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。
44 个项目，匹配「multimodal」
haiziyao
Vision routing and image generation for DeepSeek Harness through a fixed Mix model.
hyper-dsh-plugins
A lightweight DeepSeek Harness vision delegation tool for text-only routes, with native OpenAI Responses, Chat Completions, and Anthropic Messages adapters.
mochgolf
Transparent image preprocessing route for DeepSeek Harness
shaoqiuyuavailable
Scene-aware vision routing layer for DeepSeek Harness (dsh): decides which engine/backend an image should go to (chat/UI/table/code) before other vision plugins route it. Switch-gated, front-loaded, never touches other plugins' tools. 场景级识图路由层。
tiefeiyu
A see_image vision tool plugin for DeepSeek Harness — describe images through any OpenAI-compatible vision model (GitHub Copilot, OpenAI, Ollama, vLLM, LM Studio).
wang-bool
dsh 插件，可以支持图像上传，图像识别。将ds的使用体验变为多模态
1HelloMan1
Silent vision bridge for DeepSeek Harness: route chat images to a fixed vision model, preserve UI originals, and reuse observations across compaction and restarts.
AlloyPlane
该仓库暂未提供项目说明。
Leeminjing
Give text-only DeepSeek models on-demand vision: upload images, DeepSeek answers by calling a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).
NormanFxxkingRockwell
DeepSeek Harness 视觉桥：自动发现你已配置的多模态模型，给纯文本主模型装上 vision 工具，识别结果以纯文本返回。零配置，一条命令安装。
YYTbit
Vision toolkit for DeepSeek Harness -- give text-only agents eyes
ZhuXinAI
CLI-first vision sidecar for text-only coding agents. Analyze screenshots, diagrams, charts, UI diffs, and videos with OpenAI-compatible multimodal models.
sunxin-ai
Design-fidelity QA for DeepSeek Harness: lend any text-only model an eye, then judge whether the implementation matches the mock. Ships the benchmark behind that judgement — four fixtures, 23 injected defects, and every raw model transcript. Retires itself when DeepSeek ships vision.
v587d
给纯文本 LLM 一双慧眼。 一个 DeepSeek Harness（DSH）原生 skill + 零依赖 Python CLI， 为 DeepSeek 等纯文本模型补上图像理解与文档解析（OCR、表格、公式、PDF → Markdown）， 使用免费额度优先的三方多模态 API，国内网络直连、无需代理。
wulusai2333
DeepSeek Harness (DSH) native plugin — describe_image tool: a vision bridge (image → mimo-v2.5 → text description) over the ctx.fs / ctx.credentials seams
zjcdkj
DeepSeek Harness (DSH) plugins. qwen-image gives a text-only coding model eyes: an image goes to a Qwen-VL route through ctx.llm and comes back as text, so DeepSeek keeps coding while Qwen looks. Pure ESM, no build permission at install. | DSH 插件集：qwen-image 让纯文本模型借千问 VL 读图，返回文本；纯 ESM，安装无需构建授权。
DreamRift
DeepSeek Harness 多模态视觉桥（dsh-vision-bridge）：贴图经 llm/stream 自动转 VL 文字描述（解决 UNSUPPORTED_CONTENT）+ view_image/ocr_image 主动视觉工具 + 原生多模态路由自动跳过（rc.7）；零依赖。Vision bridge for text-only DeepSeek models.
hypergraphdev
DeepSeek Harness browser-extension edition: side panel with page-context awareness, vision-bridge multimodal image reading, and voice input
junhongchashui
零修改、零切换的 DeepSeek Harness 视觉能力插件：纯文本模型粘贴即读图片，云端 + 本地 Ollama 双后端自动切换，ModLens v2 风格结构化证据输出。
skillre
Zero-core-change vision capability for DeepSeek Harness: the describe_image tool + profile bundle, installable via 'dsh plugin add'