← 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 18 of 24View newestRecently updated
View plugin dsh-image-vision-bridge

dsh-image-vision-bridge

Icestab/dsh-image-vision-bridge

1GitHub stars
Manifest Valid

A DeepSeek Harness host plugin that converts chat images into vision-model descriptions for text-only main models while preserving original images in the visible transcript.

DSH Profile: webv0.1.2MIT
View plugin
View plugin dsh-token-stats

dsh-token-stats

FantasyStarry/dsh-token-stats

1GitHub stars
Indexed

DeepSeek Harness Web plugin that tracks daily LLM token usage by provider and model, with cost estimates, balance lookup, dashboards, and a /usage command.

DSH Profile: webv0.10.0
View plugin
View plugin dsh-realtime-voice

dsh-realtime-voice

zfu691531-hash/dsh-realtime-voice

1GitHub stars
Manifest Valid

A DeepSeek Harness realtime voice plugin that connects Qwen or OpenAI speech providers for ASR, voice-driven Harness turns, and streamed TTS playback.

DSH Profile: webv0.12.0MIT
View plugin
View plugin dsh-plugin-backup

dsh-plugin-backup

Eicbro3ding/dsh-plugin-backup

1GitHub stars
Manifest Valid

A DSH web settings plugin that exports and incrementally restores installed third-party plugins, custom skills, and DSH configuration as JSON snapshots.

DSH Profile: webv0.1.0
View plugin
View plugin dsh-image-unlock

dsh-image-unlock

FrostLeafKEE/dsh-image-unlock

1GitHub stars
Manifest Valid

DeepSeek Harness plugin that admits image attachments in the Web GUI and converts them to text markers for a vision-skill workflow on text-only opencode-go upstreams.

DSH Profile: webv0.0.3MIT
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.