dsh-neuron-memory本地记忆层:按预算注入、情绪优先、可审计、不联网。给 DeepSeek Harness 用。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Elio896/dsh-familiar-memory最高の DSH プラグインを見つけよう
2467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-neuron-memory本地记忆层:按预算注入、情绪优先、可审计、不联网。给 DeepSeek Harness 用。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Elio896/dsh-familiar-memorydsh-sidechatMemory-only read-only side chats for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Ephemeral-AI-Lab/dsh-plugins#cb9ea007a6b41da06b65f9ed9a86e028eee9e60e&path:plugins/sidechatdsh-krouterZero-maintenance second brain for coding agents: one-line install, an Obsidian vault distilled every night, exact lock + ranked recall that refuses instead of guessing. Chinese and English; macOS, Linux, Windows. Cursor, Codex, Claude Code, DeepSeek Harness. No vector store.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:398894496-arch/KRouterdsh-tavernDeepSeek Tavern - DSH roleplay plugin: character cards, worldbooks, presets, memory, relations, plot options. Install the companion plugins dsh-muv-engine and dsh-muv-table as well for the full experience (status bar, plot options, variable tables). PolyForm-Noncommercial-Copyleft-1.0.0
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chen731215-dev/dsh-tavern-v2oh-my-dshDSH 增强插件:长上下文、任务验证、提示词优化、代码理解、电脑操作,以及 DSH 原生界面与可选主题、配色和背景。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add https://github.com/gulagala001/oh-my-dsh/releases/download/v0.2.1-rc.3.omd.1.1.2/oh-my-dsh-0.2.1-rc.3.omd.1.1.2.tgzdsh-plugin-guideThe dsh-plugin-guide knowledge base plus the dsh-plugin-dev CLI toolchain: official docs, Cordis primer, community deep-dives, and battle-tested pitfalls registered as an on-demand agent skill, with a scaffolder, static checker, and pack verifier for building DSH plugins.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PerryLink/dsh-plugin-guidedsh-krouterDSH-KRouter — Agent knowledge OS. Self-evolution. Timer on by default; your vault-page API key or logged-in CLI is the key. Cursor, Codex, Claude Code, DeepSeek Harness. No vector store.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:398894496-arch/DSH-KRouterdsh-tavernDeepSeek Harness 酒馆管理插件 - 角色扮演、角色卡/世界书/预设管理、多会话隔离、记忆总结、关系网、剧情选项
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chen731215-dev/dsh-tavern@hr98w/dsh-memoryClaude Code- and Codex-inspired long-term memory for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add @hr98w/dsh-memory@xuxchloris/dsh-sdrDeepSeek Harness plugin for a controllable SDR digital employee
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Xuxchloris/Alex#491776832f257f7d63113f8f4b541bd075cdda55&path:packages/dsh-sdrdsh-memoirDeepSeek Harness (DSH) local-first cross-session project memory: bounded cache-friendly Hot Memory, BM25 recall/cache, provenance, lifecycle and bilingual Web GUI; no embeddings, external service or bundled runtime dependencies.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Qinling-Melon-Farmers/dsh-memoirdsh-better-reasoning-effortThird-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models page card.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:HaoyueQin/dsh-better-reasoning-effortdsh-directorxDirectorX:第一个以 DeepSeek Harness 为内核的 Video Agent Harness——面向端到端 AI 视频生产的开源 dsh-plugin,覆盖视频生成、分镜画布、智能剪辑、FFmpeg 质检与交付。The first DeepSeek Harness-native video agent harness for AI video production.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LaplaceYoung/dsh-directorxdsh-vibe-mathMulti-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — THREE agent presets in one install: vibe-math-v2 (probability-driven: qs.json + Propos knowledge base + explorer→solver→review/debate verdict), vibe-math-v3 (THIRD-generation, recommended: paper-style Markdown knowledge base with Problems/Progress/Propos/Methods/Verified + planner-agent scheduling that decides the next N actions + universal theory/method invention library + agents write their own Markdown directly via a per-file write lock), and vibe-math-v4 (FOURTH-generation: persistent self-organizing resident subagents that message & meet to decide all tasks, verify only by unanimous consensus, /compact at a context threshold, and stop only when all agree the problem is solved). Installing this bundle auto-installs all three presets (v1 was removed at v2.0.0).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ChongCyrus/Vibe-Mathematicsdsh-claude-moveFour-source migration wizard: copy Claude Code, Codex, OpenCode and Hermes sessions, memories, skills, instructions and slash commands into DeepSeek Harness as resumable sessions — copy-only, approval-gated, idempotent
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PerryLink/dsh-claude-movedsh-archived-sessionsDSH web plugin: an Archived Sessions manager in Settings — browse archived conversations, expand per-session details (disk usage, downloads, tool usage, lineage, cross-session recall), multi-select and permanently delete.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Zephyr-vibe/dsh-archived-sessionsdsh-credentials-centerOne place for every API credential DeepSeek Harness and its plugins use: every reference (env name) the model routes, media APIs, web search, desktop pet, memory embeddings and cost meter point at, whether it is configured and where it is stored, which features are bound to it, an owner-given alias/note, and set / replace / delete — through the core credential store, never a plain file.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:WZZNNE/DSH-CyberWorkStation#54855352ddc1a46f62c26ebb8ba6e9e2a4f07875&path:plugins/dsh-credentials-centerdsh-memory-liteLightweight memory for DeepSeek Harness: stores compaction summaries and extracted facts, recalls them lexically (BM25, CJK-aware) or with local embeddings, injects relevant items as a separate context message, offers memory_recall / memory_note tools, and lets the user view and edit every session's active compaction summary.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:WZZNNE/DSH-CyberWorkStation#54855352ddc1a46f62c26ebb8ba6e9e2a4f07875&path:plugins/dsh-memory-liteamadeus-for-dshSteins;Gate 0 Amadeus (Makise Kurisu) 助手:Live2D 翻盖手机 + 日语语音 + 长期记忆,DeepSeek Harness 插件
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yyxcnasd/amadeus-for-dshdsh-ros2-profiledsh-ros2 robot profile: body registration, load, communication-topology knowledge base (snapshot/learn/show/search/diagnose) and zero-pose calibration (4 tools) + robot-registration/robot-retrieval skills. Cordis bundle.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:StvLi/dsh-ros2#1c9ea44df6ee8602a3f075d81ab28e66a1740991&path:packages/profilesupergraphSupergraph workflow, skills, and MCP tools for DeepSeek Harness (DSH)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:datit309/supergraphdsh-hertaInstalls Herta (黑塔) as a DeepSeek Harness agent — persona, memory, narrative layer, voice and UI. · DSH 插件:把 Herta(黑塔)作为一个 agent 装进 DeepSeek Harness —— 人设、记忆、语音与界面。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:HerTa-st/Herta-dshdsh-unified-contextDSH Unified Context (统一上下文): migrate pi/opencode/codex/claude-code/WorkBuddy sessions into DeepSeek Harness, share AGENTS.md/skills/project & agent memory through symlinks, and migrate automations. One context, every harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add dsh-unified-contextoh-my-knowledgeOMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.
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。