Discover The Best DSH plugins

Agent collaboration · DeepSeek Harness plugins — Page 192

7395results

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

@dsh-external/dsh-global-memory

DSH Agent 跨会话全局记忆插件:会话开始注入条目级索引,模型按需 recall 记忆全文,显式保存/搜索/删除,数据仅存本机 $DSH_HOME/memory/

Memory and knowledge · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:IriskaDev/dsh-global-memory
@dsh-external/dsh-harness-pilot

把其他 harness(opencode / Antigravity / claude / codex / ZCode / MiMo / Cursor / Qoder …)接入 DeepSeek Harness:作为 DSH 子代理派发任务,可指定各家模型,并在设置页里查看已配置的 harness

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Lawrence7y/dsh-harness-pilot
@dsh-external/dsh-herdr-toolkit

Expose Herdr workspaces, panes, and coding agents as DeepSeek Harness tools.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wenhao4126/dsh-herdr
@dsh-external/dsh-image-tiler

DSH agent tool: slice a large image into labeled ~800x800 tiles plus an overview thumbnail, preserving detail for vision models.

Agent collaboration · Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:meng-114/dsh-image-tiler
@dsh-external/dsh-jev-kit

Jev decision toolkit for DeepSeek Harness: 21 named, typed judgments (privacy scan, change-scope, memory triage, batch log/bug/alert triage, agent-loop checks) built on one hardened, budgeted, ledger-backed transport. Advisory only — it never blocks.

Memory and knowledge · Agent collaboration · Notifications
@dsh-external/dsh-jev-lens

Jev quality bench for DeepSeek Harness: shadow-accounted dangerous-command judging, injection screening for fetched content, canary A/B drills, and an optional gate mode — with the ledger, the report and the settings card needed to judge whether any of it is worth keeping.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jackchen13755/dsh-jev-lens
@dsh-external/dsh-local-memory

Persistent cross-session local memory for DSH with Markdown SSOT and self-healing SQLite FTS mirror

Memory and knowledge · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:huangjua/dsh-local-memory
@dsh-external/dsh-memory

Codex-like persistent memory for DeepSeek Harness: auto-injected memory summary, raw memory tools, and per-session rollout summaries distilled into a bounded global memory file.

Memory and knowledge · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:haitang1/dsh-memory
@dsh-external/dsh-memory

Qoder-Agent-SDK-style persistent memory for DSH: a background generation pass writes knowledge into per-scope memory files after each turn, and a consumption pass loads them into Agent context on session start or explicit refresh. DSH 持久记忆插件:按 Qoder SDK 的做法分离「生成」与「消费」,user/project 双作用域,token 预算加载。

Memory and knowledge · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hongweifei/dsh-memory
@dsh-external/dsh-memory-manager

DSH 记忆管理插件(宿主级):文件夹记忆库、印象、组合与双向链接、上下文计划注入、规约记忆(新会话自动常驻)、Agent 记忆工具、图谱视图,设置页自由开关。

Memory and knowledge · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tuanmaoOVO/dsh-memory-manager
@dsh-external/dsh-mobile-nav

尽可能的使dsh适配竖屏等移动端设备

Agent collaboration · Notifications · Interface extensions · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:daetz-coder/DSH-Mobile#7c163c0f5d02afe29739f9bb1ffeace266b6aa73&path:plugins/dsh-web-mobile
@dsh-external/dsh-oh-my-agent

忠实复刻 oh-my-openagent 核心能力:ultrawork 协议 / rules 引擎 / hashline 精编 / boulder 记忆 / 结构化代码搜索 / 评论检查 / 后台监控 / 交接 / 团队任务表 / OmO 控制台面板

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sskkde/dsh-oh-my-agent
@dsh-external/dsh-paper-tutor

面向中文读者的英文论文精读 Agent 预设插件:自动安装 paper-tutor 预设,提供零依赖 PDF 文本/图表提取(pdf_extract)、工作区论文盘点(paper_scan)、LaTeX 结构解析(tex_structure)与图表视觉分析(paper_figure),结合论文代码溯源讲解论文。

Agent collaboration · Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ASAKAFENG/dsh-paper-tutor
@dsh-external/dsh-parallel-pool

动态滚动窗口子代理任务池:一次调用跑完整批独立任务,内部滚动补位,后台运行不阻塞主对话

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wyStars/dsh-parallel-pool
@dsh-external/dsh-persona-memory

DSH 角色设定与长期记忆:角色库(persona.yml + SOUL.md + USER.md)、全局/项目两级记忆(FACT.md / MEMORY.md)、长期记忆 JOURNAL.jsonl;首条消息快照注入,对所有 agent 预设生效,附右侧栏管理面板

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hu568/dsh-plugin-persona-memory
@dsh-external/dsh-petdex-pet

Petdex pet in the DSH web GUI: floating bottom-right, draggable, sprite-animated by agent activity, with a live settings page (size / enable / switch / delete / gallery search + previews / install-by-code) and hover interactions. Ships with 4 bundled Hunter x Hunter starter pets (Gon, Killua, Kurapika, Leorio).

Agent collaboration · Interface extensions · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zenglihunter/dsh-petdex-pet
@dsh-external/dsh-plan-board

思维导图式项目规划可视 + 最强防跑偏:计划→模块→任务树/DAG、执行序号、Agent GPS 站位、改图人审门、git 交叉核对、阻断级漂移防护

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hoyyang/dsh-plan-board
@dsh-external/dsh-plugin-market

DSH 插件市场:GitHub 插件浏览/搜索/详情/一键安装,带 GitHub 登录、代理与配额显示。Plugin Marketplace for DeepSeek Harness.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zr-promise/dsh-plugin-market
@dsh-external/dsh-possibility-space

Explore AI answers as a steerable two-dimensional semantic possibility space inside DeepSeek Harness.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhangguiping-xydt/dsh-possibility-space
@dsh-external/dsh-preset-switch

Optional mid-session agent-preset switching: /preset command with a settings toggle

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:aorucshiea/dsh-preset-switch
@dsh-external/dsh-project-wiki

Auditable, workspace-local project wiki for DeepSeek Harness with a native Web view

Memory and knowledge · Agent collaboration · Interface extensions · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yu-xin-c/dsh-project-wiki
@dsh-external/dsh-prompt-enhancer

提示词增强插件:输入框注入强化/还原图标,后台调用隔离 agent 结合对话上下文与仓库知识重写提示词,替换草稿文本(保留 skill 引用记号)

Skills · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Vinzelles/dsh-prompt-enhancer
@dsh-external/dsh-raiden-theme

Raiden Inazuma Atelier / 稻妻雷电工房 — violet-gold acrylic DSH Web theme: light conservatory & dark electro stage, Raiden overlays, optional agent preset.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lengzhanbao/dsh-raiden-theme
@dsh-external/dsh-router-sci

科研计算 Agent 预设 — 核工程粉体/多相流仿真(LAMMPS + Fluent DPM + LaTeX)的 dsh agent preset

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Aone2233/dsh-router-sci

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.