shinjiyu/dsh-plugin-multimodal

dsh-plugin-multimodal

Name: dsh-plugin-multimodal
Author: shinjiyu

BundleVision3 GitHub stars

Vision sidecar for DeepSeek Harness: accept pasted images on text-only models.

Install

npx @deepseek-ai/dsh plugin --profile web add github:shinjiyu/dsh-plugin-multimodal

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

[![DSH Hub](https://dshhub.dev/badge/dsh-plugin-multimodal.svg)](https://dshhub.dev/plugins/dsh-plugin-multimodal)

Paste this into your README. The star count updates with every catalog sync.

liustack/modlens

Paste an image, get OCR and layout evidence.

3551 stars+1205

Anionex/dsh-vision-toolkit

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

816 stars+299

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...

943 stars+524