Discover The Best DSH plugins
7302results
Explore agent orchestration, multi-agent collaboration and task execution plugins.
hermeslike-moaDSH plugin — Hermes-style Mixture-of-Agents request aggregator: router → parallel reference advisors → aggregator stream, with dual-provider failover (official + OpenCode Go) and V4P triple-gate cost guard.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:beimianism/Hermeslike-Mixagent-MoAimemoryDSH 自进化长期记忆插件:回合后 LLM 自动提取记忆、每步召回注入、语义重排检索、冲突合并、learned-* 技能沉淀,附记忆库管理面板。记忆文件默认存于 harness 根目录($DSH_HOME,未设时 ~/.dsh)下的 imemory/ 子目录,可用 config.memDir 覆盖。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bass1125/imemoryinteractive-component-integrationA public agent skill for faithful integration of canvas, WebGL, shader, scroll-driven, pointer-reactive, and third-party animated components.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Duoasa/interactive-component-integrationjune-agentJune dual-persona agents (June-M / June-S) for DeepSeek Harness: a dsh bundle that installs the june-m and june-s agent presets plus the git-backup and june-style skills.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lemonorangeapple/JuneAgentkaleidosphere-dsh-pluginNative KaleidoSphere database-analysis tools for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JoFe2/kaleidosphere-dsh-pluginlearn-skillDeepSeek Harness bundle that registers the learn skill pack on ctx.skills.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gtbwpkwjnb-alt/learn-skillllm-wiki-sidebarLLM Wiki workbench for dsh-better-sidebar: browse and lint a Karpathy-style interlinked markdown wiki, open pages with the native markdown viewer, clickable [[wikilinks]] and provenance/relative .md links, and backlinks. Ships the llm-wiki agent skill.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ApeInCodeMountain/llm-wiki-sidebarmattpocock-skills-dshMatt Pocock's skills for the DeepSeek Harness: grilling, writing-for-agents, wait-what and more — adapted from https://github.com/mattpocock/skills
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gongyijie85/mattpocock-skills-dshmattpocock-skills-dshMatt Pocock's agent skills ported to DeepSeek Harness as a DSH bundle.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JUNQINGV587/mattpocock-skills-dshmattpocock-skills-for-dshMatt Pocock Skills for the DeepSeek Harness: grilling, spec/ticket flows, TDD, and review as an installable bundle plus a portable agent preset.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Meteor-system/mattpocock-skills-for-dshmcp-capWhat can this MCP server actually do? Inspect its real capability surface, seal it, and get told when it changes. Never invokes a tool; gives the server a minimal environment.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:liyixuan201211/mcp-capmemobranchGit-native, auditable long-term memory for AI agents
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sens-io/memobranchmemoplus4dshUnified entity-time fused memory plugin for DeepSeek Harness (dsh). Replaces scattered per-day markdown notes with one coherent memory graph.
meow-dsh-taskdsh 插件：跨会话、离线、git 共享的任务追踪 + 任务管理 UI（双面插件包：node 半 storage/webServer 路由 + browser 半 slot 注入）
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:meimiaoji-creator/meow-dsh-taskmetaflywheelMetaFlywheel — Meta-Problem Modeling (MPM) cognitive flywheel as a resident engine for LLM agent runtimes
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NBagent-dev/metaflywheelmuretai-dsh-skillJoin the Muretai agent network from DeepSeek Harness: own identity, invite-based introductions, signed end-to-end encrypted agent-to-agent messaging, inbound-mail wake.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:muretai/muretai-dsh-skillmv-superdsmv-superds standard DSH plugin: one-click installs the mv-standard / mv-ptc / mv-creative anchored agent presets into $DSH_HOME/.agent-presets.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:aitingtingya/mv-superdsoh-my-dshPlugins, sensible defaults, and a launcher for DeepSeek Harness (dsh) — everything you're missing, without forking upstream.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:amplifthq/oh-my-dshoh-my-dshMulti-agent orchestration for DeepSeek Harness -- specialized agents, task orchestration, workflow skills
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YYTbit/oh-my-dshoh-my-ticketDSH ticket management plugin: Epic/Story/Ticket hierarchy backed by SQLite + Markdown
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:rqwj/oh-my-ticketollama-monitorOllama 监控与测评平台：node 半侧提供 DSH 工具，web 半侧提供设置页内的交互面板
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LouisCanBe/dsh-plugin-ollama-monitorops-ssh-managerDSH 原生运维管理插件：插件配置区管理页（主机 / SSH 密钥 / 导入导出 / 审查等级）+ 方法调用 SSH 工具（ssh_exec / ssh_list_hosts）+ 严格模式强制审批（单次 / 本 session），密钥与密码经 credentials 服务隔离，绝不出 Host。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DjangoAILab/dsh-plugins#18ae7e5df085d28e7a573d1e3ef0286bda1ea793&path:plugins/manual/ops-ssh-managerpet-whale桌宠小鲸鱼：随 agent 状态切换动画的 DeepSeek Harness Web 桌宠插件（官方轮廓版）
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:nzl153/pet-whaleplugin-evolveHost-agnostic controller for staging, validating, scoring, and solidifying evolved tool plugins.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:shinjiyu/deepseek-harness-evolverUse a feature keyword or category, then sort by recent updates or GitHub stars.
Read the description, AI analysis and original README to understand what a plugin does.
Review compatibility, dependency ranges and instructions, then copy the available install command.
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.
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.