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。
179 个项目，匹配「vision」
qing9835
DSH 视觉模型插件：为无视觉能力的文本模型提供图片识别。粘贴/拖入/导入的图片自动交给 OpenAI 兼容视觉模型识别为文字并发送进对话，支持多轮复核（vision_ask）、多提供商配置。
reimu-create
DSH plugin: text-only models (e.g. DeepSeek-V4) automatically see images via a vision model. Official surface-replace, cache-friendly, human transcript untouched. 纯文本模型自动识图桥
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。
vocsong
A multi-tenant platform that provisions and routes isolated DeepSeek Harness (dsh) instances — one container per user.
ximengxiaolan
Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text. ???????????
zouyuanqing
Native interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid / zoom / annotate / measure / diff / color / OCR) + MiMo V2.5 multimodal backend, zero external MCP servers.
2472786266-spec
DSH DevKit: multimodal gallery + multi-agent supervision console (DeepSeek Harness dynamic Cordis plugin)
342949145
DSH 识图桥接插件：让 DeepSeek 等纯文本模型会话也能发送图片，图片自动经视觉模型识图转文字（识图桥接，read_image 工具兼容）
AlloyPlane
该仓库暂未提供项目说明。
Bernardxu123
DeepSeek Harness (dsh) 官方 bundle 规范插件集合: dsh-vision 看图 + dsh-sensenova-image 生图 + dsh-client-stats-decimal 统计两位小数
CultOfLuna
DeepSeek 的"自动挡"：有图切 Vision，无图回 Pro/Flash，一键都不用点。 DeepSeek's "automatic transmission": image in → Vision, image out → back to Pro/Flash — not a single click.
Harvey-Will
DeepSeek Harness 图像理解插件 · 8 种分析模式 · 支持任意API接口 · 内置免费视觉模型 | DeepSeek Harness vision plugin · 8 analysis modes · works with any OpenAI- or Anthropic-compatible API · built-in free vision model
Isekai-Mfu
DSH plugin: dispatch image-recognition tasks to an opencode-go mimo-v2.5 subagent via system-prompt injection
Koreyer
A DeepSeek Harness tool plugin that lets text-only agents "see" local images — auto-detects the real format and returns a detailed text description via any OpenAI-compatible vision model.
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).
Nicholaskin
DSH（DeepSeek Harness）插件：800×800 无损切块 + 坐标标注 + 直连 DeepSeek 视觉 API 识别聚合，专治大图看不清
PRTS168
Chat with, monitor, and approve your DSH (DeepSeek Harness) agents from WeChat over the clawbot iLink gateway: two-way text/images/voice/files/video, native vision or OCR, context-rotation policies, reminders, and a standalone admin console.
Practice019
DSH 插件：通过本地 Quicker 转发（doubao web2api） 提供 `doubao_ask` 动态搜索/图片生成/多模态识图工具， 并支持**粘贴图片 → 本地路径**（paste-to-path）。
TNTsama11
DeepSeek Harness (DSH) plugin that lets a text-only agent call DeepSeek-V4-Flash-Vision-Exp to see images on demand, without manually switching models.
TiankunDai
让你能通过deepseek harness调用LM studio加载的本地视觉模型
TwistedRiCen
DSH-native Vision Evidence bridge for text-only reasoning models with native image attachments and strict multi-image validation.
WardLu
Open-source MCP vision server that gives text-only LLMs and AI agents image understanding, OCR, visual analysis, UI inspection, and multimodal capabilities.
YJLTF
一个 DeepSeek Harness 插件：为纯文本主模型补上识图能力。它把图片理解委托给你配置的一个小参数多模态模型，再把结果以文本形式交还给主模型；当活跃模型自身支持图片输入时，插件完全退避，原生多模态体验不受任何影响。
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.