Expo Config Plugin to integrate Google MediaPipe Hand, Pose & Face Landmarker with React Native Vision Camera v4. Real-time, on-device holistic landmark detection (hands, body and face) via native Kotlin Frame Processor Plugin.
Cross-platform XR sessions and native AR views for Expo and React Native, powered by Nitro Modules
AGPL TypeScript client for solving reCAPTCHA in an already-open Chrome browser
A Node-RED library to integrate Edgematrix EdgeAI Station Service APIs
MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,
Get descriptions of images from OpenAI, Azure OpenAI and Anthropic Claude models. Supports both URLs and local files with batch processing capabilities.
MCP tool for capturing screenshots and analyzing them with Claude Vision API
Facebetter Web SDK. Installing this package also installs facebetter-core.
AI integration utilities for KalxJS applications
JavaScript SDK for CompreFace - free and open-source face recognition system from Exadel
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.
Canon-aligned dataset production and generation workbench — define visual rules, build versioned training data, compile production briefs, run local workflows, batch-produce, select winners, and re-ingest into your corpus
Orientation-aware barcode scanning with a Rust/WASM core and four effort modes
Node Bindings to OpenCV
RealEye Webcam EyeTracker Light Open — lightweight browser-based webcam eye-tracker using MediaPipe and ridge regression for gaze prediction
Plug-and-play hand-gesture interaction library for the web — pinch click, drag, two-hand zoom/rotate, two-finger scroll, swipe back/forward. Powered by MediaPipe.
Use Roboflow Train computer vision models for inference on images in node.js
React Native library for SMKit UI - Advanced fitness assessments and workout programs with AI-powered motion detection and real-time performance tracking
Iris — image facts with pixel-level proof. Dimensions, format, and metadata by default; local Tesseract OCR only when requested.
The xorgate workflow engine as a library and the xwe command: run workflow templates over video and telemetry files with a 28-node catalog, including code function nodes, no platform account required.
Typescript, type-safe, opinionated port of python's uniface: a comprehensive library for face detection, recognition, ~~landmark analysis, age, and gender detection.~~
OpenDesktop — AI-powered desktop agent that controls your computer. Voice, vision, automation, memory, 50+ AI providers. Install via CLI, control everything.
OcularAudio MCP: Advanced Async Multi-Platform Video Transcript & Screen Vision Server
NatML Graph API for Unity Engine.
Background window recording, frame-level QA evidence, in-between frame views, quality comparison, graded reviews and a small-model roundtable audit for AI agents via MCP.
Node Bindings to OpenCV
Local OCR and on-device screen reading for MCP clients (Claude, Cursor): read any window, locate elements to click, assert what's on screen. Apple Vision, no API keys, nothing uploaded.
AI-ready image preprocessing for React Native: zero-copy image → tensor conversion with strong YOLO/TFLite defaults.
OpenCV bindings for Bun
Img2Num is a raster vectorization library - it converts images to SVGs
MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,
DeepSeek Harness-native integration for agent-vision-toolkit (local build: dual modal routing, paste-image preview/zoom, and upstream features): image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
CLI tool combining multimodal AI analysis with RawTherapee's engine to generate optimized PP3 profiles for RAW photography. Features automatic histogram analysis for enhanced AI processing.
AI-powered virtual background replacement using TensorFlow.js and Robust Video Matting
High-performance, zero-dependency native device-level image quality (blur, exposure, brightness) validation for React Native using Nitro Modules.
Node.js client for Mirador API (http://mirador.im)
High performance, cross platform machine learning runtime for Unity Engine.
A comprehensive, unified interface for all types of AI models - natural language, vision, audio, and video. Supports 51 providers with dynamic model discovery and multi-modal capabilities.
Surf - Computer-use agent for AgentSea. Control desktop environments through screen capture, mouse, and keyboard actions using Claude's vision capabilities.
Detect and Recognize faces as fast as possible in react native!
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
Node.js bindings for the AprilTags library written by Michael Kaess
Official Node.js client for useknockout — state-of-the-art background removal API.
A pure Rust, high-performance computer vision library focused on safety and portability.
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
Vision-first Computer Use Agent engine.
Anthropic provider for weaveIntel — chat, tool use, vision, PDF, extended thinking, citations, batches, computer use