Powerful AI agent for coding and general tasks. Terminal-first with shell, code execution, file editing, web browsing, vision, computer use. Unconstrained.
Local voice, vision, agents and quantized language-model inference.
Different ways of visualizing objects given bounding box data
Skeletonize densely labeled image volumes.
Fast Automatic License Plate Recognition.
The new inference engine for Computer Vision models
Transform, analyze, and visualize computer vision annotations.
Captcha-solving engine and CLI: a v2 pointer model for image grids, click and drag puzzles, sliders, distorted text and animated challenges. Hosted API or self-hosted on vLLM.
Python SDK and CLI for Pictograph: real-time vision tools for agents and developers. SAM3 labeling, RF-DETR and YOLOX training, TensorRT GPU endpoints, and live video streams.
OpenMMLab Computer Vision Foundation
Image Composition Toolbox
A cross-platform High-performance & Flexible Real-time Video Frames Decoder in Python.
A unified, high-performance computer vision tracking library.
Multi-modal PyTorch dataloader using ds-crawler indices
Savant Rust core functions library
OpenMMLab Image Classification Toolbox and Benchmark
OpenMMLab's next-generation platformfor general 3D object detection.
Evaluation toolkit for depth, RGB, ray and 3D point-map predictions
Reproducible pet re-identification: dataset audits, embeddings, metric learning and evaluation
OpenMMLab Model Deployment
OpenMMLab Model Pretraining Toolbox and Benchmark
Computer vision models for PyTorch
MareArts ANPR (Automatic Number Plate Recognition) library with multi-region support
equirectangular image processing with python using minimum dependencies
cuCIM - an extensible toolkit designed to provide GPU accelerated I/O, computer vision & image processing primitives for N-Dimensional images with a focus on biomedical imaging.
differential geometric computer vision for deep learning
Double Sphere & multi-model spherical-camera platform: models, calibration, conversion & 3D for wide-FOV lenses
Computer vision for medical imaging: the engine behind the platypus R package.
Fast symbolic computation, code generation, and nonlinear optimization for robotics
Run several computer vision models or a graph of them from one pip install, with the original's exact numbers.
MIT-licensed computer vision library: one Python API for YOLO, RF-DETR, RT-DETR and dozens more model families, with training and export where a family supports them.
High-performance PatchMatch implementation for image inpainting using Cython
With no prior knowledge of machine learning or device-specific deployment, you can deploy a computer vision model to a range of devices and environments using Roboflow Inference.
Versioned dataset-head contracts and extension validation for the Euler ecosystem
AI2-THOR: A Near Photo-Realistic Interactable Framework for Embodied AI Agents
cuCIM - an extensible toolkit designed to provide GPU accelerated I/O, computer vision & image processing primitives for N-Dimensional images with a focus on biomedical imaging.
Sub-3ms Physical Multi-Spectral Image Forensics & Presentation Attack Detection engine powered by OpenCV 5 and Model Context Protocol (MCP).
CUDA-accelerated Computer Vision algorithms
Accurate and Efficient General OCR System
Fast async image downloader for Python: self-tuning, rate-limit aware, every file accounted for.
UnrealCV client for python. see http://unrealcv.org for more detail.
A python tool for fitting primitives 3D shapes in point clouds using RANSAC algorithm
Industry-strength computer Vision extensions for Keras.
Computer Vision Helping Library
Ultralytics HUB Client SDK.
The realtime communication library for Python
Viewing and rendering of sequences of 3D data.
Savant Rust core functions library