Plugins

One-click Concise output style for DeepSeek Harness: results first, no filler, same work depth. Every final reply opens with a plain-language digest card (select text to copy), scoped per session, working in headless/CLI too, with /concise command, style.md overrides and a local API. Links and file paths inside the digest card render as clickable chips: URLs jump, local files open with the OS default app (v0.9+). A per-step pre-generation contract reminder (v0.11.2+) measurably fixes digest misses on audit-report/table-shaped replies.

Generic workspace base for the dsh harness (local + remote workspace providers with per-workspace routing), with SSH as one concrete provider: bind a server directory as an SSH workspace so the session's file I/O and commands run on that host, manage host

Genshin Impact Yoimiya theme: two hand-tuned palettes, a procedural fireworks particle layer, and a local music player that reads your own files — songs and covers are never uploaded. Warm syntax colors and a hand-drawn goldfish brand mark; apart from the wallpaper every pixel is CSS gradients and hand-written SVG.

Connects DeepSeek Harness to a local SiYuan (思源笔记) desktop app: registers its note tools as mcp__siyuan__<tool>, exposes the AI configured in SiYuan together with its agent loop as one more tool, ships a notes skill, and enforces a readonly/authoring/full profile on every call while keeping the tool list available when the app is closed.

Cross-session TODO board as a draggable floating panel: tasks are grouped by working directory and reorderable by drag, each one carries a run mode (remind only, continue in the current session, or open a new session in the same directory), up to four attached images sent to the model as real image attachments, and an optional local time it may run at; two checkboxes track AI-done and user-verified, and the agent picks up the next unfinished task in that directory when it finishes one.

Bridges a local MATLAB MCP server into DSH: evaluate MATLAB code, run .m scripts and tests, and inspect installed toolboxes via mcp__matlab__* tools. Requires MATLAB and the MathWorks MATLAB MCP Server binary, and a path edit after install — the plugin on its own registers no tools.

Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide provider/* rule (both stack in order). A Settings page lists every configured provider and its models for per-route editing with instant effect, and rules persist to DSH_HOME so they survive restarts. Applies to main sessions, subagents, and workflow children alike.

Self-tending living memory in one local SQLite file — a nightly patrol dedupes, merges, decays and cross-links entries on its own, with seven-signal RRF hybrid recall (FTS5 + jieba Chinese-first tokenization, optional vector KNN, graph PPR), a typed knowledge graph, conflict detection instead of silent overwrites, and web telemetry panels.

Adobe Lightroom Classic as native dsh tools through the lightroom-py MCP server: read the catalog, apply develop settings and presets, export JPEG/TIFF/PSD/DNG, and write ratings, labels, keywords and IPTC — 15 tools driving the Lightroom Classic installed on the local machine, no cloud round-trip; the Python package is on PyPI and the Lightroom plugin installs with one command.

Voice assistant for dsh web: say the wake phrase (e.g. "小鲸") to activate hands-free dictation — what you say is transcribed and typed into the chat box automatically. Supports spoken edit commands (send, clear, new line, stop reading) and reads assistant replies aloud in Chinese. Speech recognition runs locally in-browser via sherpa-onnx WASM, so it works offline without an API key.

Fully local vector memory for DSH: local embeddings, SQLite storage, automatic recall injection, dedup with conflict detection, soft-delete recycle bin, online backup, and optional LLM extraction.

Three-layer local memory for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md) read on demand through the memory_* tools + L2 searchable knowledge base (facts + SQLite FTS5, Chinese search via sliding-window tokenization) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and from approved Agent Hub documents (memory/global, memory/projects, accepted decisions) with content-hash dedup. v0.2.0 removed every automatic injection: memory enters the context only when the model calls one of the 12 memory_* tools, and data stays on the local drive.

Hand a DSH web session to the locally installed Claude Code CLI: a per-session engine selector (DSH | Claude Code), Claude models and reasoning effort in the model seat, Claude permission modes in place of the access-mode selector, and permission requests, AskUserQuestion and ExitPlanMode routed to the native DSH approval, question and plan-review cards. The stream is written as native DSH session events, so the built-in transcript, tool cards and nested subagents render it; Claude slash commands merge into the command palette; the CLI is held by a detached broker, so plugin updates and DSH restarts do not interrupt a running turn.

Runs AItelier pipelines from DSH over MCP: 39 tools (22 read, 17 write) to generate, run, inspect, edit, export and import multi-step SkillFlow pipelines. The steps execute in AItelier rather than in the DSH session and are polled by run_id, pause at engine-enforced checkpoints answered with answer_checkpoint, and leave per-step traces and step outputs to read afterwards; add_provider / map_model / edit_role point an individual role at a local or cheaper endpoint. Bundles an aitelier-pipelines skill.

Local cross-session messaging for DSH agents, with discovery, cold-session wake-up delivery, and auditable message history.

Local long-term schedule panel: top-bar "日程" text button, today/week/history month-calendar views with stats, completion checkmarks with per-day history, schedule↔conversation links with click-to-jump, recurring tasks (daily/weekly), optional auto carry-over for unfinished one-time tasks, and dailytask_* agent tools.

FormatForge for DeepSeek Harness: forge any file format (pdf/docx/xlsx/pptx/eml/toml/...) into AI-readable structured data. Thin bundle that spawns the local Python CLI (python -m formatforge) and returns protocol JSON; enhancement is delegated to the cur

Instance manager for DSH Web: a Mini Utility Dock panel that lists every local dsh web instance the machine can see (port, PID, uptime, live session count, resident memory, version), starts a new instance on an automatically picked free port in 3080-3129 or on a port you name, opens a row in a new tab, and stops one or all of them through that instance’s own graceful shutdown (appExit). Rows also show what each instance is serving, and read-only instance logs and session summaries are one click away. Where a peer is configured, the same panel lists and queries instances on other machines over a bearer-authenticated link. Every route is loopback-guarded, and a browser-facing action must additionally pass the host’s own browser authentication.

Adds 20 locales (Traditional Chinese HK/TW, Japanese, Korean, French, German, Spanish, Portuguese, Italian, Russian, Ukrainian, Polish, Dutch, Turkish, Arabic, Hindi, Indonesian, Vietnamese, Thai, Swedish) to the DeepSeek Harness Web UI, with hand-polished translations, runtime fallbacks, and automatic translation of market and third-party text.

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

Visual development studio for DSH WebUI plugins with isolated Git worktrees, live official-WebUI previews, source editing, patch inspection, builds, and validation.

Sidebar panel for account balances and local token usage, with provider/model breakdowns and a 27-week daily heatmap.

Local image, voice, music and SFX generation plus transcription, with pinned identity: characters, animals, objects and actor voices are defined once and reused on every later call, degenerate output (a near-flat image, silent audio) is rejected instead of returned as success, and a generated line can be read back as text so a clone that swallowed its ending becomes visible. The engines unload when idle, and image generation and transcription can each be pointed at an OpenAI-shaped API instead of the local Vulkan backend.