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.

OCI NodeJS client for Ai Vision Service

DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.

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

CedarJS prerender

The Dynamsoft Core module builds the foundation upon which Dynamsoft SDKs implement their functionality.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

Core logic for the checkbox widget implemented as a state machine

XState for finite state machines

CSS value parser

undefined

Skia rendering plugin for react-native-vision-camera for drawing camera frames in React Native.

A react native vision camera frame processor for cropping

A finite state machine library

Flagship multimodal vision hub for DeepSeek Harness: ~40 tools, PDF drag-and-drop, LaTeX formulas, complex tables, QR codes, UI flow diagrams, and multi-model consensus.

A React Native Vision Camera plugin for real-time OCR (Optical Character Recognition). This package enables seamless integration of on-device OCR by using Google ML Kit on Android and Apple's Vision Framework on iOS. It provides fast, efficient, and cross

A TypeScript MCP server that gives text-only LLMs image understanding through StepFun vision models.

Location tagging plugin for react-native-vision-camera for photo EXIF and video metadata.

A finite state machine iterator for JavaScript

High performance barcode scanner for React Native using VisionCamera