Nautilo update: text models can pair with vision models for images
Nautilo now lets a text model hand attached images to a vision model, is building a Gateway that routes by price, security, and intelligence, and is replacing run_shell with a Codex-style exec_command.
Nautilo updates: 1) Working on a MAJOR Collab with the big partner coming soon. Watch for it. Going to be freaking awesome. 2) Some folks wanted to use a text model but have a vision model handle images if you attach one. Done. Shipped. 3) Working hard on Nautilo Gateway that will route you based on price/security/intelligence to the models you need for the combo requested. 4) Not loving the way run_shell tool works so replacing it with a Codex style exec_command that is more reliable. Already testing really smooth. 5) Shipped a big mobile refresh to testers and if it looks good will release to the store.