← All plugin categories
DSH Plugin Category

DeepSeek Harness Vision Plugins

Explore DeepSeek Harness plugins for image understanding, OCR, multimodal input, visual grounding, image analysis, and other vision workflows.

674 indexed pluginsSorted by popularityPage 1 of 19View newestRecently updated
View plugin ModLens

ModLens

liustack/modlens

4.1kGitHub stars
Manifest Valid

A DeepSeek Harness vision plugin that turns pasted images into structured OCR, layout, and semantic evidence for supported text-only models.

v3.26.5MIT
View plugin
View plugin mnemon

mnemon

mnemon-dev/mnemon

596GitHub stars
Manifest Valid

A standalone, local persistent-memory system for AI agents, with DeepSeek Harness support provided through the separate dsh-mnemon plugin.

DSH Profile: webv0.2.9Apache-2.0
View plugin
View plugin dsh-cost-meter

dsh-cost-meter

Han-1413141/dsh-cost-meter

344GitHub stars
Manifest Valid

A bilingual DeepSeek Harness cost-tracking plugin with session and daily costs, budgets, pricing management, balance lookup, and coding-plan quota displays.

DSH Profile: webv1.7.44MIT
View plugin
View plugin dsh-personal-center

dsh-personal-center

PolinniZhong/dsh-personal-center

120GitHub stars
Manifest Valid

A local, offline Personal Center plugin for DeepSeek Harness with token analytics, cost estimation, custom instructions, font scaling, and a desktop pet.

DSH Profile: webv1.1.1MIT
View plugin

About DeepSeek Harness Vision Plugins

DeepSeek Harness vision plugins add image and multimodal capabilities to DSH workflows that would otherwise depend mainly on text. This category covers image understanding, OCR, visual grounding, image Q&A, screenshot inspection, pixel comparison, artifact handling, and bridges to external vision models. It brings these plugins together so users can compare repository identity, DSH profiles, activity, verification state, and install information.

Before installing a vision plugin, check the DSH profile it targets, supported input formats, external model or API requirements, local dependencies, and Registry compatibility evidence. Security Signals and source metadata expose relevant implementation facts, but they are evidence for review rather than an absolute safety guarantee.