Discover The Best DSH plugins

Agent collaboration · DeepSeek Harness plugins — Page 146

7302results

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

dsh-plugin-translation

Translation toolkit for DeepSeek Harness agents: segmentation, term extraction, durable glossary and tone memory, cross-segment consistency checks, source-target QA, heuristic quality scoring, tone guides, and a durable translation memory

Memory and knowledge · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:863683348/dsh-plugin-translation
dsh-plugin-vision-toolkit

Vision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images

Agent collaboration · Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YYTbit/dsh-plugin-vision-toolkit
dsh-plugin-wallet

DeepSeek Harness wallet plugin: official DeepSeek API balance cards, low-balance badge, per-session token cost estimates, and a composer cost line.

Agent collaboration · Notifications · Financial data · Interface extensions · Productivity
dsh-plugin-warroom

RTS-style orchestration for DeepSeek Harness: you are the sovereign issuing strategic orders; a resident commander agent decomposes them and deploys typed subagent troops (recon/engineer/medic/scribe) on isolated fronts, with an append-only campaign event log and hard rules of engagement.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Kaiji-Z/dsh-plugin-warroom
dsh-plugin-wepre

DeepSeek Harness plugin: publish single-screen content cards to WePre Next straight from a dsh agent session

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:shujiTech/dsh-plugin-wepre
dsh-plugin-x-profile-reader

X (Twitter) public profile/tweets reader tool backed by Apify, for DeepSeek Harness agent presets.

Agent collaboration
dsh-pocket

把 DeepSeek Harness 装进你的口袋:一个包、一个设置页,手机扫码即同步访问电脑上的 DSH(局域网 + 公网,实时同屏)。

Agent collaboration · Interface extensions · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:enoughpower/dsh-desktop-mac#f957acef9a0861cef94ae074c75d6bfab0c04379&path:plugins/dsh-pocket
dsh-pocket

Watch and steer your DSH agent from a phone browser: approve tool calls, send a message, stop a turn

Agent collaboration · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:keman-ai/dsh-pocket
dsh-policy

User-controlled policy & personalization runtime for DeepSeek Harness — enforce hard project constraints at the agent lifecycle boundary.

Agent collaboration
dsh-ponytail

Ponytail for DSH — the lazy senior dev. Live intensity switching (off/lite/full/ultra) with a toggle in the composer, injecting a minimal-code ruleset before every step to cut token usage.

Skills · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:HB123X/dsh-ponytail
dsh-ponytail-skills

Ponytail, lazy senior dev mode, for DeepSeek Harness: 6 skills (ponytail, ponytail-audit, ponytail-debt, ponytail-gain, ponytail-help, ponytail-review) adapted from DietrichGebert/ponytail (MIT)

Skills · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gongyijie85/dsh-ponytail
dsh-port-inspector

Windows Port Inspector Bundle for DeepSeek Harness

Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ianho7/dsh-port-inspector
dsh-ppt-expert

DSH extension bundle: presentation-deck expert — persona + LibreOffice Impress MCP (9 tools) + matplotlib chart kernel + live browser preview. Zero npm dependencies.

Memory and knowledge · Agent collaboration · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:TANGZHUO12/ppt-expert
dsh-pr-watch

DeepSeek Harness plugin (in development): reports what changed in your authored pull requests since your last check — merged, closed, or gone stale.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Shyboy0499/dsh-pr-watch
dsh-praxis

Praxis — a bundled engineering-methodology skill library for DeepSeek Harness (dsh). Ships as a self-contained Cordis plugin that registers a skill provider on ctx.skills.

Skills · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JohnXu22786/skill-framework
dsh-preset-agent-manager

Preset agent manager for DeepSeek Harness: a sidebar admin panel plus the preset_agent_dispatch delegation tool over per-agent plugin whitelists.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qingli-sketch/dsh-preset-agent-manager
dsh-preset-composer

Host-only custom agent preset editor via the /preset-composer slash command: name, description, preset prompt, skills, and plugins. A client UI (child-slot configure button) is reserved for future DSH support of out-of-tree client bundles.

Skills · Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:masquerator-coder/dsh-preset-composer
dsh-preset-library

Compact, searchable, tag-based agent preset management for DeepSeek Harness

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LiweiDonVee/dsh-preset-library
dsh-preset-skills

Register each agent preset's own skills/ directory as discoverable, preset-isolated skills in DeepSeek Harness, including blank-session preset switching and a startup roster prewarm that shrinks the web catalog warm race. Replacement for the old preset-skills copy-in mechanism.

Skills · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:masquerator-coder/dsh-preset-skills
dsh-preset-switch

Mid-session agent-preset switch for DeepSeek Harness: a composer button next to the access-mode control that re-links the running session's agent scope and notifies the model.

Agent collaboration · Productivity
dsh-price-less

DSH 上下文管理插件:任务边界、项目帧、自动判别与上下文优化(开发中,R2 判别域 P8–P14b1 已施工)

Agent collaboration · Financial data · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:54shitaimzf/dsh-price-less
dsh-prime-memory

L0~L3 分层蒸馏记忆插件 for DeepSeek Harness:自动捕获对话(L0)、抽取原子记忆(L1)、整合场景块(L2)、蒸馏核心画像/团队方法论(L3),并在模型步骤前自动召回注入。移植自 MemoryCore (TencentDB Agent Memory) 的管线设计。

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:drscrewdriver/dsh-prime-memory
dsh-project-anchor

User-approved Goal, Milestone, and Turn checkpoints for solo long-running DeepSeek Harness projects.

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:KKLL2025/dsh-project-anchor
dsh-project-context

DeepSeek Harness plugins for project-level persistent context: memory consolidation (MEMORY.md + CONTEXT.md), low-frequency autolearn for project skills, session archives with a mechanical index, and automatic handoff.

Memory and knowledge · Skills · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:P02-1010751281/dsh-project-context

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.