dsh-plugin-multimodal
by shinjiyu · shinjiyu/dsh-plugin-multimodal
★ 3 Stars
⑂ 0 Forks
◎ 1 Open issues
Updated: Aug 16, 2026
MIT
TypeScript
Original language: English
About
Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.
Similar plugins
by siegfly
Vision-language gateway plugin for DeepSeek Harness - paste an image, DeepSeek sees text
★ 8
MIT
TypeScript
Sep 11, 2026
dsh plugin --profile web add dsh-deepseek-visionby 121103qwq
Hosted free vision sidecar for DeepSeek Harness with durable session evidence
★ 4
MIT
JavaScript
Aug 14, 2026
dsh plugin --profile web add dsh-vision-sidecarby Sorwcyra
Paste images into DeepSeek Harness with a four-model vision race, OCR, and an automatic text bridge.
★ 4
MIT
JavaScript
Aug 14, 2026
dsh plugin --profile web add ds-vision-pluginby Fu3rte
Plug-in vision for text-only DeepSeek Harness (dsh) models: built-in free/cheap VLM presets + multi-image batch analysis
★ 3
MIT
JavaScript
Aug 15, 2026
dsh plugin --profile web add dsh-sightby poiuyjie
DSH plugin: Auto-convert images to text for pure-text LLMs (DeepSeek etc.) via any vision model. No need to switch your main model.
★ 13
MIT
JavaScript
Sep 9, 2026
dsh plugin --profile web add dsh-vision-opencodeby Scorp1o117
Vision model for DeepSeek Harness | DeepSeek Harness 外置视觉模型插件
★ 8
JavaScript
Sep 11, 2026
dsh plugin --profile web add dsh-tool-vision