Discover The Best DSH plugins
23436results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-auto-visualPlans original images for documents, sites and slides, generates them with a mock or OpenAI-compatible provider, and records each asset's declared usage
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Herbert-wang820/dsh-imagedsh-auto-workspaceCodex-style project-less chats for DSH: a new chat with no workspace gets its own local working directory
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Castor6/dsh-auto-workspacedsh-autocomposeTask-aware plugin selection and disposable DeepSeek Harness runtimes
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Han-1413141/dsh-autocomposedsh-autocount-cloudDeepSeek Harness tools for AutoCount Cloud connector commands.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:teckyuen/dsh-autocount-clouddsh-autoload-historyAutomatically load the full conversation history when a session opens — no more clicking "Load earlier".
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:magicOF2/dsh-autoload-historydsh-automationRPA-style scheduled web automation for DeepSeek Harness: record browser operations, turn them into a requirements doc, let the LLM generate Python + Playwright code, then schedule execution with run records and email notifications.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kumanana66/dsh-automationdsh-automation-centerA global Automation Center with fresh, auditable scheduled Agent runs for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:usersx/dsh-automation-centerdsh-autonomous-research自主研究 agent：给 AI agent 一个小而真实的 LLM 训练设置，让它过夜自主实验——改代码→固定 5 分钟训练→检查 val_bpb 是否改善→保留或丢弃→重复（约 12 实验/小时、一晚约 100 个）；单文件修改、program.md 超轻量 skill。受 karpathy/autoresearch（94k★ MIT）启发。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-skills-bundle#453fc2cf12e007b72e48f568e0ffe1fe4e13c616&path:plugins/dsh-autonomous-researchdsh-autoresearchDurable auto-research experiment loop for DeepSeek Harness, with create / run / monitor in the official Web GUI.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:aa2246740/dsh-autoresearchdsh-autoresumedsh web 重启后自动向固定开发会话注入「继续」：只服务目标会话，完成态不动作，避免重复注入。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:shengyvself/dsh-autoresumedsh-autoupdateBuilt-in auto-update plugin for dsh (DeepSeek Harness): manual update check from the Settings page, guarded update pipeline with health check, automatic rollback, circuit breaker and degrade ladders.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lc23313/dsh-autoupdatedsh-autoupdaterScheduled update checks for DSH itself and installed plugins, applied only in idle windows. Four schedule modes, dual-direction whitelist, web settings panel under the plugin manager.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:niubi6668889595/dsh-autoupdaterdsh-aux-degradeDSH plugin: stop auxiliary LLM calls from burning the output budget. Degrades reasoning effort for compaction summaries, session titles and prompt enhancement; raises their max_tokens floor; appends verbatim-retention sections to compaction instructions; and strips tools from compaction calls, so a high default thinking level cannot silently truncate a checkpoint.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiamubumu/dsh-aux-degradedsh-ava-bridgeDeepSeek Harness plugin that controls the Chrome browser through the installed Ava Chrome extension (CDP bridge daemon + model-facing browser tools).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sungatetop/dsh-browser-controldsh-average平均值
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-averagedsh-awakeDeepSeek Harness 防休眠插件（守夜人）：agent 任务执行期间阻止操作系统休眠，任务结束后恢复；方式子系统（systemd-inhibit / GNOME gsettings / caffeinate / pmset / PowerShell / powercfg）+ 浏览器 Wake Lock + 一键更新
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:htfc786/dsh-awakedsh-away-notifyDeepSeek Harness 插件：当任务完成且你不在 DSH 界面时，发送 Windows 系统通知（右下角 Toast）。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Kevin87654/dsh-away-notifydsh-awesome-model-settingDeepSeek Harness web plugin: a Model Capabilities settings page for declaring model input modalities, context window, output cap and image budgets without hand-editing settings.yaml.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Kazusa1085/dsh-awesome-model-settingdsh-axia-cachebilling虾算账：DSH 缓存账单插件 —— 上下文弹层实时算账（三档账单 + 真实事件计数 + Token 统计 + 实时汇率统一币种），价目目录自动填价
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Animal2404/dsh-axia-cachebillingdsh-azerbaijan阿塞拜疆国家
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-azerbaijandsh-azure-maid-skin蓝瓷女仆 · Azure Maid —— 一个可跟随系统切换深浅色的 DSH Web GUI 主题皮肤:深蓝发色主调 / 蕾丝冷白提亮 / 青宝石点缀,覆盖 90 个语义 token
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:erha2777/dsh-azure-maid-skindsh-b2us-scheduleDurable conversational and Web-managed scheduled Agent, shell, and system-notification tasks for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:changyinliangbaikai/dsh-b2us-scheduledsh-baby-clothes婴儿衣物尺码
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-baby-clothesdsh-baby-fever宝宝发烧
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-baby-feverUse 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.