dsh-timem-memoryTiMEM long-term memory for DeepSeek Harness: MCP bridge (credentials from ctx.credentials) + bundled memory/rule/knowledge skills
最高の DSH プラグインを見つけよう
7591件
エージェントの構成、複数 Agent の連携、タスク実行のプラグインを探せます。
dsh-timem-memoryTiMEM long-term memory for DeepSeek Harness: MCP bridge (credentials from ctx.credentials) + bundled memory/rule/knowledge skills
dsh-timer-taskDSH plugin: agent-schedulable recurring timer tasks with veto. When a task fires, the owning session (or its blocking subagent) is prompted and may veto (timer_veto tool or marker file); the command runs only when nobody vetoes.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:0gl20shk0sbt36/dsh-timer-taskdsh-timesheetTimesheet for DeepSeek Harness (dsh): turn-based time tracking from session logs — totals, per-day, per-project, per-provider, per-source rollups, tool-call counts, failure rates, and time-to-first-token. CLI + agent-callable timesheet tool, zero runtime dependencies.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zoahdev/dsh-timesheetdsh-tingxue听雪 · 双模式虚拟生命系统:LanceDB 自建向量记忆库 + 自建实体关系图谱 + 小 LLM 语义推理,聊天模式与 agent 模式双模式,全部交互在 QQ(dsh-notifier)。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:oranskyx/dsh-tingxuedsh-tm-guardTime-Machine-backed autonomous agent permission gate for DeepSeek Harness (dsh). Allows TM-rollback-able operations, blocks everything else.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ChaoJie0/dsh-tm-guarddsh-tmcra-memoryAutomatic TMCRA recall, injection, and role-separated writeback for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:reshuibuduo/dsh-tmcra-memorydsh-tmp-hookOne-time ephemeral webhook tool for DeepSeek Harness (dsh): mint a single-use callback URL, then wake the requesting agent session with the delivered payload.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Arcadia822/dsh-tmp-hookdsh-tmux-ccA persistent tmux control-mode cockpit for DeepSeek Harness Web.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:adrianleb/dsh-tmux-ccdsh-to-questionnaireSQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-to-questionnairedsh-todo-float-ballDSH todo 悬浮球:常驻可拖动悬浮球实时显示当前会话 todo_write 任务清单进度(总数/完成数/进行中),Shadow DOM 样式隔离,点击折叠/展开完整清单,状态颜色(待办灰/进行中橙脉动/完成绿)。数据双路同步:MutationObserver 抓官方 todo 面板为主 + 拦截会话投影帧为辅。双端可用(Desktop 桌面端 + Web 网页端)。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:loyalchiiina/dsh-todo-float-balldsh-todo-inboxDSH web static plugin: a global cross-session todo inbox. Any session's agent records human-action todos (merge MR, approve work orders, reviews) via inbox_add/inbox_done/inbox_list; a root-scope sidebar entry shows a count badge and an expandable list to view, open, and complete them. Host persists to ~/.dsh/todo-inbox.json and serves /todo-inbox/api HTTP routes for the browser half.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lumoping/dsh-todo-inboxdsh-todo-listDSH 待办清单插件:把通知、公告、邮件等文字转成带截止日期的待办,提供 todo_* 模型工具、/api/todo REST 接口与侧栏 To Do List 入口。A DSH todo-list plugin: converts notices, announcements, and emails into dated todos, with todo_* agent tools, a /api/todo REST API, and a sidebar To Do List entry.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:perry-ai/dsh-todo-listdsh-token-billLive DeepSeek balance plus per-hour token costing for DSH: two agent tools, hourly bar charts, and Markdown/HTML/JSON statements.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SanChou0627/dsh-token-billdsh-tokenslashTypeSafe Jev token optimization suite for DeepSeek Harness (DSH): Subagent Router, Fork Decoupler, Tool Schema Pruner, Output Compactor, and Settings UI
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JessenReinhart/dsh-tokenslashdsh-tool-app-verifyDSH plugin: browser & Electron UI operation and verification — actions, assertions, and visual regression testing.
dsh-tool-arxivarXiv preprint search tool for DeepSeek Harness agents (abstracts only, token-bounded)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bigstyle777/dsh-tool-arxivdsh-tool-code-reviewDSH plugin: structured code review tool — Agent reads git diff, reviews for bugs/security/style, outputs actionable findings.
dsh-tool-codereviewProfessional Code Review & Security Scan plugin for DeepSeek Harness - SARIF output, OWASP Top 10, AI-enhanced analysis, auto-fixes
dsh-tool-councilDeepSeek Harness plugin: a model-facing `council` tool that puts one question to several models on different providers at once, then reports where they agree and where they split
dsh-tool-gateway把 DSH 的工具目录收成两个元工具:find_tools 查、call_tool 调;其余工具不出现在模型可见目录里,但仍然可被调用
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:leolee9086/dsh-tool-gatewaydsh-tool-githubGitHub REST API tools for DeepSeek Harness: repositories, search, issues, pull requests, comments, account binding, and workspace integration, with a browser-side GitHub panel in the web GUI
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tkwkeven/dsh-tool-githubdsh-tool-hackernewsHacker News tool suite (hn_top_stories, hn_search, hn_item) for DeepSeek Harness agents
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tanf1ng/dsh-tool-hackernewsdsh-tool-managerManage DSH agent tools per preset and open on-demand tool groups for the rest of a session
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:pan17/dsh-tool-managerdsh-tool-nanobotNanoBot Subagent Bridge — lets DeepSeek Harness run the local nanobot AI agent (HKUDS/nanobot) as a subagent via a nanobot_run tool (oneshot CLI or persistent OpenAI-compatible server).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:2025Bigeye/dsh-nanobot-subagent-link機能のキーワードやカテゴリで絞り込み、更新日や GitHub Star で並べ替えます。
紹介、AI 分析、元の README を読み、プラグインの機能を確認します。
互換性、依存関係、手順を確認し、利用可能なインストールコマンドをコピーします。
DeepSeek Harness のコミュニティプラグイン集です。紹介、ソースへのリンク、インストール手順をまとめ、拡張機能の検索と比較を支援します。
いいえ。詳細ページは記録された互換性と依存関係を表示します。不明は互換性ありを意味しません。導入前にプロジェクトの文書を確認してください。
詳細ページのインストール欄を開き、コマンドがあれば Harness 環境で実行します。ない場合はプロジェクトの README に従ってください。