DSH插件商店 DSH-plugin store

DSH-PLUGIN STORE / LIVE CATALOG

DSH插件商店

聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。

已收录
4403
功能分类
11
更新时间
08/18 02:30
全部 4403 界面增强 235 Agent 与会话 271 开发工具 341 消息通讯 128 文件与数据 256 模型与 MCP 163 安全与治理 93 部署运维 135 生活娱乐 124 学习研究 46 其他 2611

77 个项目，匹配「mod」

文件与数据 插件

dsh-draw-router

xiaozhe7772222

Universal image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint. Supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more. | DeepSeek Harness 统一绘图路由器

deepseek-harness dsh dsh-plugin image-generation
2 1 1
3 天前
文件与数据 插件

dsh-youreyes

54xkeee

Eyes for text-only DeepSeek on DeepSeek Harness: model-invokable vision tool + wrapper adapters + general VLM channels (OpenAI-compatible / Gemini / local Ollama)

deepseek dsh dsh-plugin gemini
1 0 0
2 天前
文件与数据 插件

DeepSeek Harness 视觉增强插件：将图片交给外部视觉模型分析，输出带坐标化视觉原语的纯文本证据，使不支持多模态的文本模型也能在对话中理解图片、截图与文档。

deepseek-harness deepseek-harness-plugin dsh dsh-plugin
1 0 0
3 天前
文件与数据 插件

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.

cordis-plugin deepseek-harness dsh-plugin image
1 0 0
3 天前
文件与数据 插件

dsh-eyes

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).

dashscope deepseek-harness dsh-plugin multimodal
1 0 0
2 天前
文件与数据 插件

dsh-auto-vision

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。

cordic deepseek-harness dsh dsh-plugin
1 0 0
1 天前
文件与数据 插件

dsh-computer-use

ThreeBody6666

Native Windows Computer Use and configurable vision tools for DeepSeek Harness.

computer-use deepseek-harness dsh-plugin vision-model
1 0 0
3 天前
文件与数据 插件

Vision toolkit for DeepSeek Harness -- give text-only agents eyes

deepseek-harness deepseek-vl dsh-plugin multimodal
1 0 0
5 天前
文件与数据 技能

sidesight

ZhuXinAI

CLI-first vision sidecar for text-only coding agents. Analyze screenshots, diagrams, charts, UI diffs, and videos with OpenAI-compatible multimodal models.

agent-skills agentic-workflow claude-code claude-skills
1 0 0
4 天前
文件与数据 插件

deepseek-eyes

fryghost

Community plugin for DeepSeek Harness: give text-only models eyes - paste images natively, described via an OpenAI-compatible vision API

deepseek deepseek-harness dsh-plugin plugin
1 0 0
4 天前
文件与数据 插件

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。

agent deepseek-harness dsh-plugin vision
1 0 0
2 天前
文件与数据 技能

Give DeepSeek Eyes · 给 DeepSeek 装眼睛 — a DeepSeek Harness (DSH) Skill: local vision models or vision APIs let DeepSeek read images and graphic files

agent-skills ai-agents computer-vision deepseek
1 0 0
1 天前
文件与数据 插件

Jina AI tools for DeepSeek Harness: 12 model tools (web / arXiv / SSRN search, read, screenshot, embeddings, rerank, classify, PDF, primer) plus a settings-page API key card with live balance check.

agent dsh-plugin jina jina-search
1 0 0
3 天前
文件与数据 插件

dsh-screenshot

paicat1

Standalone screen capture for DeepSeek Harness (dsh): browser hotkeys plus an agent-facing capture+read tool. Forked out of @liustack/modlens#48 (upstream declined the feature).

deepseek-harness dsh-plugin screenshot vision
1 0 0
1 天前
文件与数据 技能

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。

dsh-plugin dsh-skill free-first multimodal
1 0 0
4 天前
文件与数据 插件

dsh-computer-use

xiaoheizi1212

Model-agnostic Computer Use for DeepSeek Harness: isolated browser, Windows native helper, third-party vision perception, and a Chrome Cookie Bridge.

computer-use computer-use-agent dsh-plugin playwright
1 0 0
4 天前
文件与数据 插件

Eyes for text-only DeepSeek: view_image tool (local Ollama or any OpenAI-compatible VLM) + chat image-attachment bridge — paste/drop images in the chat and the model can see them.

deepseek-harness dsh dsh-plugin multimodal
1 0 0
3 天前
文件与数据 技能

dsh-plugins

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。

agent-skills claude-code codex coding-agent
1 0 0
1 天前
文件与数据 插件

dsh-vision-bridge

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.

cordis deepseek dsh dsh-plugin
0 0 0
1 天前
文件与数据 渠道适配

Eyes for text-only DSH agents: bridges chat.deepseek.com's vision mode into DeepSeek Harness — deepseek_vision tool, in-chat image transcription, WeChat-QR login in Settings.

bridge deepseek deepseek-harness dsh
0 0 0
1 天前
文件与数据 插件

dsh-gemini-multimodal

RealAlexandreAI

该仓库暂未提供项目说明。

dsh dsh-plugin gemini multimodal
0 0 0
1 天前
文件与数据 插件

dsh-vision

joyiok

DSH plugin: image_analyze tool that sends screenshots/photos to an OpenAI-compatible vision model

deepseek-harness dsh-plugin vision
0 0 0
3 天前
文件与数据 插件

dsh-vision-relay

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。

cordis deepseek-harness dsh dsh-plugin
0 0 0
4 天前
文件与数据 插件

DeepSeek VisionPlus — official-grade vision extension for DeepSeek Harness. Routes image understanding to a free vision-model pool (Zhipu GLM, SiliconFlow Qwen) with automatic fallback, rate limiting, one-click platform tests and live status lines; text stays on DeepSeek. One-command install. MIT.

deepseek deepseek-harness dsh dsh-plugin
0 0 0
1 天前