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。
@ersss/dsh-migrateImport chat history and memory from other AI agents (Claude Code, Codex CLI, Gemini CLI, Aider, Cline, OpenCode, Hermes Agent, OpenClaw) into DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kkkkkkkkki/dsh-migrate@flowboard/dsh运行在 DeepSeek Harness 中的开源办公协作与团队管理插件
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Untidy-cocoabutter173/Flowboard#6cbd818f988b81962de511db404963ae31ac312a&path:packages/dsh@flowboard/dsh-clientAlign your team goals, meetings, agents, and documents in one workflow—Flowboard turns DeepSeek Harness into a natural hub for work without task management overhead.
@flowingspring/dsh-workspace-memoryWorkspace-scoped durable memory for DeepSeek Harness and optional voice integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lgquan/dsh-workspace-memory@fonlan/dsh-gitmemoGit-backed long-term memory for DeepSeek Harness: a local .mem git repo with mem_search / mem_read / mem_write / mem_delete tools, auto-managed by the agent with zero manual steps.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fonlan/dsh-gitmemo@foresight/memoryForeSight: a temporal-aspect long-term memory plugin for DeepSeek Harness (dsh)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiangrui979/foresight@gausszhou/dsh-where-am-iInject a neofetch-like device info block (host, OS, kernel, arch, CPU, memory, uptime, timezone, locale, shell, node) into each brand-new DeepSeek Harness session once; existing sessions are untouched.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gausszhou/dsh-where-am-i@getnote/dsh-plugin在 DeepSeek Harness 中用自然语言搜索、保存和阅读得到大脑笔记
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:iswalle/getnote-dsh-plugin@goodandready/dsh-session-searchDeepSeek Harness agent tool (session_search) for full-text search across historical sessions backed by core SQLite FTS5 engine without memory overhead.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:GooDAnDReaDY/dsh-session-search@guntur-d/dsh-memoryPersistent cross-session memory plugin for DeepSeek Harness: workspace-scoped durable facts with model-facing memory_write/list/search/forget tools and bounded prompt injection
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:guntur-d/dsh-memory@guowenzhang/dsh-memoryClaude-compatible memory for DeepSeek Harness: a user-chosen memory directory with MEMORY.md index and topic files, the memory tool, and a settings page
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhang-guo-wen/dsh-memory@harness-flow/dsh-obsidianDSH-native Obsidian bridge: index local projects into a vault and build a wiki-link knowledge graph
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Harzva/dsh-obsidian@harzva/dsh-session-folders给 DeepSeek Harness 的会话加一层「文件夹」归类：按 cwd 自动归档、手动移动到任意文件夹，文件夹路径即项目记忆作用域。 Adds a folder layer to DSH sessions: auto-file by cwd, move sessions between folders, folder path = project-memory scope.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Harzva/dsh-session-folders@having5548/dsh-backupDeepSeek Harness 备份与恢复插件：在 Web UI 设置里新增「备份与恢复」页，把全部工作区、完整对话（会话文件字节级复制）、附件、设置与 dsh-mnemon 记忆数据导出为一个 ZIP 备份包，并可预检后合并 / 覆盖导入。会话内容全程不解包不改写，任何 dsh 会话格式代际（v0–v3+）都可携带，harness 升级后可正常导入，dsh-mnemon 上下文注入恢复后与原本一致。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:having5548/dsh-backup@heeweelee/dsh-session-pluginDeepSeek Harness plugin: recall previously sent messages in the input box with ↑/↓, and permanently delete a workspace session's local records with a right-click.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Heeweelee/dsh-session-plugin@helibeiqi/dsh-memory-projectionDeepSeek Harness 可热插拔的记忆投影框架，运行时动态切换 Agent 认知模式，严格遵循 Model-Visible 不变量
@honcho-ai/dsh-honchoHoncho memory for DeepSeek Harness — persistent, cross-session memory that survives context resets and restarts.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:plastic-labs/dsh-honcho@hoyyang/dsh-code-graph单入口原生代码图工具：索引/保鲜/分支跟随/符号检索/调用链/影响面/路径/架构，复用本机 codebase-memory 引擎，零 MCP 会话
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hoyyang/dsh-code-graph@hr98w/dsh-memoryMarkdown long-term memory for DeepSeek Harness with Global and Workspace layers and progressive disclosure
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hr98w/dsh-memory@huanlin/dsh-plugin-device-infoDSH plugin exposing Windows device information tools — one tool per Win32 device category (time, system, cpu, memory, disk, gpu, network, battery, processes, usb, audio, printers). Read-only WMI/CIM + Node os collectors.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lsz-asd/dsh-plugin-device-info@hyls9527/dsh-memoryBounded, file-backed, cross-session self-maintained memory for DeepSeek Harness — a faithful port of the hermes-agent MEMORY.md / USER.md mechanism.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hyls9527/dsh-plugins#7d0513bce3c267dc4f50429b1389ac8df114b137&path:packages/memory@hyls9527/dsh-skill-curatorSkill lifecycle curation for DeepSeek Harness: automatic usage tracking plus a skill_curator tool that reports staleness and archives or restores user skills.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hyls9527/dsh-plugins#7d0513bce3c267dc4f50429b1389ac8df114b137&path:packages/skill-curator@ihorleleka/wiki-kitInstaller and runner assets for wiki-manager agent wiki-kit integration.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ihorleleka/Local-Rag-Wiki@jipika/dsh-memoryTwo-layer long-term memory (global + per-project) injected into the system prompt on every assembly, with a Settings panel to switch each layer off. Live re-read, zero extra LLM cost.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jipika/dsh-memory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。