Plugins

Cross-session messaging for DSH: any session on the machine can list and message any other, Claude Code-style, via a local heartbeat registry and inbox.

Side web-preview panel: local static hosting, Markdown/code/image preview, one-click run of non-static projects (Cargo/npm/Go/Python) with live logs, drag files into the chat (saved to the workspace), element mark & annotate, workspace file search on 404, and link-click takeover into the side panel.

Long-term memory for dsh via a local Hindsight service: each turn is retained with local timestamps and relevant memories (time-aware, reranked) are recalled into context before replies; each workspace binds to one memory bank, several workspaces can share a bank, and banks can have Chinese names; what gets retained is configurable (default: user messages and AI replies); history is imported only when you choose to; includes a three-step setup page with one-click local deployment (uv + Python 3.12), a sidebar status card and a panel to browse and search memories. Needs a SiliconFlow API key for the default embedding and reranker models; only Linux is verified so far.

Builds presentations by driving the LibreOffice installed on the machine over UNO instead of writing OOXML in JavaScript: `lo_build` opens a real Impress document from structured slides and lets LibreOffice export editable PPTX/ODP plus PDF and per-slide PNG, `lo_render` re-renders an existing PPTX/PPT/ODP, `lo_convert` converts between Office formats, `lo_probe` reports the detected soffice path, version and UNO bridge, and `lo_config` edits the stored settings. Needs a local LibreOffice (verified on 26.8.1.1); it uses the bundled Python, so no system Python is needed, and it keeps one warm soffice process between calls. Fully verified on Windows only; on Linux it falls back to the system python3, which needs python3-uno.

DSH remote-development local plugin: host registry, SSH tunnels, remote workspace/session discovery, an authenticated Connection RPC surface, agent tools, and a Settings page.

H.D.D skin for the DSH Web UI: full-screen boot animation, an animated eye core with idle, thinking and done states, a time-of-day greeting, and optional local GPT-SoVITS voice.

Design workbench in the right sidebar. When the model builds web pages, app screens, posters, slides or emails, each HTML file shows up as a screen on a canvas inside a device frame and refreshes when the file changes; local dev servers are proxied with hot reload intact. Click an element or drag a region to put its selector, source file and styles into the composer. Also has a design tokens panel, versions saved before and after each turn with drag-to-compare and restore, image export, a LAN QR link for viewing on a phone, link arrows and a click-through demo mode, a multi-size view, in-place text editing, reference-image palettes, and a bundled ui-design skill plus a preview_page tool. Adds a Design mode for new sessions (Standard mode's tools plus the skill, the preview tool and a design persona); the studio, automatic previews, the tool and skill in other modes, and the Design mode each have their own switch on the Plugins page.

Long-term memory for DSH stored as plain Markdown. Real user/assistant exchanges are captured into daily session files without a model call; an LLM pass then distils them into memories that are injected into the system prompt each turn. Retrieval is local (CJK bigram + BM25) in three levels — index, summary, full text — so the model only pays for the detail it asks for. Memories carry priorities; P0 and user-written entries are never changed automatically, and forgetting marks an entry stale instead of deleting it, so the whole chain stays auditable in status.md. Six tools cover recall, write, status, extract, feedback and the skill library; when a cluster of memories is ready to become a skill, a card appears at the end of the turn, writes the SKILL.md on click, and installs it only after you approve. Learning is on by default and follows the conversation model; turning the master switch off stops the LLM entirely while capture keeps working. Failures are surfaced in the prompt and in status.md instead of being swallowed. Pure JavaScript, no third-party runtime dependencies beyond the harness packages.

Local Git plus the four GitHub remote tabs in the official DSH right sidebar: Changes (per-file staging, line diffs, and commit messages written by the model already configured in DSH), History, then Code, Issues, Pull requests and Actions proxied by the host half. The token stays in the host half through ctx.credentials and /dsh-git/* accepts loopback requests only.

Plugin that turns a XiaoAI (Xiaomi) smart speaker into a voice assistant: hosts the local bridge process, listens for the wake word, runs speech recognition (ASR / STT) on what you say, keeps the conversation in the host session, and speaks the answer back through the speaker with text-to-speech (TTS) playback.

Academic tools in TypeScript, no Python or MCP server: the Zotero library through its local API or zotero.org (search, annotations, full text, citation export; add by DOI / arXiv id, notes and tags when writing is turned on), starting Zotero when it is closed; paper search across arXiv, OpenAlex, Crossref, Semantic Scholar, PubMed and Europe PMC, plus CNKI and Google Scholar through a browser window; open-access full text, citations from the DOI registry, reference checking; 11 bundled skills.

Generate images from the agent on the user's own GPU by queueing a workflow on a local ComfyUI install over its HTTP API: Z-Image-Turbo for fast drafts and Qwen-Image-2.1 for final assets and legible in-image text. Registers comfyui_generate and comfyui_status plus a skill covering model selection and prompt craft, has no runtime dependencies, and starts ComfyUI headless when no server is listening.

Custom branding for the shared DSH Web UI: a Settings → Branding panel for the name, badge, and local logo/wordmark images with size and rounding, live preview, optional page-title brand, and reset to the official look.

Turns a local Obsidian vault into a dedicated RAG chat panel: a sidebar page with the note browser, the retrieval-augmented chat and the cited source side by side, answering from fully local BM25 plus CJK-bigram retrieval over your notes and streaming through the DSH model channel, with clickable \[n] citations and mtime-based incremental indexing.

Takes over the compaction threshold on every mounted engine: forces headroomTokens to -1e6 so the ratio is the only term in the trigger, keeps retention below it on every write path, reroutes the compaction call to a chosen model, and adds a panel with a one-click compaction button and a per-session compaction log.

DeepSeek Harness × Feishu/Lark bridge: chat, cards, approvals, task board, goals and schedules in Feishu — plus fully local (offline) voice transcription with a play bar in the Web GUI.

Mirror dsh session events to MySQL, PostgreSQL, SQLite, or SQL Server while retaining local session files.

Bidi-safe RTL rendering for mixed Arabic and English text, a full Arabic interface pack (3,307 strings) registered through the DSH locale service, and three thmanyah cuts — Sans for the interface, Serif Text for reading, Serif Display for headings — placed behind whatever font the app itself is set to.

Checks in Trae and WorkBuddy daily from local login files, with a sidebar status and credits panel.

Two-way Telegram remote cockpit for DeepSeek Harness: live progress tracking, screenshot vision, git diffs, shell execution, and tool approvals. Unconfigured chatId automatically claims the first sender as owner; voice-to-text requires local ffmpeg and BeeRouter services.

Agent-structured prompt optimizer for DeepSeek Harness: rewrites composer drafts into role/task/context/constraint/format with normal, slim, and expand modes, a confirm modal with score, continue-optimize, and local, hybrid, DSH, or cloud-API engines.

SQLX database tools: list saved datasources, show or test a connection, execute SQL and open a local result page, with the sqlx CLI installed on first use.

Cron job board: schedules local scripts or dsh session tasks (fresh or pinned sessions) by cron expression, with centralized environment-variable management, run logs, and concurrency and timeout control.

One-handed, keyboard-free input for the composer: press and hold the mouse on the input box, speak, release — the text lands in the draft, and sliding up cancels without leaving a half sentence behind. No mic button to aim at and no shortcut to remember; the hand never has to leave the input area, which is the point when the other hand is busy. Recognition runs fully offline (SenseVoice via sherpa-onnx, no API key, audio never leaves the machine).