Tesseract C++ API in Pure Javascript
OpenCV JavaScript version for node.js or browser
Lightweight, probably the fastest PaddleOCR SDK in TypeScript. Runs anywhere JavaScript runs: Node.js, Bun, Deno, mobile react-native, web worker, web browsers, and browser extensions. Docker & CLI supported. The official SDK is browser-only. Accurate tex
A type-safe, modular, chainable image processing library built on top of OpenCV.js with a fluent API leveraging pipeline processing.
Browser-native computer vision media rendering and annotation engine.
OpenVINO™ Runtime for Node.js: high-performance deep learning inference on Intel CPU, GPU, and NPU.
JavaScript Computer Vision library
An easy way to run AI models in React Native with ExecuTorch
Fork of tesseract.js-core used for scribe.js. Tesseract C++ API in Pure Javascript
TinEye API node.js library
JavaScript porting of the ArUco library supporting multiple dictionaries including ARUCO_MIP_36h12 and custom dictionaries for augmented reality marker detection
WebexIntelligence computer vision library
Annotation parsing and conversion for computer vision.
Browser-based OCR SDK powered by PaddleOCR, ONNX Runtime Web and OpenCV.js
Deprecated Cloud APIs Client Library for Node.js
Asynchronous OpenCV 3.x / 4.x nodejs bindings with JavaScript and TypeScript API.
A React Native Vision Camera (v5, Nitro-based) plugin for Google ML Kit vision features. Ships text recognition (OCR) and barcode scanning today, each independently selectable to keep binary size down, for real-time frame processing and static images, wit
BlinkID Core SDK
Asynchronous OpenCV 4.x nodejs bindings with JavaScript and TypeScript API.
Composable cross-platform Edge AI SDK for audience sensing on DOOH/CTV devices
Run Ultralytics YOLO models in the browser on WebGPU (WebAssembly, ONNX Runtime Web via ort-web).
Browser offline background removal using WebGPU - powered by rembg.com technology
On-device AI for React Native and Expo: LLMs, speech-to-text, vision, and embeddings. Each capability is opt-in at build time. No API key. Zero runtime JavaScript dependencies.
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
DeepSeek Harness 的桌面自动化:给整台 Windows 机器装上眼睛和手。可以做人能做的任何事,包括且不仅限于CAD,WPS,浏览器操作,发微信。安全,快速,可靠,聪明,人性化。
Open CV package rebundled for Onfido usage
Google Cloud APIs Client Library for Node.js
A modern approach for Computer Vision on the web.
Create a computer vision endpoint in seconds
Front-End Computer Vision SDK for React
Run Freedom Ridge, the self-hosted tool for exploring and curating computer vision datasets, on this machine with Docker: npx freedomridge
A library that can extract the primary color and its hue in RGBA format and convert it.
Lightweight client for Roboflow's hosted inference API with WebRTC streaming support
MemberJunction: Computer Use - Vision-to-Action engine for driving web browsers via LLM reasoning over screenshots. MJ-independent base layer.
Shameless copy of danielgatis/rembg, but for the web. 90% organic GMO free AI generated code.
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 12 个模型友好工具
Asynchronous OpenCV 3.x nodejs bindings with JavaScript and TypeScript API.
Pure JavaScript OCR library with multilingual support using ONNX Runtime Node - no Python dependencies required!
A new algorithm for retrieving topological skeleton as a set of polylines from binary images
OpenCV compiled to WebAssembly for JavaScript applications - Single file with embedded WASM
Lightweight face detection for browser video streams, providing callbacks with face presence, quality guidance, and bounding boxes.
Minecraft 存档 → Blender 封面 / 动画 / 可编辑背景地图:自动挑机位(地形 + 太阳方向)、MCprep 材质 + BPS 骨架 + 三点布光 + AgX 合成器后期;渲完用 OpenCV 审 8 项、不合格自动重渲。同一套场景可出 10 秒动画与分镜片。
Zappar's core computer vision library, supporting image, face and world tracking.
Pure AI model inference module - object detection, classification, and more
Computer-vision-powered drawing tools for Annotorious
A lightweight, zero-dependency SVG annotation library for computer vision and image labeling projects
Computer use for the Pi coding agent: Windows apps, browsers and desktops through native UI trees, screenshots and real input, as a Pi Agent IDE plugin or standalone tools
Zappar's computer vision for JavaScript, supporting image, face and instant world tracking, and barcode scanning.