What it does
A CLI, an MCP server and an agent skill let a coding agent hand Jev a screenshot instead of pixels. Perception needs no API key, so it can be inspected before paying for a decision.
Integrations
jev-eyes
Turns an image into the text state Jev can judge — local OCR in reading order plus a character-grid layout map — and returns exactly what the model will see.
Bookmark: jev-eyes
Keep this in your collection.
Leave a noteWhat would you try with this?
: jev-eyes
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
How you can use it
A developer can use this code to read text from a screenshot. The tool extracts words and their exact locations into a text grid on your computer. You can check this local information before sending it.
An access key connects the app to Jev, an outside AI service. The app sends the text grid and asks several questions together. You can ask if the picture is purely decorative. You can also categorize it as a chart, photo, or document.