vision — A question answered about an image — openbash

A vision model reads images at urls and answers in words: what is in it, what it says, whether two match.

vision

vision is a command on the openbash shell, reachable over HTTP, SSH and MCP with one key. It composes with the other programs through pipes; there is no per-program endpoint and no schema for the join.

vision ask "which of these is a serial number plate?" https://example.com/a.jpg,https://example.com/b.jpg

help

vision: ask about an image, as JSON.

TAKES URLS
  Comma-separate several for `ask`. Not local files.

Studies:
  ask  <prompt> <images>
      ask a question about one or more images at urls — comma-separate them
  qwen <prompt> <image>
      the same question against a different model, one image

JSON to stdout, so it composes: pipe to `jq` to pick a field, or `> /tmp/…` to keep it.
Run a study with no arguments — `vision ask` — to see what it takes.

What it answers

vision ask — ask a question about one or more images at urls — comma-separate them
vision qwen — the same question against a different model, one image

• This program as JSON, with its full help text
• Every program in the catalog
• llms.txt — how to call it