Discover The Best DSH plugins

DeepSeek Harness plugins — Page 310

21799results

Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.

dsh-composer-ux

DSH Web 输入体验增强插件:可配置发送/换行键位 + 自定义输入框右键菜单 + 面板尺寸记忆 + OpenCode 会话请求头(含设置页)

Memory and knowledge · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fangwen9527/dsh-composer-ux
dsh-composition-doctor

Read-only DSH and Cordis composition diagnostics, snapshots, diffs, and isolated preflight.

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lemonxiny55/dsh-composition-doctor
dsh-computer-use

DSH 视觉整机控制插件(P2):经 macOS Accessibility API(AXUIElement)把本机 GUI app 变成 AX 快照优先的元素级工具集(观察 4 + 窗口管理 1 + 动作 6 + 截图兜底 1,共 12 个 computer_* 工具);v0.2.0 窗口对象化:windowId 不透明句柄(WindowRegistry + tombstone + CG 截图绑定)+ 输入后端分层(mode/delivery,Tier 1 pid 定向预留);Swift 辅助进程零 npm 依赖;敏感动作可选人工审批(默认关)。

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-computer-use
dsh-computer-use

Computer-use mode for DeepSeek Harness: screen capture plus mouse, keyboard and window control, for operating software that has no agent-facing integration and for reading information that only exists on screen.

Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EvangeliMo/dsh-computer-use
dsh-computer-use

Model-agnostic Computer Use capability for DeepSeek Harness: isolated browser first, provider-neutral observation, text planner + third-party vision perception.

Agent collaboration · Vision tools · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiaoheizi1212/dsh-computer-use
dsh-concise

Concise 输出风格开关:结果先行、少废话(对齐 Claude Code 内置 Concise output style)。composer 模型选择按钮右侧一键开关,按会话独立生效(新会话默认关),支持 /concise 命令、style.md 自定义风格与本地 API。

Developer tools · Productivity
dsh-concurrency-meter

Read-only model request concurrency monitoring for DeepSeek Harness

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Wanbinyu/dsh-concurrency-meter
dsh-conflict-deal

冲突化解

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-conflict-deal
dsh-conflict-guardian

Detects DSH plugin conflicts (duplicate mounts, failed/pending plugins, duplicate config row ids) at startup, auto-stops or restores the affected plugins, and shows a conflict report popup in the web UI. DSH 启动时检测插件冲突,自动停用/恢复冲突插件,并在 Web 界面弹出冲突报告。

Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:baisama-cloud/dsh-conflict-guardian
dsh-conn-dot

Green connection dot beside the DSH sidebar brand mark: merges the runtime WebSocket recovery state with a 30s same-origin liveness probe, so a broken/hung dsh web server turns the dot red.

Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:afterrealism/dsh-conn-dot
dsh-connect

All-in-one DeepSeek Harness (DSH) chat bridge: one plugin, one config block — Feishu/Lark, Telegram, DingTalk, and Web mirror adapters plus the web-settings pane, all behind a channels[] selector

Agent collaboration · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:IvanWu2015/dsh-connect#7e45fa5ed304b0ffa3f20f1fc01a33d6d0663b54&path:packages/connect
dsh-connect-comate

Connect the locally signed-in WPS Comate account to DeepSeek Harness as a model provider, via a secure loopback shim (reverse-proxy style). 通过安全回环 shim(反向代理),把本机已登录的 WPS Comate 账号接入 DeepSeek Harness 作为模型来源。

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bakasbk/dsh-connect-comate
dsh-console

DSH 控制台插件:主视图「控制台」标签页,真 PTY 交互终端(iTerm 风格多标签),vim/top/ctrl+c 全支持。

Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chinazkk/dsh-console
dsh-content-rewriter

一键将内容改写为多种风格:小红书、知乎、商务邮件、精简版、扩写版、Twitter/X

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jetheaven/dsh-content-rewriter
dsh-content-studio

DSH bundle plugin: 内容创作与多平台分发 —— 桌面截屏/录屏、Markdown→小红书图文卡片(5 配色 × 4 版式、照片插图、背景图)、dev.to 官方 API 发布、发布前人工审阅(草稿落盘),并挂载 Playwright 与小红书 MCP。

Vision tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ZRui-C/dsh-content-studio
dsh-context

Conversation Context tab and /context: composition, history, events

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kedoupi/xiaotaozi-dsh#27564cbe6c5f08b7d77e783b6e1540bab0a80f94&path:plugins/context
dsh-context-compaction-optimizer

DSH plugin: mark messages as invalid so an operator annotation digest steers what a compaction checkpoint absorbs. Cache-preserving: appends after the cached prefix, never rewrites history.

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bigPaulSixSixSix/dsh-context-compaction-optimizer
dsh-context-compression-improved

Improved fork of dsh-context-compression-selector with an orthogonal code-skeleton compression gate

Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:drscrewdriver/dsh-context-compression-improved
dsh-context-compressor

Context compression for small-context models on the DeepSeek Harness Web GUI: one click condenses the whole conversation into a few sentences, opens a fresh session in the same workspace, and re-injects the summary as the first message so a small model keeps working with a clean, compact context.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qwert702/dsh-context-compressor
dsh-context-governor

Session context governor for DeepSeek Harness: prompt size and per-step cost in dollars (cache-read/cache-write aware), cache-hit, context bands, a per-session compaction threshold derived from the model window, DeepSeek balance and peak/off-peak tariff, and a one-click handoff. It never calls a model and spends no tokens.

Financial data · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mpinaev/dsh-context-governor
dsh-context-lens

Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gordonlu/dsh-context-lens
dsh-context-lens

Single-session context anatomy for the DeepSeek Harness Web GUI: attribution, headroom planning, and a context x trajectory timeline — not another usage ledger.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yukitakasama/dsh-context-lens
dsh-context-maid

自动上下文策展:tool 输出瘦身 + 无效日志清理 + 工作流/记忆钉扎保护 + 先归档后压缩

Memory and knowledge · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Icstick/dsh-context-maid
dsh-context-management

Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.

Agent collaboration · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PlxloYzb/dsh-context-management

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.