000 FPS.

korniakornia/kornia

A differentiable computer vision library for PyTorch, providing geometric vision and image processing algorithms for AI workflows.

RunAnywhereRunanywhereAI/runanywhere-sdks

SDKs for adding private, on-device AI features like LLM chat, speech-to-text, and text-to-speech to mobile and web apps.

ML.NETdotnet/machinelearning

An open-source, cross-platform machine learning framework for .NET developers to build, train, and deploy custom ML models.

GPTCachezilliztech/GPTCache

A semantic cache library for LLM queries that reduces API costs by 10x and boosts response speed by 100x.

Microsoft ML for Apache SparkAzure/mmlspark

An open-source library for building massively scalable machine learning pipelines on Apache Spark.

Scalable sentiment analysisdotnet/machinelearning-samples

A collection of samples demonstrating how to use ML.NET for various machine learning tasks in .NET applications.

spark-nlpJohnSnowLabs/spark-nlp

A state-of-the-art Natural Language Processing library built on Apache Spark, offering 100,000+ pretrained models and pipelines in 200+ languages.

robosatmapbox/robosat

An end-to-end Python pipeline for semantic segmentation of aerial and satellite imagery to extract features like buildings and roads.

WebDNNmil-tokyo/webdnn

A framework for running deep neural network models directly in web browsers using ONNX format with WebGPU, WebGL, and WebAssembly backends.

MCP Memory Servicedoobidoo/mcp-memory-service

Open-source persistent memory backend for AI agent pipelines with REST API, knowledge graph, and autonomous consolidation.

Claude Swarmparruda/claude-swarm

A Ruby framework for orchestrating multiple AI agents as a collaborative team with persistent memory and semantic search.

LightlyTrainlightly-ai/lightly-train

An all-in-one framework for training state-of-the-art computer vision models, covering pretraining, fine-tuning, and distillation.

GoMLXgomlx/gomlx

An accelerated machine learning framework for Go, offering a PyTorch/Jax/TensorFlow-like experience with support for CPUs, GPUs, TPUs, and WASM.

ros_deep_learningdusty-nv/ros_deep_learning

Deep learning inference nodes for ROS/ROS2 with support for NVIDIA Jetson devices and TensorRT.

perpetualperpetual-ml/perpetual

A hyperparameter-free gradient boosting machine with a simple budget parameter, built for high performance with Rust and bindings for Python and R.

TensorLayerXtensorlayer/TensorLayerX

A unified deep learning and reinforcement learning framework supporting multiple backends and hardware platforms.

isolation-forestlinkedin/isolation-forest

A distributed Spark/Scala implementation of Isolation Forest and Extended Isolation Forest algorithms for scalable unsupervised outlier detection.

whisper-openvinozhuzilin/whisper-openvino

A fork of OpenAI's Whisper speech recognition models optimized with OpenVINO backend for faster CPU inference.

type4pysaltudelft/type4py

A deep similarity learning-based type inference tool for Python that provides ML-powered type auto-completion.