Record chess games from a camera or video of a real board, in the browser. Moves as SAN/PGN, on-device.
ThreeJS wrappers for Zappar's computer vision library
A meta-package that installs and exposes the full Face-Auth ecosystem: API client, webcam utilities, and real-time video guidelines. The easiest way to add facial authentication to any web project.
DSH desktop agent: a native-vision decision loop that drives the host desktop through the Cua Driver tools. DSH 桌面 Agent 子插件。
Vision-first Mac computer use for DSH: window list, screenshots, OCR text targeting, numbered elements, background clicks and typing. Works without the accessibility tree.
React Native SDK for Anyline Tire Tread scanning and depth measurement
MCP server for AI vision analysis via OpenRouter
An edge library for deploying computer vision applications built with Roboflow to JS environments.
GammaCV is a WebGL accelerated Computer Vision library for browser
Real-time pose detection for React Native and Expo. 33 landmarks, iOS and Android, powered by MediaPipe.
JavaScript SDK for CompreFace - free and open-source face recognition system from Exadel
Node.js bindings for AprilTag detection library
All-in-one BlinkCard browser SDK for fast and accurate debit and credit card scanning and recognition in web applications.
Vision plugin for ElizaOS - provides camera integration and visual awareness
Open-source AR virtual makeup SDK for the web — real-time face tracking (MediaPipe) + WebGL/Three.js shaders, face morphing, and no licensing lock-in.
Ui.Vision MCP: MCP server for browser and desktop automation (RPA) with OCR, image recognition and real mouse/keyboard input. Works with Claude Code, Claude Desktop, Codex, Cursor, Windsurf, VS Code, LM Studio and any other MCP client.
BlinkCard Core SDK
Hako Devices 箱: line drawings and 3D views of Raspberry Pis, Macs, PCs, phones, tablets, game consoles, NAS boxes and classic machines, as a web component, with tags to filter 2,200+ machines by CPU, brand and more, and a typed way to assemble machines fr
Unofficial fork of computer-user by jing-hy: Codex-style Windows computer use for DeepSeek Harness. Clicks target live UI Automation element refs (ref/name) rather than pixels estimated off a downscaled screenshot, so they land exactly; screenshots ride t
A Node.js library for running MediaPipe models that are typically browser-only. This package uses a local Express (web) server and Playwright (headless browser) to bridge the gap between Node.js and MediaPipe's browser-based APIs.
Run AI inference in Unity Engine.
Unified on-device hardware orchestration and multi-modal AI acceleration runtime for Mobile Node.js & Android Termux
Camera component for React. We can use this component for computer vision tasks like barcode scanning, text recognition, etc.
Asynchronous OpenCV 4.x nodejs bindings with JavaScript and TypeScript API.
Windows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.
DOOH advertising SDK — add ads to vending machines, kiosks, billboards, and digital signage in one command. MCP server for AI agents. OpenRTB 2.6, VAST, proof-of-play, audience sensing.
Asynchronous OpenCV 3.x / 4.x nodejs bindings with JavaScript and TypeScript API.
Perform Affine, Projective or Piecewise Affine transformations over any Image or HTMLElement from only a set of reference points. High-Performance and easy-to-use.
Computer Use 插件:虚拟鼠标真人操作 + 原生视觉模型接入(deepseek-v4-flash-vision-exp 直读截图),screen_observe 等 20 个模型友好工具;浏览器组 browser_* 为兜底
Histogram of Oriented Gradients (HOG) features
Official client and command line for Sight by Raku: hand over photos, get completion-check verdicts.
On-device computer vision & VLM multimodal inference framework utilizing device resources for Android Termux & ARM64
Run AI prediction functions in Unity Engine.
为 DSH(DeepSeek Harness)打造的本地桌面 Computer Use 增强插件(Windows 完整验证,macOS 已接入):纯 JS 视觉差分、网格位置编码、键盘注入、语义级记忆压缩、长程任务闭环与人机共驾授权。
VisionCamera frame processor plugin wrapping Google MediaPipe Pose Landmarker for real-time on-device pose estimation in React Native. iOS (Swift) and Android (Kotlin), both production-validated.
TypeScript & JavaScript machine learning library
TypeScript SDK for Datalab's Indra OCR models: page orientation, line detection, recognition (Latin, Cyrillic, Greek, Devanagari, Bengali, Chinese), reading order, layout blocks, markdown, optional math, and PDF text layers. Runs on Node.js, Bun, Deno, br
Node-RED nodes for Google Cloud Platform
Camera, audio, ONNX inference, and audience metrics for Trillboards Edge AI SDK
Typescript version of jsfeat for WebARKit
Lightweight local visual grounding engine exposed as agent tools
n8n community node for NVIDIA NIM - Chat completions and image analysis with NVIDIA AI models
MCP for Ultralytics Platform workflows, datasets, training, prediction, and model operations.
MCP server for AI vision analysis via OpenRouter