Discover The Best DSH plugins

Productivity · DeepSeek Harness plugins — Page 167

5702results

Find task management, document processing and everyday workflow automation plugins.

dsh-composer-keys

Keyboard shortcuts for the DSH chat composer: Arrow Up/Down to cycle through historical user messages, Ctrl+C to clear input.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kexin8/dsh-composer-keys
dsh-composer-recall

Arrow-key input history for DSH 0.1.2-alpha.1: press ↑ in an empty composer (or at the start of the draft) to recall this session's prompts, ↓ to go forward, Esc to restore what you were typing.

Memory and knowledge · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:WongYuYe/dsh-composer-recall
dsh-computer

Computer use capability Service Definition for DeepSeek Harness: the ctx.computer seam providers register into

Productivity
dsh-computer-playwright

Playwright provider for the dsh computer use seam: drives a local Chrome over playwright-core

Productivity
dsh-computer-use

DeepSeek Harness plugin: Linux X11 computer-use tools (screenshot, mouse, keyboard) via a Python XTest helper

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

Windows 桌面 Computer Use 工具:驱动本机 Codex 原生助手(codex-computer-use.exe),经 stdio JSON-RPC 提供 UI 自动化(UI Automation 树 + SendInput 输入注入)。

Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gxpppp/dsh-computer-use
dsh-computer-use

Independent cross-platform desktop computer-use plugins for DeepSeek Harness

Vision tools · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:leolee9086/dsh-computer-use
dsh-computer-use

Windows desktop control for DeepSeek Harness with per-Agent tool loading, observed UIA target recovery, incremental observations with retained full snapshots, native screenshots, batching and human brakes.

Agent collaboration · Interface extensions · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ltmroberthk915/dsh-computer-use
dsh-computer-use-native

Windows computer use for DeepSeek Harness built for a vision model: screenshot the real desktop, read the interface from pixels, and click what you see. Drives Win32 through koffi FFI with no native addon and no accessibility tree, and posts input to a window's own queue so the desktop focus is left alone.

Vision tools · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dao-awa/dsh-computer-use-native
dsh-computer-use-plugin

Vision-only desktop automation plugin for DeepSeek Harness (fusion refactor)

Skills · Agent collaboration · Vision tools · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:beijingwahw/dsh-computer-use-plugin
dsh-computer-use-vision

Windows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.

Memory and knowledge · Skills · Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xuanyuanluoxue/computer-use-vision
dsh-computer-use-win

Windows computer-use bundle for DeepSeek Harness: screenshots, window enumeration, and mouse/keyboard control with approval gates.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:secretxuan/dsh-computer-use-win
dsh-computer-use-win

Windows computer use for DeepSeek Harness: an MCP stdio server + PowerShell UIA backend, bridged into DSH via @deepseek-ai/dsh-mcp-client. Read/act on real Windows desktop apps (UI Automation tree, screenshots, typed input, OCR, window management).

Vision tools · Interface extensions · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Yu-tao-Li/dsh-computer-use-win
dsh-computer-use-windows

Windows computer use for DeepSeek Harness — UI Automation accessibility tree with optional VLM grounding. Approval-gated, allowlisted.

Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dimitririchko-ops/dsh-computer-use-windows
dsh-computer-use-windows

Safety-gated Windows Computer Use tools for DeepSeek Harness with ModLens visual grounding.

Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:nanbbb/dsh-computer-use-windows
dsh-concurrency-guard

DSH 并发请求监控与门闩:挂钩 llm/stream 瀑布,统计全部在途模型请求并按来源分类(主会话/子代理/插件/压缩/标题)与会话活跃聚合,达到上限 FIFO 排队,防止并发超限被供应商锁号;提供 WebUI 实时面板(含历史清理)、HTTP JSON 端点、状态文件与 concurrency_status 工具。

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fu827707013/dsh-concurrency-guard
dsh-conda-workspace-env

Choose and persist a Conda environment per DeepSeek Harness workspace

Skills · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Mshir0/dsh-conda-workspace-env
dsh-console-hub

DSH 插件:网络设备 console 映射端口(Telnet / Raw TCP)会话管理 —— 配置增删改查(敏感信息存 credentials)、连接/关闭/发送/读取、分页自动处理,模型侧 console_* 工具,高危指令 approval 拦截。

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:RBkreb/dsh-console-hub
dsh-context-badge

A local-only context badge with automatic first-five user-message capture, purpose summary, per-session notes and todos for DeepSeek Harness, plus an optional macOS foreground-window companion.

Notifications · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LeslieWylie/dsh-context-badge
dsh-context-compass

Session health for DeepSeek Harness: real token-meter data, configurable continue-vs-new decision model. Reactive header badge (compaction-aware), /compass command, context_compass tool.

Notifications · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NinjaSln-labs/dsh-context-compass
dsh-context-console

DSH context console with trajectory, prompt/skill/MCP/tool inventory, message forging, and conservative session-log recovery.

Skills · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:anweat/dsh-context-console
dsh-context-dashboard

Sidebar context/billing dashboard for DeepSeek Harness: live context ring, per-session usage & spend, account balance and token-plan quota readouts across configured LLM channels.

Financial data · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lcohvne-tomorin/dsh-context-dashboard
dsh-context-dashboard

DSH 会话上下文统计面板:统计每个会话的消息数、轮次、工具调用、字符数与预估 token,生成全量/按项目上下文报告,帮你看清上下文消耗大户。Context usage dashboard for DeepSeek Harness — per-session message/token statistics and context reports (zstd + plaintext logs).

Financial data · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-context-dashboard
dsh-context-enhancement

Persistent task state and context-aware compaction for DeepSeek Harness coding sessions.

Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chuxindd/dsh-context-enhancement

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.