Paste an image and it just works — eyes for text-only agents on DeepSeek Harness. Free out of the box, no key, no Python, one command.
功能特性
- No Python. The whole pipeline — downscale, grounding, crop, pixel diff, palette, OCR, SVG trace, cutout, HTML screenshot — runs on sharp / potrace / tesseract / system Chrome.
- DeepSeek stays the brain. Text turns are untouched in model, cost and context. The vision model is only the eyes, called on demand; answers are cached by image content.
- Selective proxy. Only the configured vision provider hosts go through your local proxy; DeepSeek stays direct.
- Auto-create “+ Auto Vision” model groups: enabled by default; follows the live model catalog with no restart;
- Manual auto-vision scope (optional): only for disabling auto-wrap or limiting selected models;
- Vision backend chain: the real image-capable models used by vision_describe and friends; the built-in free Qwen is normally enough, and text-only models should not be placed here;
安装命令
npx dsh-vision-router repair --profile web项目预览
项目简介
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.