DSH plugin v2: a standalone image-generation workspace (sidebar entry + its own main view) for the OpenRouter Image API — chat-style prompt column, picture area with history, draggable parameters.
DSH web plugin (dsh-better-sidebar consumer): render CSV/TSV/PSV files and xlsx/xlsm workbooks as a structured, sortable, filterable table in the right sidebar — with sheet tabs and a circuit breaker (rows/cols/cells plus the two zip-container gates) so no input can freeze the browser.
Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:drscrewdriver/dsh-opensheet-sidebar
OpenViking in the DSH web GUI: a Studio panel, a per-session memory-commit status pill with its commit timeline, and a right-sidebar tab showing what the current session retrieves.
Memory and knowledge · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:A2chitect/dsh-openviking-enhance
Long-session resource governor for DeepSeek Harness: measures the context each request actually carries, tracks per-session growth, warns before a session becomes expensive to run, and (optionally) trims the rendered history in the web UI.
Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:aoripus/dsh-optimize
Command palette (⌘K) for the DeepSeek Harness Web GUI: keyboard-first quick entries over sessions, settings, and actions, with a customizable hotkey and a register extension point.
Paperclip upload button for the DeepSeek Harness Web UI: pick a desktop file, upload it into the session workspace uploads/ directory, and get a 📄 filename in the composer.
Parked thoughts for later: jot follow-up topics while the AI is working, without interrupting the conversation, and push them into the composer draft when the time is right. DSH web plugin. 稍后说:等待 AI 时记下想聊的话题,不打断当前对话,稍后一键带入输入框。
Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kevin-zx/dsh-park-notes
Cherry Studio-style paste: pasted text/code blocks into the DSH Web composer render as a bordered, collapsible, language-tagged card instead of a long flat string; the original text is restored as a fenced block on send.
Interface extensions · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:cjm-m/dsh-paste-code-block
Peak-hour indicator for the DSH web GUI: a native header chip showing whether the current Beijing time is inside DeepSeek's API peak window (daily 09:00–12:00 / 14:00–18:00), with a live clock, countdown, and ×2/off-peak pricing hints. · DSH Web GUI 高峰指示灯:原生会话头部胶囊,实时显示当前北京时间是否处于 DeepSeek API 高峰时段。
Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiaoyi-xx/dsh-peak-status
DeepSeek Harness 峰谷任务排队插件:开关拦截输入入队,DeepSeek API 谷段(工作日 09:00-12:00 / 14:00-18:00 之外)自动按序执行,支持编辑/删除/拖拽排序/手动送出/失败暂停恢复/严格完成标志校验,队列与配置本地持久化,UI 为 better-sidebar 页签。Peak/valley-pricing task queue with switch, valley-window auto execution, edit/delete/drag/send/pause-resume, strict completion markers, local persistence and a better-sidebar tab.
Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EmptyCollin/dsh-peak-valley-queue
Find the right plugin, then get started
Search by task
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
Check and install
Review compatibility, dependency ranges and instructions, then copy the available install command.
Questions about DSH Hub
What is DSH Hub?
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.
Does inclusion mean a plugin is tested and compatible?
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
How do I install a plugin?
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.