플러그인

Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

Local toolbox for the DSH web GUI: 35 pure-client tools (text, encoding, hashing, extraction, conversion, reference tables) in a sidebar view, plus the /toolbox command and config-driven agent tool exposure.

Zero-dependency MCP client bridge that connects stdio and HTTP MCP servers and registers their tools as mcp_<server>_<tool> for the agent.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Human-readable Markdown memory for DeepSeek Harness: user-level (~/.deepseek-harness/MEMORY.md) + workspace-level memory injected every turn, auto daily-log writing with distillation, bridges existing WorkBuddy/CodeBuddy memory dirs, memory_note / memory_note_user / memory_read tools with built-in dedup, and a bilingual settings page. Plain-text storage, no database.

Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.

Adds a Settings Usage dashboard for DeepSeek API balance, official token and cost analysis, trends, context warnings, and live API activity.

**DeepSeek Chat (chat.deepseek.com) same-style attachments**: paperclip upload button, 240×64 DS-style file cards with official colored doc icons (PDF/DOCX/XLSX/PPT/IMG extracted from the DS frontend bundle), drag-and-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message, and real attachment cards rendered in the transcript (custom user renderer) with the model reading full content.

Workspace file tree for the Web UI: multi-tab preview (text/DOCX/PDF/Markdown/CSV/images), inline Markdown editing, a Git changes panel, and file operations (rename/delete/copy/move/create) via context menu.

Right-side prompt toolbox panel with 24 built-in deep templates plus user-defined ones, accessible via the /prompt slash trigger and a context-aware floating suggestion card; one-click inserts the selected prompt into the composer.

DSH 세션과 승인된 Agent Team Room 간의 비동기 LLM 요약 컨텍스트 중계, 즉시 스냅샷과 예약된 요약 제공

읽기 중복 제거가 적용된 증분 파일 마운트: 마운트된 줄 범위는 모델에 다시 전송되지 않으며, 디스크 변경 시 무효화 후 재마운트, Mounted Files 탭과 토큰 절감량 집계 제공

DeepSeek Harness 에이전트 기능을 MCP 서버로 노출해 외부 MCP 클라이언트(예: Hermes)가 Harness를 구동해 코딩 작업을 수행하도록 함. Hermes = 두뇌, Harness = 팔

음성으로 입력하고 음성으로 답변 받기: 받아쓰기 음성이 사용자 메시지로 변환(transcribe)되고, 에이전트가 답변을 소리 내어 읽어줌(speak), ~/.dsh/voice 아래 로컬 우선 저장

md/txt/docx/pdf로부터 감사 가능한 KB 팩(SQLite FTS5)을 구축하며, 결정적 검색과 원문 읽기 지원

Local knowledge base RAG for DeepSeek Harness -- index project files and search for relevant context

Writing tools that remove AI-sounding patterns and match your personal voice. 8 deterministic tools scan text, build a style fingerprint from your samples, and return rewrite briefs.

DeepSeek Harness (dsh) plugin for @tabilo/ai-code-review: registers the ai_code_review tool (review | context) that reuses the Node.js engine to collect diffs, run tests/coverage, do impact analysis, and feed pack skills to the model.

Youdao-style word-selection translation for the DSH web GUI. Select text anywhere, click the floating button, get a translation from the harness's own LLM — no API keys, no third-party endpoints. 有道风格划词翻译：DSH Web GUI 里划选文本即现悬浮「译」按钮，点击由 harness 自带大模型翻译，无需

A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, models.dev prices, context windows, live per-task token cost and a local-model filter. One-command install: dsh plugin add dsh-model-garden.

DSH 智能上下文压缩插件 —— 在有限窗口内管理认知资源，让 Agent 记住真正重要的信息。 Smart context compression for DSH — managing cognitive resources within limited windows, so your Agent remembers what truly matters.

Xiaomi MiMo text-to-speech controls for DeepSeek Harness Web assistant messages