17 Image Understanding Qwen Mm Plugins DSH Plugins
A cluster of 17 repos centred on multimodal, ocr and vision.
How this collection was built
This collection is machine-derived: DeepSeek Harness plugin READMEs are vectorised with TF-IDF and grouped by cosine similarity, so membership is a statement about wording, not an endorsement — it can be, and sometimes is, overridden by hand. No official DSH extension point maps cleanly onto this cluster; browse categories for the authoritative axis. Members are ordered by GitHub stars. Clustered on 2026-08-15.
Members, most-starred first
Dsh Vision
oil-oil
Near-native image understanding for DeepSeek Harness
Dsh Vision
william-jin-cmu
dsh 插件：给纯文本 DeepSeek 加视觉——view_image 工具桥接任意 OpenAI 兼容 VLM（默认智谱免费档，实测 4 厂商 10 模型）
Dsh Vision Complete
Yts1919
给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。
Dsh Vision Proxy
Flyvhidbwo
DeepSeek Harness 插件：DeepSeek 大脑 + 自动识图。GUI 附加图片自动经 OpenAI 兼容 VLM 转译成文字后交给 DeepSeek 作答；支持百炼/智谱/OpenRouter 等任意 OpenAI 兼容端点（默认 qwen3.7-flash），无 key 自动探测本地 Ollama（图片不出本机）；安装时有一问式确认
Dsh Plugin Deepeye
Favio8
DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.
Dsh Her Eyes
huashenglian
一个可以让ai自动调用VLM(多模态模型)进行视觉分析的dsh插件。A dsh plugin that allows AI to automatically invoke VLMs (multimodal models) for visual analysis.
Qwen MM Plugins
omdsh-dev
Qwen-MM-Plugins支持
Dsh Image Router
1m01m0
Configurable multimodal vision routing for DeepSeek Harness
Dsh Multimodal
MC5lan
给 DeepSeek 安装一双眼睛和一支画笔:会话里直接贴截图/图片,GLM 视觉模型先精确转写图片内容(报错信息、代码、界面逐字保留),然后 DeepSeek 继续处理你的问题——同一轮完成,全程无感;需要配图时,DeepSeek 自动调用文生图后端出图并显示在会话中。
Dsh Deepseek Vision
Argonaut790
Image understanding, OCR, and persistent visual evidence for text-only DeepSeek Harness models
Deepseek Omnimodal
good-boy4069
Open-source multimodal MCP plugin for text-only AI agents: recognize and generate images, video, and audio through Qwen/DashScope. Supports Codex, Claude Code, and DeepSeek Harness ecosystem.
DSH Plugins 4U
honghudavy-star
DSH 自建插件集合：微信桥接器 + GUI 微信入口补丁，一键安装
Shadow Vision
WardLu
Open-source MCP vision server that gives text-only LLMs and AI agents image understanding, OCR, visual analysis, UI inspection, and multimodal capabilities.
Dsh Deepseek Vision Router
mochgolf
Transparent image preprocessing route for DeepSeek Harness
Dsh Qwen Mm
RRRosmontis
Qwen-MM-Plugins integration bundle for DeepSeek Harness (dsh) — multimodal MCP tools (vision, OCR, ASR, search, video, Blender, FreeCAD) + image attachment bridge. 让 DeepSeek Harness 原生支持多模态。
Dsh Qwen Mm Plugins
ShuiHan268
DeepSeek Harness 的 Qwen-MM-Plugins 集成插件：12 个多模态 MCP 工具（视觉/OCR/定位/ASR/音视频）、Web 设置页（粘贴 Qwen API Key 即用）、内置技能与一键安装器
Glm4v Vision Mcp
ethanweave
GLM-4.6V 图像理解 MCP：识图/OCR/图表解析，原生接入 DeepSeek Harness（dsh-mcp-client），也兼容 Codex/Cline 等