videre-mcp: MCP server for vision-to-text — 6 tools, 3 model modes (Florence-2, MiniCPM-V, PaddleOCR), Docling document parsing, DSPy prompt optimization
1 file for Codex and OpenCode: Videre-MCP AGENTS.md — 2,150 tokens loaded in every session.
AGENTS.md A 2,150 tok These files are Veedubin/Videre-MCP's own configuration — they tell Codex and OpenCode 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.