"author:Veloce-AI" matching MCP servers:

• screencye

  veloce-ai-idm

  A

  license

  -

  quality

  B

  maintenance

  Eyes for text-only LLMs: decodes screenshots into exact structured text (words, coordinates, sizes, colors) using pure-code CV and OCR. Enables text-only models to reason about UI layouts without vision models or VRAM usage.

  Updated 6 days ago (2026-08-08 13:37 UTC)

  MIT