DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
52 个项目，匹配「dsh-vision」
Yuuz12
DeepSeek Harness Vision Helper/DeepSeek Harness 视觉辅助方案
haiziyao
Vision routing and image generation for DeepSeek Harness through a fixed Mix model.
lium970320
DSH 视觉桥接插件：让无视觉能力的主模型看图（会话收图 + 自动转文字 + view_image 工具）
moon09300731
DeepSeek Harness 视觉能力全家桶：vision_understand 工具 + 粘贴/拖拽/按钮三入口识图
xiaoshihou514
DeepSeek Harness: vision
yepyeel
提供dsh中deepseek v4等无法识图的模型一双眼睛
314857493
Free GLM vision for text-only DeepSeek Harness: paste images in the GUI (auto-transcribe route) + vision tool + skill
Xin-Zhang-IceMan
DeepSeek Harness 视觉插件：让纯文本模型拥有视觉能力 / Vision plugin for DSH: vision_analyze tool + automatic image transcription for text-only models.
moton16
Give your text-only LLM eyes: zero-dependency MCP server that reads images via external OpenAI-compatible vision models with automatic provider fallback, plus a one-command patch for DSH image-attachment degradation.
poiuyjie
DeepSeek Harness plugin: open .md references from chat in a dockable side-by-side preview panel instead of the system editor; per-session recent-file tracking; pairs with dsh-vision-opencode for visual-verification workflows.
princefrogdida-ux
Windows-first vision suite with image understanding, OCR, screenshot diffing, and multi-provider routing for DeepSeek Harness.
visail
Paste an image into the chat box and text-only DSH models can "see" it — auto-rewrite of pasted images + analyze_image tool routed to a Kimi vision model.
wdwind
DeepSeek Harness native vision plugin!
xzyonline
Vision for text-only DeepSeek: view_image tool via any OpenAI-compatible VLM endpoint. macOS/Windows/Linux, one-click install.
yan5236
让不支持图片输入的主模型通过已配置的视觉模型理解图片的 DSH 插件：自动桥接、像素坐标描述、vision_ask 追问工具与设置页
AbdullahElTiby
Vision bridge for text-only models (DeepSeek, pi-ai routes): Gemini Flash describes attached images at the llm stream seam and provides a describe_image tool.
Anyi-qaq
⚠️ 已归档，不再维护，不可用（archived & unavailable）
LittleInk
一键式为dsh提供看图功能，借鉴了claude-vision-skill,先让agent读取了这个skill，后面尝试使用的时候发现平台会限制ds模型直接读取图片（只能剪贴板或者路径），所以做了一个桥接功能，VLM看完图后再把内容发送给DS并输出内容
Nanawwa
Give a text-only DeepSeek Harness model eyes: a proxy provider that delegates image understanding to any vision-capable model the harness can route, plus vision and vision_config tools.
TIPSONG
该仓库暂未提供项目说明。
YuLee-314
DeepSeek Harness 视觉补全：孪生路由解锁原生图片体验，本地 Ollama 请求层看图，零云端依赖。Vision twin + local agentic vision tools for DeepSeek Harness.
Zhangbo-cn
该仓库暂未提供项目说明。
ariesy
DeepSeek Harness (DSH) dynamic Cordis plugin: global image upload button + configurable vision-model recognition with fallback
br1nosense
让 DeepSeek Harness (DSH) 纯文本模型也能发送并识别图片：识图技能（火山 doubao）+ 宿主补丁。Vision + host patch for DSH text-only models.