OpenVINO™ Runtime for Node.js: high-performance deep learning inference on Intel CPU, GPU, and NPU.
React Native Vision Camera plugin for on-device text recognition (OCR) and translation using ML Kit. Maintained fork of react-native-vision-camera-text-recognition
Needle Engine is a web-based runtime for 3D apps. It runs on your machine for development with great integrations into editors like Unity or Blender - and can be deployed onto any device! It is flexible, extensible and networking and XR are built-in.
Browser-based OCR SDK powered by PaddleOCR, ONNX Runtime Web and OpenCV.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
Asynchronous OpenCV 4.x nodejs bindings with JavaScript and TypeScript API.
Run Freedom Ridge, the self-hosted tool for exploring and curating computer vision datasets, on this machine with Docker: npx freedomridge
Shameless copy of danielgatis/rembg, but for the web. 90% organic GMO free AI generated code.
Asynchronous OpenCV 3.x nodejs bindings with JavaScript and TypeScript API.
OpenCV compiled to WebAssembly for JavaScript applications - Single file with embedded WASM
This package encompasses machine learning models, such as the Convolutional Neural Networks (CNN) model used for text recognition, empowering various foundational products under DCV architecture.
Pure AI model inference module - object detection, classification, and more
Dynamsoft MRZ Scanner JavaScript Edition is a ready-to-use SDK for web applications that accurately recognizes and parses Machine-Readable Zones on Machine-Readable Travel Documents.
A lightweight, zero-dependency SVG annotation library for computer vision and image labeling projects
React Native Firebase - Firebase ML brings the power of machine learning vision to your React Native application, supporting both Android & iOS.
TypeScript SDK for B3OS beta: vision (web pages and browsers), render, infer, sandboxes, routines, actions and vault, on the machine that runs the model.
pure nodejs OPCUA SDK - module node-opcua-nodeset-machine-vision
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
Vision and speech interfaces for human-machine interaction
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.
Asynchronous OpenCV 4.x nodejs bindings with JavaScript and TypeScript API.
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.
Run AI prediction functions in Unity Engine.
TypeScript & JavaScript machine learning library
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.
Bed of Roses — an ambient AI desktop companion with a draggable presence and generated app/widget surfaces.
n8n community node for NVIDIA NIM - Chat completions and image analysis with NVIDIA AI models
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.
n8n community node for SiliconFlow AI models - chat completions, vision language models, embeddings, and reranking
Cerebrum Ultimate creates editable JavaScript home automations from user requests, with conversational clarification and local execution for Node-RED.
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.
React Native Firebase - Firebase ML Kit brings the power of machine learning vision to your React Native application, supporting both Android & iOS.
n8n node for Fal.ai - LLM text generation, image/video generation, image editing, and vision AI models
AI integration utilities for KalxJS applications
Discovery, metrics and control of llama.cpp-family servers and OpenAI-compatible servers for pi (llama.cpp, ZINC, DwarfStar/ds4, lucebox, LM Studio, vLLM, SGLang, TGI, halogen): scan machines (localhost, LAN, Tailscale), register models, read real context
Renamed to llmwire. This package re-exports it unchanged; switch your import when convenient.
React Native Firebase - Firebase ML Kit brings the power of machine learning to your React Native application, supporting both Android & iOS.
Sixth CLI - AI-powered development assistant using Claude Code, Google Gemini, Grok API and many more
Analyze images using pre-trained machine learning models. Detect and label objects, faces, landmarks, logos, and text (OCR) in images. Extract text from photos, documents, PDFs, and handwritten content. Detect explicit or unsafe content with SafeSearch. I
A React Native Expo module for scanning MRZ (Machine Readable Zone) from passports and ID cards using the device camera. Supports TD-1 (ID cards) and TD-3 (passports) formats.
High-performance TensorFlow Lite library for React Native, powered by Nitro Modules
NatML Graph API for Unity Engine.
AI-ready image preprocessing for React Native: zero-copy image → tensor conversion with strong YOLO/TFLite defaults.
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,
n8n node for Fal.ai - LLM text generation, image/video generation, image editing, and vision AI models