@deepseek-ai/dsh-client-ui-agent-presetAgent-preset surfaces: the default for later sessions, this session's seat, and the composition editor
Discover The Best DSH plugins
5437results
Find task management, document processing and everyday workflow automation plugins.
@deepseek-ai/dsh-client-ui-agent-presetAgent-preset surfaces: the default for later sessions, this session's seat, and the composition editor
@deepseek-ai/dsh-client-ui-directory-picker-browseIn-app directory browsing surface: the workspace directory-flow owner rendering the host's listing and creation primitives
@deepseek-ai/dsh-client-ui-directory-picker-nativeNative directory-picker surface: the renderless workspace directory-flow occupant driving the host's OS chooser
@deepseek-ai/dsh-client-ui-goalSession goal surface: GoalBar docked above the composer, read from the goal session projection
@deepseek-ai/dsh-client-ui-jobsSession-header background-job list: live registry state mirrored from session/jobs frames
@deepseek-ai/dsh-client-ui-model-selectionModel selection over the shared model catalog, Session projection, and session.selectModel
@deepseek-ai/dsh-client-ui-open-in-appWeb Session-header "Open In..." split button opening the session workspace directory in a locally installed application
@deepseek-ai/dsh-client-ui-permission-presetsPermission surfaces: a new-session default in General settings and a current-session /permission popup over the permissions projection
@deepseek-ai/dsh-client-ui-referenceUnified Web @file and @session reference source
@deepseek-ai/dsh-client-ui-scheduleRead-only active Schedule catalog in the Web Session header
@deepseek-ai/dsh-client-ui-sessionSession Controller adapter for React and session-scoped slots
@deepseek-ai/dsh-headlessThe dsh one-shot bundle: a direct core Agent/Session runner over dsh-base with no Host, HTTP, or browser layer
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:See-Sol-Lab/DeepSeekGUI#f8fae741698467d001e73dab9f46355ead23a716&path:packages/bundle/headlessdsh-ego-browserego-browser (ego-lite) integration plugin for DSH: structured browser-automation tools (30+ ego_*) that drive the vendored ego runtime through ctx.subprocess, plus a realtime watch panel (live SSE screencast + direct mouse interaction + download capture + human-verification notice). Web shell: floating watch panel without dsh-better-sidebar, sidebar tab with it. Headless/TUI hosts: tools-only. [0.1.2-rc.1: verified compatible with DSH v0.1.2-rc.1 and v0.1.3-alpha.1]
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Fisfzy/dsh-ego-browsergal-viewDSH Web GUI 会话页的 GAL 视窗:Galgame 风格对话视图 + 场景元素可视化编辑器
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Ayase34/gal-viewdsh-lowtidelowtide: human-adjudicated off-peak batch task pipeline for dsh (peak/valley pricing aware)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:KelaoHu/dsh-lowtide#bc0eec546db7efbe691b37fa4dd43e8f24402c0b&path:packages/dsh-lowtidelowtide-corePlatform-agnostic core logic for lowtide (windows/pricing/model/digest/scheduler/ledger)
dsh-auto-reviewSecond-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PerryLink/dsh-auto-review@zseven-w/dsh-iosDeepSeek Harness plugin for the iOS Simulator — build, run, and interact with a live simulator stream inside a conversation. Tested with DSH 0.1.0-rc.6.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ZSeven-W/dsh-iosdsh-mnemonThree-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Grivn/dsh-mnemondsh-chat-importImport Claude Code / Codex / ChatGPT / Cursor / Gemini / Reasonix / Pi Coding Agent / opencode / ZCode / Grok Build / OpenClaw / Hermes / Kimi CLI / Qoder CLI / WorkBuddy conversation histories as resumable DeepSeek Harness sessions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Nwflower/dsh-chat-import@ychris12138/dsh-usage-statsToken usage, provider accounts, session cost estimates, budgets, and exports for the dsh web GUI
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Ychris12138/dsh-usage-statsdsh-memory-evolve为 DeepSeek Harness 带来分层记忆(全局 / 用户 / 项目 / GIT 分支 / 每日)与自我进化(经验沉淀 + 技能自动创建)和技能管理、待办管理、CLI 调度(kimi/codex/grok/hermes 等外部 AI 统一调度)、临时信息便签,带 WebUI 管理界面。Hermes-style long-term memory, self-evolution, skills, todos and external CLI agent dispatch for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:csyangwen/dsh-memory-evolvedsh-antibrowDeepSeek Harness plugin: an agent browser with a persistent identity - engine-level fingerprint spoofing, per-profile cookies and passkeys, residential proxy egress.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:antibrow/dsh-antibrowbaro-dshbaro as a DeepSeek Harness subagent provider: delegate a multi-story goal, get parallel execution, independent review and a verified outcome back — with a live run panel in the sidebar
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jigjoy-ai/baro#f9a610774532fdde578b656dd838766e1173c4fc&path:packages/baro-dshUse 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.