DSH Plugins

ds-vision-plugin

by Sorwcyra · Sorwcyra/ds-vision-plugin

Manifest valid

4 Stars

0 Forks

Updated: Aug 14, 2026

Install

dsh plugin --profile web add ds-vision-plugin
GitHubnpm

MIT

JavaScript

Original language: English

hasBundlePatch

About

Paste images into DeepSeek Harness with a four-model vision race, OCR, and an automatic text bridge.

Similar plugins

dsh-plugin-multimodal

by shinjiyu

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

Vision & MultimodalManifest valid

3

MIT

TypeScript

Aug 16, 2026

dsh plugin --profile web add dsh-plugin-multimodal

by siegfly

Vision-language gateway plugin for DeepSeek Harness - paste an image, DeepSeek sees text

Vision & MultimodalModels & ProvidersManifest valid

8

MIT

TypeScript

Sep 11, 2026

dsh plugin --profile web add dsh-deepseek-vision

by zyh20041227

Full-coverage image tiling for DeepSeek Harness vision models, dense-text OCR, and document AI

Manifest valid

4

MIT

TypeScript

Aug 23, 2026

dsh plugin --profile web add dsh-vision-tiler

by ysr666

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

Vision & MultimodalModels & ProvidersManifest valid

1.1k

8.7k/wk

MIT

JavaScript

Sep 13, 2026

dsh plugin --profile web add dsh-vision-router

by poiuyjie

DSH plugin: Auto-convert images to text for pure-text LLMs (DeepSeek etc.) via any vision model. No need to switch your main model.

Tools & CapabilitiesVision & MultimodalManifest valid

13

MIT

JavaScript

Sep 9, 2026

dsh plugin --profile web add dsh-vision-opencode

Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Vision & MultimodalManifest valid

0

778/wk

dsh plugin --profile web add dsh-tesseract-ocr