ai-product-photo-sorter

CatalogMesh is an AI workspace for product catalog operations, including grouping, review, SKU matching, exports, storage, and guarded automation. It turns a raw chronological product shoot into reviewed product groups, catalog/SKU matches, exports, cloud-storage copies, and controlled connector actions. The original photos remain untouched, and human review remains the authority for catalog identity and externally visible publication. The system provides both GUI and CLI parity, with a desktop Automation Center generated from the same automation CLI parser. It supports cloud AI providers (Gemini, OpenAI, Anthropic) and local AI via Ollama, along with local evidence such as embeddings, OCR, and barcode evidence. The Review Center allows non-destructive merge/split/move, corrections, approval state, and audit history. SKU matching offers ranked deterministic catalog candidates with mandatory human confirmation. Exports include safe offline Shopify draft and neutral PIM export profiles. Storage Center enables local-first rclone copy/dry-run/manual mirror to configured cloud remotes, with safe automatic post-run copy. Connectors for Shopify, Akeneo, and Odoo are approval-aware with connector-specific safety boundaries. The tool is available in English, Arabic, and Chinese. It also provides an MCP server with safe scan/audit/proposal tools only, and no generic remote-mutation, storage-transfer, or publish executor is exposed.