jack4862/mimo-vision-mcp

Uses the Xiaomi MiMo v2.5 multimodal model to add image recognition capabilities to text-only base models such as deepseek-v4-flash.

These files are jack4862/mimo-vision-mcp's own configuration. They tell 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.

1Stars on the repository
1Files it configures its agents with
1,359Tokens loaded in every session
1Agent configured

Instructions