Plugins

ROS2 debugging toolset and robot-state vision analysis for DeepSeek Harness: node/topic/service/action/interface/TF enumeration, whole-graph topology JSON, rosdep checks, approval-gated builds and custom message scaffolding, GUI screenshots and multimodal vision observation, plus headless RViz2 offscreen rendering (low-poly meshes, direct pixel read, GPU passthrough - motion rendering at 30Hz) with parallel VLM realtime analysis.

MCP server manager for DeepSeek Harness: add, edit, enable/disable, restart and delete MCP servers from Settings → MCP 管理, with JSON export/import, four mcp_manager_* model tools and an HTTP API; install via npx, npm or cross-platform scripts.

MCP bridge that lets ChatGPT Web create, view, continue, and supervise DeepSeek Harness agent sessions and goals while preserving DSH's native approval, sandbox, and workspace security model.

Image generation and image reading for DSH: an Images page in the sidebar, labelled 图像 in Chinese (one row per model, 10 ratios, 1K–4K sizes, a contact sheet with detail cards, zoom, reuse and delete), three preset providers plus custom endpoints — one needs no key at all — and a vision-review skill. A pasted key is written to ~/.dsh/secrets/media-tools.env (mode 600) and only sent to the provider you picked. The page follows the harness language (Chinese or English). Requires Python 3.9+ (generation runs through scripts/generate.py); the page needs desktop DSH 0.2.1+.

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

DeepSeek Harness Cordis tools for All in Flash, powered by All in Luna

Design-aesthetics skill pack (10 styles: dark SaaS, minimal white, neumorphism, brutalism, glassmorphism, Japanese minimal, bento grid, cyberpunk, vaporwave, art deco) with runnable landing-page demos: tokens, component rules, forbidden lists, and acceptance checklists per style.

Steam Workshop-style in-app plugin browser: search, hot/newest/trending (7/30/90-day) sorting, Chinese keyword mapping, bilingual descriptions and README translation, plugin-signature filtering, and one-click install/update.

Watch a video together with a text-only agent: with ffmpeg and the bundled browser extension reporting your real playback position (not a timer), it hands over one segment at a time just before that segment ends. It ships no TTS engine — it emits timed speech events, and speaking them aloud needs your own voice/TTS setup.

给 DeepSeek Harness 的跨会话记忆：按工作区隔离、跨会话共享的长期记忆。常驻 prompt 的只有浅层要点，长文用段级引索定位到段、只取那一段，深层原文（当时的思考、命令、结论）留在本地向量库里按需取回。检索自带噪音过滤与时间通道，零联网（本地嵌入模型），不改动官方内核。

Evolving memory infrastructure for DSH — evidence, time, context, and correction for long-term continuity — backed by a local Python 3.11+ memory service (fastapi/uvicorn/pydantic, started automatically as a python3 subprocess).

A long-term memory plugin for DeepSeek Harness. Every turn is judged and stored into a local SQLite (utterance / event / version / stage / decision), with a browsable panel.

Douyin assistant plugin: picks a daily round of videos, reads comments, writes a dated report, can like and comment with an @ mention (both off by default), and publishes clips rendered by your own ComfyUI. Windows only; needs Python 3 and a system Chrome, and the first run needs the install-main-dependencies step plus a QR-code login.

DSH SlideStudio — AI presentations with editable PPTX export for DeepSeek Harness

Live2D 桌宠插件：为 DSH Web GUI 挂一只可拖动、会跟随鼠标、能换动作与表情的 Live2D 宠物。

Mobile web shell for the DSH Web GUI: overlay drawers, draggable FAB, mobile composer fixes, and a floating image-upload button pinned above the composer (native gallery/camera, integrated with the validated add-images pipeline), zero desktop regression. Published on npm as dsh-webui-mobile.

A read-only mirror for installed DeepSeek Harness plugins: capability inventory with evidence, cross-plugin conflicts, and a diff of what changed since the last scan

Provider-independent DSH document parsing powered by MinerU, with native background jobs, immutable results, and safe request coalescing.

Input experience enhancement: voice input, AI polish, anti-overwrite, prompt optimization with diff preview, and auto locale switching following DSH UI language.

VSCode-style editing experience for DeepSeek Harness: a Monaco-based central file editor (tabs, Ctrl+P quick open, status bar) and interactive diff review of agent edit/write results with per-change Keep/Undo, rollback and archiving, persisted across restarts.

Role-play conversations with character cards, in-chat character-card authoring and editing, and image generation through configurable backends.

Ollama provider for DeepSeek Harness with model management, health checks, rule-based local routing, and cloud fallback.

Windows desktop computer-use tools (click, type, key, screenshot) with freshness checks, approval gating, process-identity verification around every action, and a sanitized audit trail.

DeepSeek Harness bundle registering one skill that turns long-form production (academic papers, industry analysis, business commentary) into a 9-role pipeline: T1 literature / T2 data / T3 case scouts running in parallel, T4 analyst, T5 writer, T6 critical companion, T7 auditor, T8 finalizer run by the coordinator, T9 peer reviewer — across 6 phases with triangular evidence verification, a 26-check M-gate (25 scripted checks plus one human checkpoint), a G0-G16 audit including a Chinese AI-trace gate, peer-review scoring with journal matching, and 4 human checkpoints. Installs with `dsh plugin add lunheng-article-pipeline` (package.json#dsh.bundle.patch plus a lib/index.js entry that registers the skill); ships role cards for T1-T9, templates and 36 zero-dependency verification scripts, with five-language READMEs.