플러그인

One-click backup, export, import and migration of a whole DSH config: settings, plugins, MCP, skills and workspaces. Secrets are excluded by default and, if you opt in, are AES-256-GCM encrypted rather than written in the clear; imports preview first and auto-backup with rollback, profiles hold multiple setups, and remote sync pushes portable config through a private Git repo with secrets excluded.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

Knowledge-base-driven agent preset: wiki long-term memory, a web KB UI, a management page and optional UI polish.

Font engine for the Web GUI: system font enumeration, global and per-component font-size tuning with a Spy++-style picker, settings page.

DeepSeek Harness web GUI용 VS Code 스타일 3열 탐색기 + Monaco 에디터 플러그인입니다.

AI가 VLM(멀티모달 모델)을 자동으로 호출해 시각 분석을 수행할 수 있게 해주는 dsh 플러그인입니다.

DSH-better-sidebar 기반의 사이드바 질문 탭으로, Codex 스타일의 사이드 질문이나 Claude Code의 /btw 기능을 구현합니다.

DeepSeek Harness의 세션 간 인용(cue) 플러그인입니다.

Deepseek Harness + DeepSeek 기반으로 개발된 Deepseek Harness용 메시지 알림 메신저, 서드파티 채널(현재는 Feishu webhook)을 통해 푸시 가능

DeepSeek Harness 플러그인 번들로, 에이전트를 위한 graphlint 데드 코드 탐지 도구(graphlint_query / graphlint_build / graphlint_config + graphlint 스킬)를 제공합니다.

플러그인 스토어: npm 공식 카탈로그 + awesome 큐레이션 목록(550개 이상 플러그인, 11개 카테고리), dsh 필드 품질 검증, 공식 `dsh plugin add/remove` 원클릭 설치, 사이드바 + 설정 진입점

로더에 독립적인 DSH Web 시작 복구 기능으로, 손상된 것으로 보이는 플러그인을 감지하여 일시적으로 건너뛰고 Boot Guard가 관리하는 변경 사항만 복원합니다.

Qwen 멀티모달 플러그인 지원입니다.

DSH Web UI용 Steam Workshop 스타일 플러그인 스토어입니다: 커뮤니티 플러그인을 탐색, 검색, 원클릭 설치할 수 있으며 미러 가속, 진행률 UI, 보안 검사, 중국어 설명을 제공합니다.

Claude Code-inspired skin for the DeepSeek Harness web GUI

Local-first long-term companion plugin suite for DeepSeek Harness

Tavily-backed web search for the DeepSeek Harness: rotation-aware tavily_search model tool plus the Tavily Search settings card (keys, usage strategy, usage gauge, on/off switch).

Cherry Studio-style knowledge base system for DeepSeek Harness (DSH): bases, documents, chunking, embeddings (OpenAI-compatible / Ollama / local / lexical fallback), retrieval, model-facing tools, and a browser management panel

Toggle switches for the plugin inventory: enable/disable any plugin live from Settings → Plugins → Plugin list without restarting, with groups/filters, bulk toggle, undo, and backup.

LLM auto-approval for sandbox escalation requests, with presets and a fail-closed fallback.

A starter template for dsh plugins covering config, tools, events, services, hooks, browser UI slots, and slash commands.

Evidence-first guard: warns the agent when it claims success without a matching tool-execution record in recent context.

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

Literary DSH plugin: one session is one book. Cover-card /new opens one of 19 realms, a prose-only 诸天万界DSH preset keeps the model writing fiction, keyword worldbook entries ground each turn, and /export-story typesets the session into a Markdown novel.