@deepseek-ai/dsh-api-remotesRemote BFF assembly and Host Agent/Session lookup policy
最高の DSH プラグインを見つけよう
20408件
DeepSeek Harness のコミュニティプラグインを検索。用途、インストール方法、互換性を比較し、AI ワークフローに合う拡張機能を見つけましょう。
@deepseek-ai/dsh-api-remotesRemote BFF assembly and Host Agent/Session lookup policy
@deepseek-ai/dsh-app-bootShared boot glue for the app bins: .env loading, fail-loud Loader guards, snapshot-aware config resolution, and the Loader boot sequence
@deepseek-ai/dsh-attachmentDurable immutable attachment storage seam for the DeepSeek Harness
@deepseek-ai/dsh-attachment-localPrivate content-addressed DSH_HOME attachment storage
@deepseek-ai/dsh-baseThe shared dsh core as a profile bundle: every profile's first patch layer, inserting the base plugin rows over the empty profile root
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:KaichenCurry/dsh-design-mode#1e21a4d4847950f551aa8b1211fbe9596e85108e&path:packages/bundle/base@deepseek-ai/dsh-client-connectionWire consumer layer: HTTP-up/WebSocket-down client, ConnectionController dual streams with reconnect, and fixture api
@deepseek-ai/dsh-client-hmrDev-only hot-reload driver for script-loaded client entries: SSE rebuilt frames → invalidate/prefetch → fiber swap through the vendored Loader entry
@deepseek-ai/dsh-client-localeLocale plugin: Host-backed zh/en preference, browser-derived fallback, locale snapshots, and typed namespace dictionaries
@deepseek-ai/dsh-client-modulesClient module system, dual-face: node half composes the __DSH_BOOT__ entry graph (incremental dsh.client scan, bundle route, index tap, webPlugins service); browser half is the lazy-CJS module table the vendored cordis Loader consumes as its internal seam
@deepseek-ai/dsh-client-runtimeClient core services: SlotRegistry, SessionRuntime (scope tree + object layer)
@deepseek-ai/dsh-client-ui-agent-presetAgent-preset surfaces: the default for later sessions, this session's seat, and the composition editor
@deepseek-ai/dsh-client-ui-attachmentDynamic attachment presentation plugin for conversation input and message-image slots
@deepseek-ai/dsh-client-ui-brand-officialOfficial DeepSeek Harness brand occupants for the Web client's sidebar and conversation Hero slots
@deepseek-ai/dsh-client-ui-commandsClient command surface: global directory cache, '/' source, three command UI kinds, popupSelect registry
@deepseek-ai/dsh-client-ui-conversationConversation domain: skeleton, ordered chat flow, composer with the Host-backed busy-Enter preference, and details host
@deepseek-ai/dsh-client-ui-deliverablesProduced-files turn tail and clickable final-response file references for Web
@deepseek-ai/dsh-client-ui-design-modeDSH Design Mode infinite image canvas, inline comments, version tree, and composer context sync
@deepseek-ai/dsh-client-ui-directory-picker-browseIn-app directory browsing surface: the workspace directory-flow owner rendering the host's listing and creation primitives
@deepseek-ai/dsh-client-ui-directory-picker-nativeNative directory-picker surface: the renderless workspace directory-flow occupant driving the host's OS chooser
@deepseek-ai/dsh-client-ui-goalSession goal surface: GoalBar docked above the composer, read from the goal session projection
@deepseek-ai/dsh-client-ui-input-triggerInput trigger pipeline: '/' and '@' detection, candidate menu, pick routing to registered sources
@deepseek-ai/dsh-client-ui-jobsSession-header background-job list: live registry state mirrored from session/jobs frames
@deepseek-ai/dsh-client-ui-layoutShell plugin: three-column AppFrame with drag handles, ctx.layout viewing-state service (navigation + panels)
@deepseek-ai/dsh-client-ui-message-feedbackPer-message feedback controls contributed to the assistant-message action strip, backed by the messageFeedback Host Remote
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。