Turn any reference video into structured shot data + AI prompts — Claude Code skill
Proactive screen awareness + Claude Vision assistance
Self-hosted vinyl collection manager with barcode scanning, AI cover identification, and Discogs price tracking.
Monorepo para el aplicativo completo de Traxo. Incluye Frontend con Angular, Backend con Spring Boot, Microservicios con Python y FastAPI, documentación e infraestructura.
Telegram bot for OTC client onboarding — screenshot OCR → email automation
Your life. Your voice. Your book. — Memoir pipeline from physical artifacts. Digitize family letters, journals, photos → searchable archives, memoir scaffolds, AI writing companions.
Turn YouTube videos into queryable knowledge sessions — Gemini watches the video to pick key frames, Claude describes them and answers your questions. CLI + MCP server.
AI pre-print bed safety check for Klipper/Moonraker - cancels a print if a part is left on the bed or the homing path is blocked
Image-processing burst pipeline showcasing Temporal Cloud + AWS Lambda — durable fan-out/fan-in with Claude vision in the loop.
Drive-watched n8n workflow that extracts invoice fields with Claude Vision and writes to Google Sheets. Part of the n8n-ai-agents catalog.
IDP: layout analysis + Claude Vision fallback + Pydantic-validated field extraction + confidence-gated routing. Legal/finance/healthcare.
Detect and annotate character body parts in anime/VTuber/illustrated images using the Claude Vision API (2-stage scout + detect).
Computer vision + RPA agent that automates legacy accounting software using Claude Vision + PyAutoGUI
YouTube Video Frame Extractor for AI Testing & UI Debug 2026 - Lightning Fast CLI Tool
Self-hosted security camera pipeline for Raspberry Pi: Rust capture app, S3 storage, Claude vision tagging, and a searchable dashboard.
Multimodal AI family coach — text, voice, and camera-aware. Learns your family. Built on Claude + Claude Vision + Web Speech API.
AI audiobook generator for digital comics — per-character voices, HITL pipeline, cross-volume series memory
Reusable visual style modes for Claude — invoke a /command instead of re-describing the look you want every time you ask for a diagram, illustration, or study aid.
Mobile web app: snap a food photo, Claude estimates macros/calories/glucose spike, logs to localStorage with 7-day trend + personalized advice.
A Claude Code plugin that extracts frames from video files for visual analysis and UI debugging.
Add a description, image, and links to the claude-vision topic page so that developers can more easily learn about it.
To associate your repository with the claude-vision topic, visit your repo's landing page and select "manage topics."