Discover The Best DSH plugins

Agent collaboration · DeepSeek Harness plugins — Page 138

7302results

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

dsh-im-hub

A multi-platform IM gateway for DeepSeek Harness (dsh) — Feishu (Lark), WeCom (WeChat Work), and Telegram. Turn your dsh agent into a chat assistant reachable from the messaging apps you already use.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ThreeBody6666/dsh-im-hub
dsh-imessage

Photon-hosted iMessage transport and configuration UI for DeepSeek Harness

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:photon-hq/dsh-imessage

dsh-img

★ 1
dsh-img

Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。

Agent collaboration · Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gmleong/dsh-img
dsh-import-agent-settings

导入智能体设置:从 Claude Code / Cursor / Codex / cc-switch 一键导入 Skills、MCP、指令、模型供应商等到 DeepSeek Harness(设置 → 通用设置 → 导入智能体设置)

Skills · Agent collaboration · Developer tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MayBeTheWorld/dsh-import-agent-settings
dsh-import-copilot-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/Copilot 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-copilot-files
dsh-inapp-browser

A shared interactive browser inside DeepSeek Harness and Better Sidebar: mouse, keyboard, screenshots and agent tools.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:alllllinnrann/dsh-inapp-browser
dsh-inherit

导入智能体设置:从 Claude Code / Cursor / Codex / cc-switch 一键导入 Skills、MCP、指令、模型供应商等到 DeepSeek Harness(设置 → 通用设置 → 导入智能体设置)

Skills · Agent collaboration · Developer tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MayBeTheWorld/dsh-inherit
dsh-init-command

DSH plugin: /init slash command that generates an AGENTS.md guide for the current project with a two-stage model call

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LittleFishStars/dsh-init-command
dsh-insight

DeepSeek Harness (dsh) 浏览器伴侣:网页划词即解读、侧栏多轮追问、Markdown 渲染,并让 dsh 智能体读取当前页面、抓取网络请求、驱动浏览器。

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Suguyun/dsh-insight
dsh-insights

DSH plugin: replica of Claude Code's /insights command — cross-workspace session usage analysis powered by the global session-query corpus, with per-session LLM facet extraction (cached), 8 analysis prompts, and a self-contained interactive HTML report. Runs as a foreground /insights command in the session, orchestrated via insights_collect / insights_facet / insights_aggregate / insights_render / insights_run model tools with subagent-parallel facet fan-out.

Memory and knowledge · Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DDDPG/dsh-plugins#543d4b046af0c67602be6d16cba7f6ed94239247&path:plugins/dsh-insights
dsh-interactive-terminal

Interactive terminal plugin for DeepSeek Harness

Agent collaboration · Interface extensions · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mingzhicode/dsh-interactive-terminal
dsh-issue-tracker

Jira Cloud issue-tracker service and model-facing tools for DeepSeek Harness

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xxiaoxiong/dsh-issue-tracker
dsh-j-space

Bundles the J-Space Cognition Suite as a DSH skill provider: an on-demand inner-workspace skill (reasoning, planning, ledger) for DeepSeek Harness agents.

Skills · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Harzva/dsh-j-space
dsh-jev-decide

DSH 插件:把 TypeSafe Jev(System One 决策模型)注册为 agent 工具 jev_decide。调用 https://api.typesafe.ai/v1/systemone,让 agent 在路由/分级/guardrail 等场景拿到带校准概率的结构化判定(noul/choice/score),而不是让大模型瞎猜。

Agent collaboration
dsh-jev-interceptor

Millisecond System-1 judgement for every tool call in DeepSeek Harness: Jev-powered risk classification and evidence-gated auto-approval, fail-closed by construction.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AskTheWay/dsh-jev-interceptor
dsh-journal-calendar

Daily journal and calendar for DeepSeek Harness: the journal_record tool appends one JSON file per day, and the right sidebar draws it as a calendar.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:crease123/dsh-journal-calendar
dsh-jspace-trigger

Configurable near-field trigger that reminds a DeepSeek Harness agent to load the J-Space Cognition Suite only when rules say it is worth it

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EricWang1358/dsh-jspace-trigger
dsh-just-enough-tools

Progressive tool and skill selection for DeepSeek Harness, powered by Jev

Skills · Agent collaboration · Financial data
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:RickT34/dsh-just-enough-tools
dsh-kanban

A DeepSeek Harness (dsh) plugin that turns the ji-kanban Jira/GitLab board into an agent-worked kanban: each project is a workspace-wide connection plus a local issue cache, exposed as model-callable tools with a browser board view.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JianwuYang/dsh-ui-kanban
dsh-kernel-kimi

Kimi Code written in DSH form: the full kimi-cli 1.49 tool surface registered as DSH tools.

Agent collaboration · Developer tools
dsh-kimi-tide

kimi-tide(月汐)— Kimi Code subscription as a native DeepSeek Harness LLM provider, with built-in OAuth token management.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tafcear/kimi-tide#bea7ecc91ca666363c31abb45eafd0651b8e3a37&path:packages/dsh-kimi-tide
dsh-kingdee

Kingdee Cloud Starry Sky secondary-development plugin for DeepSeek Harness (DSH). Typed tools over the Kingdee Cloud WebAPI, credential-safe config, and a companion domain skill.

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:maxwell-feng/dsh-kingdee
dsh-krouter

Hot-pluggable KRouter for DeepSeek Harness. Same Obsidian vault as Cursor and Codex. No vector store.

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:398894496-arch/runtime36
dsh-kubernetes

Safe Kubernetes capability for DeepSeek Harness: workload inspection, bounded logs/events, failure diagnosis, and approval-gated changes with dry-run by default.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xxiaoxiong/dsh-kubernetes

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.