Awesome Opensource Ai

Open Source Computer Vision Library

12 Weeks, 24 Lessons, AI for All!

Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

Learn it. Build it. Ship it for others.

We write your reusable computer vision tools. 💜

Cross-platform, customizable ML solutions for live and streaming media.

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

Datasets, Transforms and Models specific to Computer Vision

Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

Open-source simulator for autonomous driving research.

An open source implementation of CLIP.

Low-code framework for building custom LLMs, neural networks, and other AI models

🐍 Geometric Computer Vision Library for Spatial AI

Point Cloud Library (PCL)

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

Fast and Accurate ML in 3 Lines of Code

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

Webots Robot Simulator

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Superfast AI decision making and intelligent processing of multi-modal data.

A flexible, high-performance 3D simulator for Embodied AI research.

Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.

Segment Anything in QGIS: click an object to get its outline, or name what you want (buildings, solar panels, trees) and get every match as vector polygons. QGIS plugin by TerraLab, free tier, no GPU needed.