Discover The Best DSH plugins

Productivity · DeepSeek Harness plugins — Page 183

5757results

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

dsh-import-vscode-ai-files

Load a workspace's own VSCode/Copilot AI configuration (.github/copilot-instructions.md, .github/instructions, .github/skills) into every DeepSeek Harness session. DSH 加载 VSCode AI 配置插件。

Skills · Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NEVSTOP-LAB/dsh-import-vscode-ai-files
dsh-importer

DSH plugin: sync chat.deepseek.com sessions into DSH as context — settings page, auto sync, per-session fetch, and a 'send' button that stages a file-reference prompt into the composer.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PrismScopes/dsh-importer
dsh-in-convo-mode-change

Switch the agent preset (conversation mode: Standard / Code / Minimal / Creator) of a session mid-conversation, straight from the session header.

Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jiangr100/dsh-in-convo-mode-change
dsh-indexbookmark

A DSH web client bundle: conversation question index for the DSH Web UI — list every question you asked in a session and jump straight to it. 对话问题索引插件:列出会话中你提过的所有问题,点击一键定位。

Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:cuhaitiang0405-collab/dsh-indexbookmark
dsh-inline-media-viewer

Persistent inline image, video, and audio previews for DeepSeek Harness Web conversations, with workspace-confined local reads and a configurable ComfyUI proxy.

Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Wisdoverse/dsh-inline-media-viewer-plugin
dsh-input-enhancer

DeepSeek Harness plugin that enhances the web chat composer: lock Enter-send to prevent accidental sends, and auto-enlarge the composer while locked for long-form editing. IME-safe and per-session.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qiqiangvae/dsh-input-enhancer
dsh-input-history

DSH 输入历史导航插件(纯 client 双面):对话输入框中按 ↑/↓ 方向键遍历当前会话发送过的消息(shell history 式交互),浏览中编辑或发送即退出。

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:czhzz/dsh-input-history
dsh-input-history

Standalone arrow-key input history for the DSH web composer: every sent prompt (Enter or the send button, in any session or workspace) persists to ONE global localStorage ring (default 100 entries, overridable) and ↑/↓ recalls it instantly and completely.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sunshaobei/dsh-input-history
dsh-intent-loop

Session-scoped Intent Loop tools for DeepSeek Harness, backed by the shared local MCP core.

Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:rrrrrredy/intent-loop
dsh-intercom

Intercom plugin for DeepSeek Harness (dsh): discovery and messaging between independent dsh sessions on the same machine

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Sqhao-O/dsh-intercom
dsh-interrupt-button

A green interrupt button beside the DeepSeek Harness send box: silently stops a running agent, which then summarizes its progress and asks for your new requirements; the interrupt prompt is customizable.

Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:guo-ziao/dsh-interrupt-button
dsh-ios-control

Authenticated LAN gateway for DeepSeek Harness: reverse-proxies the official web UI with Basic Auth, advertises via mDNS, and adds a fork_session tool.

Agent collaboration · Interface extensions · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Hjay1101/dsh-ios-control
dsh-isolation-pod

隔离舱:在 DSH 主会话之外运行受沙箱约束的隔离任务;主会话默认完全无感,结果返回与文件导出都要手动确认。

Agent collaboration · Productivity
dsh-j-space

Automatic J-Space cognition suite for DeepSeek Harness (dsh): a zero-config dsh-plugin that adds structured working state, checkpoints, and verify-before-ship discipline to every agent session.

Skills · Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wxxb789/dsh-j-space
dsh-jenkins

Jenkins CLI plugin (dual-face): multi-server config page, model tools, and a per-workspace Run-Jenkins-Job entry with environment tabs. Bilingual UI (zh/en), no hardcoded paths, publishable to npm / GitHub

Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jsoncode/dsh-jenkins
dsh-jev-memory

Typed, auditable long-term memory for the DeepSeek Harness: a turn-end write hook, a judgement layer (Jev or a deterministic fallback), a local store, and per-session recall injection.

Memory and knowledge · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lrqiisrom/dsh-jev-memory
dsh-jev-ultrafast

Drive a browser from one natural-language goal: TypeSafe Jev picks the next operation and target from an indexed element table, so a DeepSeek Harness session spends one tool call instead of one turn per click.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xingzhen199186/dsh-jev-ultrafast
dsh-jiey-browser

Drive Jiey Browser from DeepSeek Harness — real Chromium agent tools over MCP

Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jiewaigongxing/dsh-jiey-browser
dsh-job-progress

Live progress for long-running background jobs in the DeepSeek Harness web GUI: a draggable floating ball with a per-session task panel showing done/total, speed and ETA.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Rice00/dsh-job-progress
dsh-just-chat

One-click native conversations with independent workspaces for DeepSeek Harness

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:exoticknight/dsh-just-chat
dsh-kanban

A minimal DSH web GUI kanban board: sidebar entry plus a multi-column board with local persistence, real task execution through dsh sessions, and per-task model selection (provider/model applied via session.selectModel before the run). Standalone cordis bundle — no dsh source changes.

Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:raosay/dsh-kanban
dsh-kanban-flow

Agent-driven kanban board plugin for DeepSeek Harness: one board per workspace, per-task agent sessions, human/agent workflow guards, light/dark UI. Based on the dsh-kanban plugin architecture.

Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:thomasvvugt/dsh-kanban-flow
dsh-kanban-watcher

DSH ↔ Hermes 双 Agent 协作管道的看板执行侧插件:监听 Hermes kanban 队列,把任务交给 DSH Agent 在 Web GUI 会话中执行,并把结果回写看板与 done 文件。 支持会话继承([会话继承:关键词] 续接历史会话)。

Agent collaboration · Productivity
dsh-keyring

DeepSeek Harness 密钥保险库插件:密钥自动脱敏、自动收纳、密码本设置页、跨重启持久(官方 profile bundle)

Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:re-ITRT/dsh-keyring

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.