dsh-auto-memoryClaude Code style auto-memory plugin for DeepSeek Harness: typed memory files + MEMORY.md index auto-injected into the system prompt
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AskTheWay/dsh-auto-memory最高の DSH プラグインを見つけよう
1213件
会話の記憶、ナレッジ検索、コンテキスト管理のプラグインを探せます。
dsh-auto-memoryClaude Code style auto-memory plugin for DeepSeek Harness: typed memory files + MEMORY.md index auto-injected into the system prompt
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AskTheWay/dsh-auto-memorydsh-autonomyAutonomy level plugin for DeepSeek Harness: per-session creativity/autonomy control (strict → wild) via graded system-prompt directives
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:abab996/dsh-autonomy#f3bb33a144dc3b58393fe37f7e00dee67e27db75&path:packages/dsh-autonomydsh-autonomy-clientAutonomy slider client plugin: per-session autonomy level control in the composer tool row, left of the model switcher
dsh-btwGlobal /btw command: one-off model Q&A that is not recorded into session memory (Claude Code /btw equivalent)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:clclyzybzjsq/dsh-btwdsh-btwClaude Code-style /btw side question (fork, no tools, single turn) + /remember session memory for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wensincai/btw4DeepseekHarnessdsh-cardiancardian —— DeepSeek Harness 知识中心插件:RepoWiki / 知识卡片 / 记忆,全部落地到本地 Obsidian 仓库
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:myYangyunfan/dsh_cardiandsh-character-studioDeepSeek Harness native immersive roleplay studio & companion system. Unifies decoupled character cards with Hindsight graph memory.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Ryu6Zero/dsh-character-studiodsh-checkpointsDSH conversation checkpoints: list every user instruction, jump/scroll to it, roll the visible conversation back to it (optionally with file snapshots), recall/edit sent instructions, show this round's file changes inline under the conversation, and a VS Code-like diff viewer (unified/side-by-side) with per-file undo.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ANOKO1122/dsh-checkpointsdsh-cipher把 cipher 的持续思考/三中台/四类记忆以 UNNI/LOOP 会话模式接入 DSH
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NoxTyrannus/dsh-cipherdsh-clawshellClawShell vision re-implemented as DeepSeek Harness plugins: self-perception (sense), self-adaptation (adapt), swarm trust + ecological niche (swarm), plus tools.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jorinyang/dsh-clawshelldsh-client-ui-report-panelChatGPT-style report artifact panel for the card: 'report' render intent: turn-tail cards, a right-hand panel with tabs/search/scroll memory, and ask-in-chat
dsh-clipboard-historyClipboard history plugin for DeepSeek Harness: monitors the system clipboard and exposes recall/copy tools.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kuangre123/dsh-clipboard-historydsh-collabMulti-agent collaboration shared workspace for DSH (DSH × Claude Code × Kimi Code × DevEco Code): outbox/status/tasks/knowledge/artifacts protocol as a cross-platform DSH plugin + CLI.
dsh-composer-uxDSH Web 输入体验增强插件:可配置发送/换行键位 + 自定义输入框右键菜单 + 面板尺寸记忆 + OpenCode 会话请求头(含设置页)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fangwen9527/dsh-composer-uxdsh-context-maid自动上下文策展:tool 输出瘦身 + 无效日志清理 + 工作流/记忆钉扎保护 + 先归档后压缩
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Icstick/dsh-context-maiddsh-conversation-atlasProject-level conversation memory explorer for DeepSeek Harness with related memories, cross-session bridges, BM25 search, and exact chat navigation.
dsh-data-ledger数据管理 + AI 管家:统一本地数据看板(来源/位置/摘要、回收站删除),并给智能体装上看懂与清理数据的 ledger_* 工具
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Niuniu-Sir/dsh-data-ledgerdsh-deeptutorDeepTutor bridge bundle for DeepSeek Harness: learning capabilities, knowledge bases, and note archiving (HTTP/WS first, CLI fallback; auto-adapts local/remote deployment).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:TecFancy/dsh-deeptutordsh-dejavu-memoryDeepSeek Harness plugin: DejaVu memory client — automated long-term memory (boot/read/search/create/update/delete) backed by your own DejaVu MCP server.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:RealAlexandreAI/dsh-dejavu-memorydsh-distillation-director蒸馏主管(distillation-director):把一本书蒸馏成可执行 Agent 技能的判态制元技能(V4.1 三闸门禁制)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:winsonpong98-cloud/dsh-distillation-directordsh-dream-reflectionScheduled dream-reflection plugin for DeepSeek Harness: bounded, redacted, quarantine-reviewed memory cards over workspace sessions.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:acosmi/dsh-plugin#3412f579033144497a22903ef64255d835cb29bf&path:plugins/dsh-dream-reflectiondsh-engram-recapForces periodic Engram memory recall and save reminders for DeepSeek Harness agents: injects a dynamic system-prompt context that reminds the model to load prior session memory at the start of a session, and to save new decisions/bugfixes/learnings every N turns - so knowledge survives across sessions without depending on the model remembering to do it unprompted.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:elmaxid/dsh-manage#994c0ee484a6bffad09ba130ffc6576b1e2e9e98&path:plugins/dsh-engram-recapdsh-env-profileDSH 全局经验插件(骨架):自动探测本地依赖/便捷路径/网络/磁盘并沉淀为跨会话环境档案,订阅 session/event 折叠每会话统计,把低开销摘要注入每轮系统提示,env_profile 工具按需查全量——减少重复探测、加快会话、降低 token 消耗。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Yvesgao/dsh-env-profiledsh-errkbRecycles errors: diagnose once, inject the known fix next time.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jingchangzhao-gif/dsh-errkb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。