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.

589 indexed pluginsSorted by popularityPage 17 of 17View newestRecently updated
View plugin dsh-tokstat

dsh-tokstat

kongjianguan/dsh-tokstat

0GitHub stars
Manifest Valid

DeepSeek Harness settings-panel plugin for local usage, latency, throughput, and estimated-cost statistics, with an optional Python TUI.

DSH Profile: web-devv0.1.1MIT
View plugin
View plugin dsh-zhipu

dsh-zhipu

fineven/dsh-zhipu

0GitHub stars
Manifest Valid

An all-in-one Zhipu BigModel integration for DeepSeek Harness, providing web search, server-rendered web reading, and GLM-4.6V vision features through one ZAI_API_KEY.

DSH Profile: webv1.0.1MIT
View plugin
View plugin plug

plug

qing9835/plug

0GitHub stars
Manifest Valid

A DeepSeek Harness plugin that converts pasted, dropped, or imported images into text through an external vision model before sending the result to a text-only model.

DSH Profile: <name>v1.0.0MIT
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.