Discover The Best DSH plugins

Agent collaboration · DeepSeek Harness plugins — Page 135

7257results

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

dsh-efficiency

效率导向的 DeepSeek Harness 增强:不打开浏览器也能秒回 agent 提问、随时看到进度。桌宠与 galgame 仅为可选交互模块。

Agent collaboration · Notifications · Interface extensions · Developer tools · Productivity
dsh-emotion-pet

Emotion Ball pet dock for the DeepSeek Harness Web composer

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:cpt-kenvie/EmotionPet
dsh-engine-switch

A pure runtime that routes DeepSeek Harness sessions to pluggable loop engines by agent-preset. Ships no engine; downstream plugins register engines via ctx.engineSwitch.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Yuki-takuya-kun/dsh-engine-switch
dsh-engram-recap

Forces periodic Engram memory recall and save reminders for DeepSeek Harness agents: injects a dynamic system-prompt context that reminds the model to load prior session memory at the start of a session, and to save new decisions/bugfixes/learnings every N turns - so knowledge survives across sessions without depending on the model remembering to do it unprompted.

Memory and knowledge · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:elmaxid/dsh-manage#994c0ee484a6bffad09ba130ffc6576b1e2e9e98&path:plugins/dsh-engram-recap
dsh-enhanced

Everyday upgrades for DeepSeek Harness in one plugin: vendored multi-engine free web search (with self-hosted SearXNG support), persistent skills and MCP server management, auto-compact tuning, instance controls, and Matrix/Cyberpunk themes

Skills · Agent collaboration · Interface extensions · Integrations · Productivity
dsh-enhanced-plugins

Enhanced DeepSeek Harness bundle: MCP management, pi-ai request types, plugin market, workspace file references, and product subagent toggles

Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sky-unicorn/dsh-enhanced-plugins
dsh-error-audit

DeepSeek Harness 实时 AI 自审插件:报错/警告连同时间、错误码、会话、用户原话、AI 动作与工作区写入日志目录,并主动通知 AI

Agent collaboration · Notifications · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:166767/dsh-error-audit
dsh-expert-orchestrator

专家编排模式 agent preset — 首席编排者:每条消息先归类分诊、PM 先行规划、合并花名册优先委派、任务板依赖调度、消息总线并行落盘、分级交付门禁、经验池按需沉淀。

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mario841859784/dsh-expert-orchestrator
dsh-experts

DeepSeek Harness bundle that turns expert teams (markdown persona rosters) into model-routable skills. Engine and roster are separate: teams are data directories users can author.

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:libinyam/dsh-experts
dsh-explore

Trajectory-level parallel exploration for DeepSeek Harness agents

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JIAChenyu525/dsh-explore#af6289545fd81690895f9c8e3700012113df4b8c&path:packages/plugin
dsh-explore-core

Pure trajectory-search algorithms (best-of-N, MCTS, verdict, diff, patch) for dsh-explore

Agent collaboration
dsh-external-agents

把外部 CLI Agent(Codex / Claude Code)注册成 DSH subagent provider:codex 升级为「单工具 + model 参数」+ 内部 route provider + 原生 ctx.jobs 异步(完成自动通知 / job_output(wait:true) 带上限等待);claude 为自写单工具。彻底移除 dsh-tool-subagent 依赖。v2.2 新增 argsProfiles 权限档位;v2.3 固化后台收数最佳实践文案(不新增 sleep 工具,见 DESIGN.md §8)。v2.4 新增 codex session 连续性:--json 强制捕获 session id(成功必有 id,否则按失败上报)+ session_id 参数续接历史会话(resume argv 从零构建,resumeArgs 为唯一旗标旋钮)。v2.5 claude 同样支持 session 连续性(--session-id 新会话/--resume 续接,工具层预生成 UUID)。

Agent collaboration · Notifications · Interface extensions · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DjangoAILab/dsh-plugins#18ae7e5df085d28e7a573d1e3ef0286bda1ea793&path:plugins/manual/dsh-external-agents
dsh-f1-skin

F1 Race Control themed skin for the DeepSeek Harness Web UI — Red Bull / Ferrari / McLaren / Mercedes team themes with broadcast photo backdrops, native settings panel, dark & light.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:frank-fan-818/dsh-f1-skin
dsh-failbook

失败账本 — DeepSeek Harness 工具失败记录、签名聚类与失败感知重试拦截(含 Web UI 面板)。Failure ledger for DeepSeek Harness: capture, cluster, persist and learn from failed tool calls, with a failure-aware retry guard and a Web UI panel.

Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:G1en-114/dsh-failbook
dsh-feishu-bridge

飞书机器人 ↔ DeepSeek Harness 桥接插件:通过飞书 WebSocket 长连接收发消息,把飞书会话映射到 Harness Agent,并把 Agent 的回复与执行过程回传到飞书。

Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ailoushu666/dsh-feishu-bridge
dsh-feishu-bridge

Feishu → local DeepSeek Harness Agent bridge (dsh-plugin)

Agent collaboration · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhbdream/dsh-feishu-bridge
dsh-feishu-plugin

Feishu/Lark bot bridge for DeepSeek Harness with approvals, progress updates, context, and file transfer.

Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yangzhaofeng496/dsh-feishu-plugin
dsh-file-edit

Workspace file browser with whole-document CodeMirror editing, agent-change review, references and rendered markdown

Agent collaboration · Interface extensions · Developer tools · Productivity
dsh-file-review

Review files produced by DeepSeek Harness turns in a line-numbered unified diff modal

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:left0ver/dsh-file-review
dsh-file-upload-local

本地手搓的 DSH 文件上传插件:流式上传(突破 base64 大小限制)、文件卡片、chat history 内预览/下载、图片内联预览

Agent collaboration · Vision tools · Interface extensions · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DjangoAILab/dsh-plugins#18ae7e5df085d28e7a573d1e3ef0286bda1ea793&path:plugins/manual/dsh-file-upload
dsh-find-plugin

Find DeepSeek Harness plugins inside the agent — live GitHub dsh-plugin topic search, ranked by stars.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:awesome-dsh-plugin/dsh-find-plugin
dsh-find-plugins

Find DSH plugins across five community catalogs plus live GitHub and npm search, ranked by relevance × trust × freshness × popularity — not stars alone.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Eray114514/dsh-find-plugins
dsh-flash-godmode

V4 Flash 神模式 v0.2(opencode-go 适配版)——w7 persona(分类/回顾/反跑题锚)+ 首轮工具锚定 + 按任务复杂度的深度/快速引导分派(agent/inbox/spliced 捕获,headless 首轮可用)。

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Cavan-Ou/dsh-flash-godmode
dsh-flat-teams

Leaderless flat agent teams for DeepSeek Harness: cross-window structured task dispatch, recorder service, and web dashboard

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:whateverboy2333/dsh-flat-teams

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.