87 #vision DeepSeek Harness (DSH) Plugins
Every indexed repository carrying the GitHub topic vision, sorted by stars. The tag is the author's own word for it — the install verdict on each card is ours.
Repositories tagged #vision, most-starred first
Modlens
liustack
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网第一个 DeepSeek Harness 视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
Agent Vision Toolkit
Anionex
为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
Dsh Vision Router
ysr666
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
Dsh Vision
oil-oil
Near-native image understanding for DeepSeek Harness
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
linenxi-ctrl
为 DeepSeek Harness 增加外挂识图模型：圆形鲸鱼按钮、发送图片识图自动回传、模型自主截图+识图工具、多协议自动适配、小白一键安装（未装 Node.js 自动下载）
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 Drop To Path
loudMore
DSH 插件:图片与文件直达纯文本模型——图片保留原生附件体验,PDF/Office/压缩包/视频/音频显示为附件栏方块,点击发送时自动转为工作区路径,配合 dsh-vision-toolkit 粘贴即看图。A DSH plugin that delivers images AND files to text-only models as workspace paths: images keep the native attachment UI, other files show as square chips in the rail, paths append on send — pairs with dsh-vision-toolkit.
Dsh Visual Plugin
jyh20030112
Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel
Dsh Vision Provider
libinyam
Config-only DeepSeek Harness bundle for OpenAI-compatible vision models.
Dsh Image Bridge
kbpoyo
DSH 插件：让纯文本模型也能看图。Web 端直接粘贴图片即可发送，无需指定图片路径；模型自主调用视觉技能查看，多模态模型原生直通，零skill绑定。
Dsh Plugin Deepeye
Favio8
DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.
Codex Eyes Hands
651002
专为 DeepSeek Harness 打造：把本机 Codex CLI 变成纯文本 AI agent 的眼睛和手——看图/读文件/画图/监督执行/双通道容灾
Dsh Aux Vision
XyTT2N2bTc
DeepSeek Harness 辅助视觉插件：任意纯文本主模型 + 任意视觉模型（默认 opencode-go/mimo-v2.5）。含图轮自动看原图并注入描述；纯文本轮零视觉调用。Auxiliary vision for text-only models.
Dsh Auxiliary
dsh-plugins
Auxiliary models for DeepSeek Harness: vision understanding and context compression through dedicated model routes.
Dsh Xiapan Media
dongsheng123132
Native vision, gpt-image-2 and Seedance plugins for DeepSeek Harness via Xiapan Cloud
Dsh Vision
Terry12138qy
DeepSeek Harness 识图插件：为不具备原生识图能力的模型提供识图能力（阿里云百炼 qwen3.5-omni-plus，失败自动切换智谱 glm-4.6v-flash）。由 claude-vision-skill 移植适配。 | Vision tool for DeepSeek Harness
Dsh Sfversion
sparkmio
SF视觉桥——给纯文本模型的 DeepSeek Harness 装上眼睛。
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 Tool Ocr
ferstar
本地 OCR 插件：让纯文本生成 LLM 也能读懂图片 | Local OCR plugin: give text-only generative LLMs the ability to read images
Dsh Vision
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
Dsh Vision Primitives
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.
GrassVison
moduqishi
给纯文本大模型装上原生视觉：流式真实思考链 · 跨轮次无感重看 · 像素级证据与 SVG 图元 · OpenAI/Anthropic/Responses 三协议兼容 | Native vision for text-only LLMs: streaming real thinking chain, cross-turn re-view, pixel-level evidence & SVG primitives, OpenAI/Anthropic/Responses compatible.
DeepSeek Prism
YOGEMOW
为纯文本模型按需识图：DSH 零补丁 Cordis 插件（prism_see 工具 + 图片 VEP 降级 + 技能运行时注册）+ Codex Skill；多 Provider 视觉 API，VEP/1 低 Token 视觉证据包
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 Llm Deepseek Vision
NagasakiSoyo-ui
Vision-augmented DeepSeek adapter plugin for DeepSeek Harness: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description
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
Free Vision Skill
niyongsheng
Local‑only vision skill for macOS 本地化识图技能
Dsh Deepseek Vision Router
mochgolf
Transparent image preprocessing route for DeepSeek Harness
Dsh Sight
Fu3rte
Plug-in vision for text-only DeepSeek Harness (dsh) models: built-in free/cheap VLM presets + multi-image batch analysis
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 Media Skills
akqwpeter-prog
Free vision & image generation for DeepSeek Harness — paste an image into any chat, even text-only sessions. GLM-4V-Flash + Gemini failover, ModLens-style evidence, Kolors generation. 免费读图·生图 · 无 Key 入库
Dsh Ui Spec
yumimanji
DeepSeek Harness plugin: turn UI screenshots into structured, implementation-grade web frontend specs. Deterministic geometry (sharp) + optional vision-model semantics, merged into one JSON + Markdown spec.
Dsh Mimo Vision Hint
Isekai-Mfu
DSH plugin: dispatch image-recognition tasks to an opencode-go mimo-v2.5 subagent via system-prompt injection
Dsh Vision Bridge
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）
Dsh See Image
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).
Dsh Vision Helper
Yuuz12
DeepSeek Harness Vision Helper/DeepSeek Harness 视觉辅助方案
Ds Vision Plugin
Sorwcyra
Paste images into DeepSeek Harness with a four-model vision race, OCR, and an automatic text bridge.
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
Dsh Vision Bridge
Xieweikang123
Give a text-only dsh model eyes: pasted images recognized into text via an OpenAI-compatible vision endpoint.
Dsh Vision Bridge
x-Xin23
给 DeepSeek Harness 纯文本模型装上原生视觉（Windows）：粘贴即看图——预注入描述，模型首轮就看见，不用选模型、不用调工具；see_image 精查；自定义视觉后端（任意 OpenAI 兼容模型）+ 四后端容灾；换主模型视觉自动跟随。| Give text-only DeepSeek Harness models native-feeling vision on Windows: paste and the model just sees it — pre-injected descriptions, see_image tool, custom backends, 4-backend failover.
Dsh Plugin Vision Toolkit
YYTbit
Vision toolkit for DeepSeek Harness -- give text-only agents eyes
Deepseek Eyes
fryghost
Community plugin for DeepSeek Harness: give text-only models eyes - paste images natively, described via an OpenAI-compatible vision API
Dsh Img
gmleong
Give text-only models eyes: analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible endpoint. 给纯文本模型装上眼睛的 dsh 插件。
Dsh Plugins
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
Easy Vision
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.
Doubao Vision Dsh
hawkongz
让纯文本模型通过桌面豆包看见聊天图片的 DeepSeek Harness 宿主插件(CDP 桥接,全预设生效,识别可取消)
Dsh Sight
cransmathenia666-hash
Give text-only DeepSeek Harness (dsh) agents vision — pasted images auto-convert to text descriptions with persistent caching, each image converted only once.