@deepseek-ai/dsh-weather-skyWeather & Sky: IP-based live weather visualization for the DeepSeek Harness browser UI (sun/moon with phases, clouds, rain/snow/fog/thunder) with conversation controls.
最高の DSH プラグインを見つけよう
7431件
Harness のパネル、テーマ、ターミナル、操作画面のプラグインを探せます。
@deepseek-ai/dsh-weather-skyWeather & Sky: IP-based live weather visualization for the DeepSeek Harness browser UI (sun/moon with phases, clouds, rain/snow/fog/thunder) with conversation controls.
@deepseek-ai/dsh-web-appThe dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chiyulogg-commits/deepseek-harness-sentence-reasoning#c54dbe8f6955ae58cd47da04888e38f9d3b8f369&path:packages/bundle/web-app@deepseek-ai/dsh-web-appThe dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chiyulogg-commits/deepseek-harness-zh-tw#820655a039d277360cec0634fc383af596874e88&path:packages/bundle/web-app@deepseek-ai/dsh-web-appThe dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:deepseeker-app/DeepSeeker#4a4e23d43bbac23d0392905748bbaa40c35d5989&path:packages/bundle/web-app@deepseek-ai/dsh-web-appThe dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Missher12/deepseek-harness-desktop#013c602ae9e498d4ff4cb89e03828d0462a911cf&path:packages/bundle/web-app@deepseek-ai/dsh-web-appThe dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Shonean/deepseek-harness-vscode-desktop#be5ea06574a5704125af750b6347df82dca8a7e4&path:packages/bundle/web-app@deepseek-ai/dsh-web-appThe dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:smallhug/dsh-tauri#7607e32b120d2365a4df4aca1ff804d2d6899fb5&path:packages/bundle/web-app@deepseek-ai/dsh-web-appThe dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yth1120/dsh-web-workbench#38daee27fcbef2888f3cba4c5f05c03010577c0d&path:packages/bundle/web-app@deepseek-ai/dsh-web-restartOne-click restart button for the DSH Web UI: sidebar-footer button POSTs /restart-dsh; a detached Linux script kills the source-checkout dsh web instance and relaunches it from /home/prime/deepseek-harness. Linux port of github.com/1123762794/dsh-web-restart with an Origin guard.
@deepseek-ai/dsh-work-board-appInstallable dsh profile bundle: mounts the work board host service, model tools, and web kanban UI over a web profile
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AFANman/dsh-work-board#46d544f190c57c4e6d6253fade03a5eecd87b0be&path:packages/work-board-app@deepseek-ai/dsh-workspaceWorkspace entity registry (ctx.workspaceRegistry): durable workspace records with validated session attachment over the domain data form for the DeepSeek Harness
@deepseek-ai/dsh-workspace-reviewWorkspace git review service (ctx.workspaceReview): changed-file listing and bounded unified diffs for the DeepSeek Harness
@deepseek-ai/dsh-workspace-wslAdd and manage Windows and WSL workspaces from the sidebar; WSL workspaces run Linux commands by default (wsl_bash tool).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:CaptainJi/dsh-workspace-wsl@deepseek-harness-tui/dsh-tuiClaude Code style interactive TUI front door for DeepSeek Harness agents, built on the ported Ink core.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:raktim-mondol/dsh-tui-en@deepseek-kanban/pluginDeepSeek Harness 任务看板插件(主机状态机 + git 调度 + 浏览器看板 UI)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhouStar7/dsh-kanban@deepwork/desktopClean-room DeepWork desktop shell (commit 976d91c): Electron shell + sidecar DSH engine + Chromium stock DSH web UI, sharing $DSH_HOME
@dennisrongo/dsh-weatherWeather bar for DeepSeek Harness (dsh) — current conditions at the bottom of the web UI via Open-Meteo, rendered into shell.overlay
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dennisrongo/dsh-plugins#377c8ef55a1bc9a64a99d08a7b73c398ae83b113&path:plugins/dsh-weather@dfy-plugins/dsh-image-generation为 DeepSeek Harness 提供独立的图像生成与编辑 Skill、工具和设置界面。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiaoxiao44443/dfy-dsh-plugins#8a6956ca217ba88ff8858148ca801f63d0285806&path:plugins/image-generation@doiiarx/dsh-settings-search-pluginSearch field for the DSH Web Settings panel: independent candidate list over the content column, click to navigate to the owning section and focus the setting
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DoiiarX/dsh-settings-search-plugin@dong-victor/dsh-better-sidebar-jupyterJupyter notebook support for the dsh-better-sidebar editor: .ipynb opens inline as a runnable notebook viewer with IDEA/PyCharm-style run mode (Ctrl+Enter / Shift+Enter / run-all shortcuts, IDEA toolbar, gutter run icons, In/Out labels, execution duration, collapsible tracebacks), a lazy-start Python kernel (jupyter_client + ipykernel via python/bridge.py), background execution and save-back. Registers the ipynb file viewer through the ctx.betterSidebar service.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dong-victor/dsh-better-sidebar-jupyter@dong-victor/dsh-mcphubMCPHub 桥接插件(DSH Web GUI):把本地 MCPHub(http://localhost:3000,@samanhappy/mcphub)聚合暴露的全部 MCP server 工具桥接进 DSH。宿主侧以 MCP Streamable HTTP 客户端连接 MCPHub 聚合端点 /mcp(或 /mcp/<group> 分组端点),把发现到的工具以 mcp__mcphub__<server>-<tool> 形式注册为 agent 原生工具;提供 mcphub_status / mcphub_resync 两个 agent 工具,/api/dsh-mcphub/status 环回路由与侧边栏「MCPHub」面板(连接状态、server/工具清单、一键打开 MCPHub Dashboard)。断线自动指数退避重连、工具集热同步(tools/list_changed),无需改 dsh 源码。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dong-victor/dsh-mcphub@dong-victor/dsh-opencodego-usageopencode Go 套餐余额查看插件(DSH Web GUI):侧边栏直接显示 rolling(5小时)/weekly(周)/monthly(余额) 三档用量进度条、百分比与重置时间,60s 自动刷新,无需点击;点击打开详情面板(倒计时、状态徽章、端点/密钥信息);agent 工具 opencode_go_balance 可直接回答套餐用量。密钥默认取 llm-pi-ai 的 opencode-go 路由 apiKeyEnv(OPENCODE_GO_API_KEY,官方 opencode 模型专用密钥)并经 credentials 服务解析,端点默认 https://opencode.ai,无需二次配置。零构建依赖、纯 JS 即装即用:`dsh plugin --profile web add @dong-victor/dsh-opencodego-usage`。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dong-victor/dsh-opencodego-usage@dougen/dsh-deepseek-usageDeepSeek 余额侧边栏插件:余额(官方 API)、当前档单价与峰谷时段指示灯,支持中/英文界面。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dougen/dsh-deepseek-usage@dsh-agent-toolchain/dsh-api-visualizerAPI capture visualizer for the dsh web GUI: a sidebar entry plus a live panel showing API-call records the agent captures from the client process (method / url / status / duration / headers / bodies / notes). Records are appended to a JSONL store via the api_capture_append agent tool or the /api/dsh-api-visualizer/ingest route; the panel polls and renders them. No dsh source changes.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lemonmmice/dsh-agent-toolchain#8dc0b45342b159d82fcc5cda36110d2bdae97fe1&path:plugins/dsh-api-visualizer機能のキーワードやカテゴリで絞り込み、更新日や GitHub Star で並べ替えます。
紹介、AI 分析、元の README を読み、プラグインの機能を確認します。
互換性、依存関係、手順を確認し、利用可能なインストールコマンドをコピーします。
DeepSeek Harness のコミュニティプラグイン集です。紹介、ソースへのリンク、インストール手順をまとめ、拡張機能の検索と比較を支援します。
いいえ。詳細ページは記録された互換性と依存関係を表示します。不明は互換性ありを意味しません。導入前にプロジェクトの文書を確認してください。
詳細ページのインストール欄を開き、コマンドがあれば Harness 環境で実行します。ない場合はプロジェクトの README に従ってください。