← 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 2 of 24View newestRecently updated
View plugin dsh-capability-menu

dsh-capability-menu

PKUfudawei/dsh-capability-menu

87GitHub stars
Manifest Valid

Unified capability management plugin for DeepSeek Harness providing resident, on-demand, and disabled exposure policies for tools and skills.

DSH Profile: webv0.1.5Apache-2.0
View plugin
View plugin dsh-im-connect

dsh-im-connect

MichengAI/dsh-im-connect

74GitHub stars
Manifest Valid

Connect major messaging platforms including Feishu, DingTalk, WeChat, WeCom, QQ, Telegram, Discord, and Slack to local DeepSeek Harness agents.

DSH Profile: webv1.0.9Apache-2.0
View plugin
View plugin dsh-Remote

dsh-Remote

Blank-not-black/dsh-Remote

58GitHub stars
Manifest Valid

Mobile and remote web console bundle for DeepSeek Harness with session monitoring, approval controls, and file management over LAN or Tailscale.

DSH Profile: webv0.8.0MIT
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.