Plugins

Injects PowerPoint entrance animations and slide transitions into existing .pptx files by writing the OOXML timing tree (p:timing), which python-pptx does not implement. Requires Python 3 with python-pptx installed (the plugin auto-detects python / python3 / py).

Adds a global document-routing prompt so PDFs, images, and Office files are read with the right tool.

Reads images with a vision model on the same provider when the selected model cannot see them, and passes that description to the text model.

Read a video with a text-only model: with ffmpeg installed, sample frames at a 0.1-10 second interval into contact sheets where every frame carries its real timecode, extract the audio track and send it to iTingnao (needs an ITINGNAO_API_KEY) for a timestamped transcript, and describe each sheet with an image-capable model in the host, so the plugin works on its own without any other vision plugin. A composer slider sets the sampling interval, and pure audio files are transcribed without frame sampling.

Infinite canvas workspace in the DSH sidebar — arrange text, image, video and audio nodes, generate media with AI, and let agents drive every canvas operation through MCP tools. Ships a local bridge service, ready to use offline after install.

Local document library for DSH Desktop (Windows only, installed with the bundled PowerShell script): upload files once, then every conversation can search and read them through four tools (library_list / library_search / library_read / library_save); upload, download and batch download live in the Settings panel. Files stay on the machine unless you enable the optional vision model, which sends images to the endpoint you configure.

Codebase knowledge graphs for DeepSeek Harness: seven graphify_* Agent tools, a /graphify command, and a Graphify page build and query a project graph locally with AST parsing (no API key), plus path/explain/god-node lookups and wiki/HTML/SVG/GraphML/Obsidian exports. Requires the graphify CLI (graphifyy); only full document/PDF/image extraction needs an LLM key.

Reads the local NTQQ (QQ 9.9.x) message database on Windows and Linux and exports group and private chat history to txt, csv, json, md, html or sqlite. Ships sixteen model tools: qqnt_status and qqnt_doctor for environment and blocker checks, qqnt_extract_key, qqnt_index to build or inspect the sidecar index, qqnt_list_groups, qqnt_list_chats, qqnt_search, qqnt_stats for totals and monthly counts, qqnt_export_group, qqnt_export_chat and qqnt_export_batch (a chat can be named the way the user says it, and ambiguity refuses instead of guessing), qqnt_jobs for OCR, speech-to-text, chunking and model downloads, qqnt_media for a chat's downloaded images, qqnt_storage for disk usage and allow-listed cleanup, and qqnt_ask plus qqnt_recall for retrieval with citations. The local web UI on 127.0.0.1:46728 adds an incremental SQLite index, six views (chats, export, statistics, ask, settings, models), a task panel, a single-pane layout on narrow screens, sender redaction, media bundling, per-day splitting, export presets and AES-256 password ZIPs; OCR, speech and embedding components install into the plugin's own virtualenv on demand. Needs python3 with sqlcipher3 (the settings page can create a private virtualenv), and the database key is read from the running, logged-in QQ client.

Moss text-to-image inside DSH — describe the picture in chat and get it back; needs a Moss API key from platform.moss.cn, and generation is billed to your own account.

Trim tools for long chats: trim_context / estimate_context_tokens keep the system persona and the last message, drop the oldest user/assistant pairs to fit a turn or token budget, and report before/after estimates; the conversation is not trimmed unless something calls the tools.

One-off two-person password chat in the DeepSeek Harness right sidebar: end-to-end encrypted (the server sees ciphertext only), with images and screenshots, fully cleared on end.

Six material skins for the DSH Web GUI — Ink Jade, Terracotta, Aurora, Abyss, Sakura Mist and Paper — painted with CSS only: one engine derives the 119 --dsw-* alias tokens from six colour inputs per appearance, Alt+K cycles skins, and the choice is remembered in localStorage. No images, no host route.

One install for a whale-girl boot animation, a cyber code-eye video background and a holographic dark theme. The skin and background video (CC BY-NC-SA) are downloaded from the upstream repo on first launch; the boot animation is only installed when @ljwei-stak/dsh-boot-animation is already present.

Adds a cost-and-balance chip to the composer stats row beside the shipped token-usage pill — the session's estimated DeepSeek cost, a peak/off-peak light and the signed-in account's remaining balance, with each billing item priced in the breakdown; it activates only when a DeepSeek official route is present.

Full-screen boot animation for DeepSeek Harness: a wave sweeps the screen, a whale assembles from particles inside three breathing dot rings, and a four-language salute lands over a segmented progress bar; ships an 18-second cut and 3.8-4.5-second short cuts, a language picker in settings, and a four-language preview queue.

A right-sidebar gallery of every image and video in your workspace, newest first, with thumbnails, type filters, search, and a lightbox.

A Windows pixel Madara desktop companion with 16 animation clips driven by Harness task events, using the original BigFish runtime dependency.

Long-term memory backed by a local SQLite store: project-scoped memory auto-injection with junk filtering, rule-based or model-assisted memory extraction from recent turns, write-side dedup and feedback-weighted ranking. The Python bridge runs on $NEXUS_PYTHON or the DSH-bundled interpreter at <DSH home>/dsh-runtimes/dsh-primary-runtime/dependencies/python/ (Python 3.8+).

A Madara pixel theme with dark crimson colors, Chinese pixel fonts, and a skippable Sharingan startup animation.

Shows per-answer and conversation cost estimates from recorded token usage, with automatic model pricing updates and detailed price-source breakdowns.

RGB lighting effects for DeepSeek Harness: animated composer ring, sidebar rail, session indicator, and glowing brand logo.

A fork of dsh-boot-animation that plays an intro clip when DSH opens, ships four embedded clips with an in-app library, and adds batch deletion for clips you added yourself. It reuses the same plugin id as upstream, so the two cannot be installed together.

An animated macOS desktop companion for DeepSeek Harness that follows work across chats, reacts to approvals and errors, takes snack breaks during long runs and naps when idle. Requires a separate shell app.

An animated pixel cat that lives over the DSH web interface and follows what the agent is doing — sitting while the session is calm, lying down and falling asleep while a run is in progress, and waking when the turn returns or typing starts. It can be dragged anywhere, remembers its position, sleeps after a minute of inactivity, and offers an enable switch, four sizes and a status-reaction toggle in Settings.