JevMade hello@JevMade.com
← Back to experiments

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.

Source screenshot of jev-eyes
SOURCE SCREENSHOT · source ↗ · captured 2026-09-24Full screenshot ↗

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.

Maker-reported (not independently measured by JevMade): "in about two seconds" for `jev-eyes see` on a 1440×900 banking screen (README caption)

Primitives
choice, noul, score
Platform
Python
Added
Project created

Source checked 2026-09-24 — opened the GitHub repository directly.