dsh-community-pluginsDeepSeek Harness 社区插件中心：对接 GitHub dsh-plugin 话题社区，侧边栏一键浏览/安装/卸载社区插件（镜像加速）
최고의 DSH 플러그인을 만나보세요
시각 도구 · DeepSeek Harness 플러그인 — 23 페이지
1453개 결과
이미지 이해, 스크린샷 분석 및 시각 상호작용 플러그인의 입력 조건과 사용법을 비교하세요.
dsh-composer-image-tools聊天输入框图片工具(自研):上传图片(≤10MB 防烧 token) + 自定义区域截图(Electron desktopCapturer),注入 DSH 草稿图片轨。零外部依赖。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ai-yucheng/dsh-composer-image-toolsdsh-computer-useDSH 视觉整机控制插件（P2）：经 macOS Accessibility API（AXUIElement）把本机 GUI app 变成 AX 快照优先的元素级工具集（观察 4 + 窗口管理 1 + 动作 6 + 截图兜底 1，共 12 个 computer_* 工具）；v0.2.0 窗口对象化：windowId 不透明句柄（WindowRegistry + tombstone + CG 截图绑定）+ 输入后端分层（mode/delivery，Tier 1 pid 定向预留）；Swift 辅助进程零 npm 依赖；敏感动作可选人工审批（默认关）。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DjangoAILab/dsh-plugins#18ae7e5df085d28e7a573d1e3ef0286bda1ea793&path:plugins/manual/dsh-computer-usedsh-computer-useModel-agnostic Computer Use capability for DeepSeek Harness: isolated browser first, provider-neutral observation, text planner + third-party vision perception.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiaoheizi1212/dsh-computer-usedsh-cost
★ 1dsh-cost用量与费用面板：token 消耗、峰谷计价估算、DeepSeek 真实余额（web profile 本地插件）
dsh-cursor-themeCustomize the PC mouse cursor for every UI state inside DeepSeek Harness. 在 DSH 里自定义鼠标各种状态的图案。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:auki-zy/dsh-cursor-themedsh-custom-brandCustomizable brand area for the DeepSeek Harness web GUI: replace the whale logo and the DeepSeek wordmark with local images, and edit the HARNESS badge text — double-click to change, right-click to reset. 自定义 DSH 左上角品牌区：logo 与 DeepSeek 文字可换本地图片，HARNESS 徽章文字可双击编辑。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:baisama-cloud/dsh-custom-branddsh-custom-provider-settingsRequest headers, image input, and reasoning settings for custom DeepSeek Harness providers
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:supersealwqas/dsh-custom-provider-settingsdsh-deepseek-visionDeepSeek web vision bridge: give text-only DeepSeek models image recognition via a deepseek_vision tool
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Cheng-cheng9669/dsh-deepseek-visiondsh-deepseek-vision-routerTransparent image preprocessing route for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mochgolf/dsh-deepseek-vision-routerdsh-design-qa让 DeepSeek Harness 里任何纯文本模型都能读图。识图是按需调用的 tool —— 图片不进主模型上下文，不看就不花钱；附 23 处缺陷的评测集，换模型可自测。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sunxin-ai/dsh-design-qadsh-desktop
★ 1dsh-desktopDSH Desktop — 内嵌官方 DeepSeek Harness Web UI 的桌面客户端（含自动更新）
dsh-desktop-voice官方 DeepSeek Harness（dsh）原生桌面壳：Tauri 2 把官方 WebUI 变成原生桌面窗口，保留会话/工作区/插件/技能。内置 SenseVoice 离线语音输入、插件市场、视觉模型配置；锚定模式解决 DeepSeek 思考模式问题
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:TommyFang2077/dsh-easy-desktop#b15292dd03bb9542ff9dad70388dc3137fdb92b7&path:plugins/dsh-desktop-voicedsh-doc-shareDSH 对话报告化分享插件：生成带封面、摘要统计与章节排版的精美报告，导出为 PNG 图片 / 单 HTML 文件 / PDF。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dawsondx/dsh-doc-sharedsh-docling
