← 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.

852 indexed pluginsSorted by popularityPage 3 of 24View newestRecently updated
View plugin dsh-prompt

dsh-prompt

FeatherHunter/dsh-prompt

47GitHub stars
Manifest Valid

A prompt toolbox for DeepSeek Harness offering 24 preset templates, /prompt slash command, and custom template management directly in the chat UI.

DSH Profile: webv0.4.34MIT
View plugin
View plugin dsh-pua

dsh-pua

MichengAI/dsh-pua

39GitHub stars
Manifest Valid

Enhance DeepSeek Harness agents with iterative task persistence, customizable personas, verification loops, and status panels.

DSH Profile: webv1.0.3Apache-2.0
View plugin
View plugin clutch-dsh

clutch-dsh

Cerbur/clutch-dsh

34GitHub stars
Indexed

A suite of productivity plugins for DeepSeek Harness including Git Worktree management, session titling, discussion workflows, and celebratory UI effects.

DSH Profile: webvworktree-release-0.1.18MIT
View plugin
View plugin dsh-robotic-harness

dsh-robotic-harness

dingkaihu63/dsh-robotic-harness

26GitHub stars
Indexed

An installable DeepSeek Harness bundle for robotics and embodied-intelligence workflows, spanning asset inspection, MuJoCo simulation, diagnostics, experiment evidence, and reports.

DSH Profile: rh-demov0.1.0MIT
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.