为明日方舟的长篇剧情打造的RAG类DSH插件，拥有多种快速检索能力。

把外部 Agent CLI、持久终端、工作区调试和远程访问，装进 DSH 原生界面。

Durable agent-created automations for DeepSeek Harness

MC 资产面板 + 「MC 模组工作室」模式 + mc-mod / mc-art 两个 skill：3D+物品栏、像素/结构编辑器、出错的报告自动放进输入框、GameTest 判定闭环。原生 Windows 可用（不需要 WSL），不绑定任何具体 mod。

MUV 变量表格编辑器 —— 树形变量面板、宏测试浮窗（random/pick/roll）、骰子快捷栏、pick 缓存管理；支持直接读取 SillyTavern PNG 角色卡（含正则脚本、世界书、变量表）。dsh-muv-engine 的伴生插件

Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.

DeepSeek Harness 原生桌面版，基于 Tauri 2，内置 Node.js 运行时，一键安装，极速启动，托盘常驻，自动更新。DeepSeek Harness native desktop version: built on Tauri 2 with a bundled Node.js runtime.

Bilingual floating DeepSeek Harness pet with live context, lifetime token ledger, trends, opt-in completion sound, and editable Prompt Optimizer enhancement.

Multi-engine web search and evidence synthesis for AI coding agents. Unified MCP server, Pi extension, and DeepSeek Harness bundle — free search, X/Twitter, parallel research, and TUI setup.

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, and sanitized LLM prompt/completion capture from the session/event stream, with async batching, bounded offline buffering, and retry

把已有音视频处理成需要的成品。 需要本机 FFmpeg / ffprobe 欢迎提交 issues 和 PR。

DSH 原生 MUV 引擎 —— 正则脚本、状态栏级联（任意字段/行动选项）、变量追踪、LaTeX、宏展开、标签 CSS、visual 代码块渲染（信纸/终端/报纸/手机），内置 diag.mjs 诊断工具。需与伴生插件 dsh-muv-table 一起安装

Text-to-speech for DeepSeek Harness: speak agent replies in the Web UI with a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak).

Local document knowledge base for DeepSeek Harness: library_add/remove/list, hybrid semantic+keyword library_search with diversity re-ranking, relevance filtering and lost-in-the-middle avoidance, citation-aware injection, library_cite_check and library_d

WeChat channel for DeepSeek Harness

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

Model router for DeepSeek Harness: keep a pool of models and every step is routed to one of them with its reasoning effort set — a click-only composer panel, three authorization scopes (a manual pick only counts in the scope that owns it, and effort scope

Use a Kimi Code membership in DeepSeek Harness through a dedicated Kimi subscription model route

DeepSeek Harness 智能看板：任务卡片 + 一次性 Worker/Verifier 派发 + 依赖调度 + 管线分档 + Team 模式（歧义上报主窗口裁决）

Your coding agents remember what you decided — and what you changed. Plain-Markdown memory in Obsidian, shared by Claude Code, Codex and Cursor over MCP. Every answer cites its page; when the vault does not know, it says so. Imports your past sessions on install.

Persistent project memory for dsh agents: index docs (PDF/Markdown/text) and code symbols into a searchable per-workspace store, recall them with cited sources, and keep experience entries (problems -> solutions) searchable on demand.

DSH Web 运维面板：安全重启、健康监控、备份和 Linux 权限维护。

Gives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis