Discover The Best DSH plugins
7205results
Explore agent orchestration, multi-agent collaboration and task execution plugins.
dsh-whale-girl-live2d鲸鱼娘桌宠：把 Live2D 鲸鱼娘挂进 DSH Web 界面的桌宠插件——模型常驻桌面，跟着 agent 的真实状态换表情与动作，点一下就能直接跟 agent 说话，右键菜单可换表情 / 换装 / 摆场景 / 演小动作。（Whale Girl Pet: a Live2D companion for the DeepSeek Harness Web UI. Model assets are non-commercial, CC BY-NC-SA 4.0.）
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Andersen216/dsh-whale-girl-live2ddsh-win-notifyDSH plugin: Windows toast notification with sound when an agent task completes.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MuziIsabel/dsh-win-notifydsh-workspace-hygieneA DeepSeek Harness plugin that actively assesses artifact value and keeps agent workspaces organized, auditable, and recoverable.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:taoshi1999/dsh-workspace-hygieneforeman-dsh-configForeman worker configuration card: provider/model/effort for the delegate_worker lane, edited in the DSH settings UI, applied to the local worker preset by the host half.
gongwen-skill中文公文全流程处理工具 - GB/T 9704 格式检查/修复/内容优化/模板生成/版式注入
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:linhut/gongwen-skillJnpzDSH 技能配置插件：设置页新增“技能配置”分类 —— MCP 服务器管理（JSON 自动转换、动态启停）+ 技能管理（zip/.skill 上传自动识别、创建与删除）
knotline-dshA single project operating map for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MrMaii/knotlinelunheng-article-pipeline论衡（lunheng-article-pipeline）— 多 Agent 深度长文流水线技能包（DeepSeek Harness 原生插件）：定题→并行检索（文献/数据/案例）→分析→大纲人在环确认→写作→批判→审计→审稿→修订→配图→终检交付，9 个独立角色 T1-T9 互不可替代（文献/数据/案例/分析/写作/批判/审计/终检/审稿），主控 = T0 调度 + T8 终检亲执行（T8 独立角色，执行者主控担任，不 spawn），T9 审稿可选默认选中学术必选，三角验证 + M 机械化硬门 + F 失败模式防御 + G14 中文 AI 痕迹闸 + 期刊匹配助手，用 dsh subagent 子代理编排。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zuoyunlai/lunheng-article-pipeline-dshmeow-memoryCross-session project memory for DeepSeek Harness: seven-layer SQLite memory, first-turn snapshot injection, per-message keyword hits, memory_remember/search/project tools, automatic reflection with reflection-fold UI, and nightly dream consolidation.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Phant0Meow/dsh-memory-meowmindspace-dsh-session-memoryEditable, session-isolated personalization memory for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Spirtxiaoqi7/mindspace-dsh-session-memoryoctie-cliA graph-based task management system with CLI and web UI for atomic, verifiable tasks
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:StarChen-Cycler/octie-dsh-pluginorbit-runtime-ui-testsLocal-first, durable workflow runtime for Agent Apps—compile static Workflow DSL to LangGraph and orchestrate trusted multi-agent execution through Codex, WorkBuddy, DeepSeek Harness, or any MCP client.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:TNJ2026/orbit-runtimepromptaflow-ui-testsLocal-first, durable workflow runtime for Agent Apps—compile static Workflow DSL to LangGraph and orchestrate trusted multi-agent execution through Codex, WorkBuddy, DeepSeek Harness, or any MCP client.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:TNJ2026/promptaflowqiushi-dsh-evidence-auditObserve-only hash-chained evidence receipts for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:030611/qiushi-dsh-evidence-auditqq-mode-consoleNimuQDock-dsh mode console for DeepSeek Harness settings UI (chat / agent)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NimuStudio/NimuQDock-dsh#6a516cb034085c559a88b93abe4e4cd88e0f5163&path:plugins/qq-mode-consoleroblox-devforum-mcpMCP server that searches the Roblox DevForum and official creator docs so AI coding agents can debug Roblox games against real community and engine knowledge.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EL4CTEO/roblox-devforum-mcpspatial-trajectoryAgentAstra — a spatial agent-trajectory view for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Rgndmln/dsh-agent-astratencentcloud-agentobs-sdk-dshTencent Cloud Service CLS observability plugin for DeepSeek Harness — direct upload to Tencent Cloud CLS
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:TencentCloud/tencentcloud-agentobs-sdk-dshthinking-sliderThinking-strength slider: replaces the composer model seat's reasoning-effort button list with a snap-to-step slider for the DSH web UI.
vscode-dshStart, open, and manage the DeepSeek Harness Web UI from VS Code.
yinchao-ai-musicGenerate complete AI songs and BGM with YinChao, including lyrics-to-song, reference-audio creation, and song extension.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yinhcao/yinchao-ai-music-skill@acnlabs/dsh-plugin-acnDeepSeek Harness plugin: join ACN so this agent can discover, message, and collaborate with other agents. Defaults to the China region.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:acnlabs/dsh-plugin-acn@across2005/harness-self-evolutionBenchmark-driven self-evolution plugin for DeepSeek Harness: iterate on a frozen benchmark, accept only when strictly better, roll back deterministically from verified snapshots.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Across2005/harness-self-evolution-plugin@addozhang/dsh-discordDiscord-first adapter for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:addozhang/dsh-discordUse a feature keyword or category, then sort by recent updates or GitHub stars.
Read the description, AI analysis and original README to understand what a plugin does.
Review compatibility, dependency ranges and instructions, then copy the available install command.
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.