Discover The Best DSH plugins

Agent collaboration · DeepSeek Harness plugins — Page 193

7395results

Explore agent orchestration, multi-agent collaboration and task execution plugins.

@dsh-external/dsh-soundscape

DSH 工具/思考音效:agent 思考氛围音 + 全工具分类音效 + 音效文件夹直替(wav/mp3 自动转换)

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:berserk0501/dsh-soundscape
@dsh-external/dsh-subagent-model-picker

让主会话模型从已配置模型里自主选择子代理模型

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:cczzyy-cn/subagent-model-picker
@dsh-external/dsh-taffy-theme

Taffy Live Atelier — candy acrylic DSH Web UI theme with light/dark stage art, character overlays, and a Taffy agent preset.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lengzhanbao/dsh-taffy-theme
@dsh-external/dsh-task-router

Task delegation router for DSH: main model plans/verifies, sub-models search/browse/code/verify.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Tiko9527/task-router
@dsh-external/dsh-tool-failure-journal

Failure journal: every tool call that exits abnormally is written to a durable JSONL journal on disk, clustered by error signature, and readable back by the agent through a `failure_journal` tool.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:catsenior507/dsh-tool-failure-journal
@dsh-external/dsh-ui-manager

DSH-UI-Manager: manage installed UI/skin plugins from the web settings — enable one at a time, restore the default UI, rename display names, open plugin homepages, and uninstall skins.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:FURO2170/dsh-ui-manager
@dsh-external/dsh-vision-bridge

DeepSeek Harness vision bridge: session screenshots route by model capability. Image-capable models receive attachments inline; text-only models see the standard placeholder, and the bridge reads the image through a vision-language model — on demand via the vision_bridge_read tool or automatically via agent/pre-step context injection. 会话截图按模型能力自动分流:多模态模型原样直读;纯文本模型经 VLM 代读(tool/auto 双模式)。

Agent collaboration · Vision tools · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:shenhuanageshei/dsh-vision-bridge
@dsh-external/dsh-vision-toolkit

DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.

Skills · Agent collaboration · Vision tools · Interface extensions · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hezi2020/dsh-plugin-wiki#0f911a1b7aef331b19607a60c884be50e910c0ab&path:plugins/Anionex-dsh-vision-toolkit
@dsh-external/dsh-vision-toolkit

DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.

Skills · Agent collaboration · Vision tools · Interface extensions · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hezi2020/dsh-plugin-wiki#0f911a1b7aef331b19607a60c884be50e910c0ab&path:plugins/dsh-vision-toolkit
@dsh-external/dsh-volcark-quota

火山方舟 Coding Plan / Agent Plan 额度实时查看 DSH 插件:AK/SK 直连 open.volcengineapi.com(GetCodingPlanUsage / GetAgentPlanAFPUsage),悬浮小球 + 可拖拽悬浮窗展示各窗口已用/剩余/重置倒计时(两位小数),AK/SK 在「设置 → 插件」页配置。

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ZnonEn/dsh-volcark-quota
@dsh-external/dsh-voredteam

dsh-voredteam —— 单模式(网络安全模式)DSH 插件合集:黑板书 Fact/Intent/Hint 引擎 + 总控派发专业子 agent + 作战面板/设置 两个面板 + 唯一门禁(禁 DDoS/禁爆破/模糊测试低频)。

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xydijkkk/dsh-voredteam
@dsh-external/dsh-web-service

Expose DSH over HTTP: 47 REST + SSE routes for workspaces, sessions (streaming, history, stats, todos, cancel), models, settings, skills and files, plus an OpenAI-compatible /chat/completions. · 把 DSH 的能力开放成 REST + SSE 接口与 OpenAI 兼容端点,供三方控制台、客户端与 Agent 集成。

Skills · Agent collaboration · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:toddpan/dsh-webapi
@dsh-external/dsh-webrelay

DSH Web 中继插件:右侧内置浏览器(relay 反向代理同源嵌入外部 AI 站点)+ 输入框闪电按钮(提示词优化 / 与外部 AI 协作优化:压缩上下文→初优化→外发→收回回复→终优化→写入输入框)。

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Baisbt/dsh-plugin-webrelay
@dsh-external/project-nav

DSH plugin: architecture-first project governance. v0.10.0 makes the model a TREE + GRAPH — the containment tree (who belongs to whom) now sits beside a dependency graph (who imports whom), and the graph is DERIVED from a static import scan: never registered, never hand-written, never stale. Seven gates (anchor / scope / mainline / impact / repeat-patch / decision / completion) are pure queries inside the single write entry point nav_commit, so there is no begin/done lifecycle and no orphan state: closure is decided by EVIDENCE (did the scope files change?), never by session identity — kill a session and its intent still closes (A1). Governance surface is minimal by construction: anything that would rot when code changes must be a PROJECTION, not a document — hand-written surface is two contracts (ARCHITECTURE.md / AGENTS.md), and .internal/arch/*.md dropped its sha1-fingerprint/freshness machinery to become an on-demand projection. ONE append-only event log (.internal/events.jsonl) remains the single source of truth; the runtime model (incl. the dependency graph) is disposable — delete runtime/ and governance loses nothing (I3). Tool face 6: nav_graph (read, incl. mode=impact) / nav_commit (intent) / nav_decide (ADR) / nav_node (nodes) / nav_render (projections) / nav_set (mainline vector).

Memory and knowledge · Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Fishsb/dsh-project-nav
@dsh-external/skill-mcp-stats

统计每轮对话中 agent 使用的 skill 与 MCP 工具,支持对话内查询与 Web 面板查看

Skills · Agent collaboration · Integrations
@dsh-foundry/daily-agent

Agent-scoped daily behavior over the official Standard preset

Agent collaboration · Interface extensions
@dsh-gsd/bundle

A DeepSeek Harness plugin bundle that reimplements opengsd-core (Git Ship Done) as a host-plane plugin set, replacing the default agent-loop behavior with the GSD phase loop (Discuss -> UI design -> Plan -> Execute -> Verify -> Ship). Includes checkpoint-resume, a window ledger, a conversational UAT loop, capability gates, and a real background-job runtime.

Agent collaboration · Interface extensions · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jaaty/dsh-gsd-bundle
@dsh-hardware-buddy/dsh-hardware-buddy

DeepSeek Harness host plugin that mirrors agent state to a CodeBuddy StickS3 pet over USB CDC and routes physical A/B approval back into the approval waterfall.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:baidang201/dsh-hardware-buddy
@dsh-lite/plugin-health

A lightweight, local-first distribution and verified plugin kit for DeepSeek Harness.

Agent collaboration

Find the right plugin, then get started

  1. Search by task

    Use a feature keyword or category, then sort by recent updates or GitHub stars.

  2. Explore capabilities

    Read the description, AI analysis and original README to understand what a plugin does.

  3. 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.