MCP-Server für lokale Bild-Analyse: YOLOv8-Objekterkennung und EasyOCR, mit LLM-optimierten Markdown-Berichten (kein API-Key, komplett offline)
2 files for Codex, OpenCode and Claude Code: vision-mcp AGENTS.md, vision-mcp CLAUDE.md — 1,855 tokens loaded in every session.
AGENTS.md A 1,850 tok CLAUDE.md A 5 tok These files are hwalde/vision-mcp's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.