★ 1dsh-doclingNative document intelligence for DeepSeek Harness, powered by Docling.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Sqhao-O/dsh-doclingdsh-easy-mcp
★ 1dsh-easy-mcpDSH MCP 服务器图形化管理插件：在设置界面查看/新增/编辑/启用禁用/删除/重连/测试 MCP 服务器（stdio / streamable-http / SSE，含 resources/prompts 与图片桥接），配置持久化到 settings.yaml，变更实时生效。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:amazing-tree-keeper/dsh-easy-mcpdsh-ernie-imageDSH ERNIE-Image-Turbo text-to-image plugin: generate images via Baidu AI Studio, save them as durable session attachments, plus a settings card and a generation gallery panel
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:omdsh-dev/dsh-ernie-imagedsh-eye-visiondsh-eye-vision: give text-only DeepSeek Harness models eyes — image understanding via any OpenAI-compatible multimodal API. Fork of dsh-free-vision with custom-provider fixes and an allowed-directories whitelist.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AlloyPlane/dsh-eye-visiondsh-eyebrain
★ 1dsh-eyebraindsh-eyebrain：识图桥(understand_image) + 思考档位控制 + 发送接管。为纯文本主模型外挂小参数多模态模型，全部配置在 dsh Web 内完成，无需手改配置文件。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YJLTF/dsh-eyebrain#6598e911a4b9955a23171f937165364106e650f5&path:packages/dsh-eyebraindsh-eyebrain-clientdsh-eyebrain 的 dsh Web 客户端插件：插件设置卡片（识图模型 / 思考档位 / 接管清单）+ composer 工具行思考强度 chip（会话级覆盖）。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YJLTF/dsh-eyebrain#6598e911a4b9955a23171f937165364106e650f5&path:packages/dsh-eyebrain-clientdsh-eyes
★ 1dsh-eyesOn-demand vision for text-only LLMs in DeepSeek Harness: keep pasted/attached images in the backend, and let the model call view_image to look at them anytime via any OpenAI-compatible vision endpoint — as if the model were natively multimodal.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Leeminjing/dsh-eyesdsh-file-drop拖拽非图片文件：桌面壳直取原始路径 / 拖拽自带路径直取 / 普通文件上传到工作区换取路径
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dannyvan/dsh-file-dropdsh-file-upload-local本地手搓的 DSH 文件上传插件：流式上传（突破 base64 大小限制）、文件卡片、chat history 内预览/下载、图片内联预览
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DjangoAILab/dsh-plugins#18ae7e5df085d28e7a573d1e3ef0286bda1ea793&path:plugins/manual/dsh-file-uploaddsh-file-viewerRead-only file previews inside DeepSeek Harness for images, PDF, CSV, Markdown, JSON, YAML, source code, and large files.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:liguobao/dsh-file-viewer검색부터 설치까지
작업으로 검색
기능 키워드나 카테고리로 범위를 좁히고 최근 업데이트 또는 GitHub Star로 정렬하세요.
기능 살펴보기
소개, AI 분석, 원본 README를 읽고 플러그인의 기능을 확인하세요.
확인 후 설치
호환성과 의존성 범위, 설치 안내를 확인한 뒤 제공된 설치 명령을 복사하세요.
DSH Hub 자주 묻는 질문
DSH Hub란 무엇인가요?
DeepSeek Harness 커뮤니티 플러그인 디렉터리입니다. 소개, 소스 링크, 설치 안내를 모아 확장 기능 검색과 비교를 돕습니다.
등록된 플러그인은 호환성 검증이 끝났나요?
아니요. 상세 페이지는 기록된 호환성과 의존성 범위를 표시합니다. 알 수 없음은 호환을 의미하지 않으므로 설치 전 프로젝트 문서를 확인하세요.
어떻게 설치하나요?
상세 페이지의 설치 영역을 확인하세요. 명령이 있으면 Harness 환경에 복사해 실행하고, 없으면 프로젝트 README를 따르세요.