ximengxiaolan/dsh-vision-bridge

dsh-vision-bridge

BundleVision3 GitHub stars

Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text. ???????????

Install

npx @deepseek-ai/dsh plugin --profile web add dsh-vision-bridge

Restart `dsh web` after install. Bundle APIs can change during the developer preview.

liustack/modlens

Paste an image, get OCR and layout evidence.

Anionex/dsh-vision-toolkit

Image Q&A, long-screenshot OCR, and UI reconstruction.

ysr666/dsh-vision-router

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel d...