Easy Vision
Koreyer/easy-vision · model-adapters
A DeepSeek Harness tool plugin that lets text-only agents "see" local images — auto-detects the real format and returns a detailed text description via any OpenAI-compatible vision model.
★ 2GitHub stars
0Forks
2026-08-25Last updated
JavaScriptLanguage
MITLicense
Key features
- Give a text-only agent the ability to "see" local images — from any OpenAI-compatible vision model.
- Auto-detects the real format — reads magic bytes (PNG / JPEG / GIF / WebP), tolerating wrong file extensions
- Sends the image as a base64 data URI to your configured OpenAI-compatible vision model via chat completions
- Returns a text description — or optionally writes it straight to a Markdown file for a UI spec, mockup notes, or any document
Requirements
- Requires an OpenAI-compatible endpoint that accepts base64 image_url data URIs.
- The API key is resolved from the environment or $DSH_HOME/.credentials.yaml
Install command
dsh plugin --profile web add github:Koreyer/easy-vision