Plugins

One DSH tool that runs a command on any execution surface the machine has -- WSL, MSYS2, Git Bash, PowerShell, nushell, interpreters, throwaway containers, ssh, real terminal windows and a real console -- and reports the version each one gives and the capabilities it has.

Wraps the separately installed agent-desktop CLI (`npm i -g agent-desktop`) as nine DSH tools (ad_status, ad_list_windows, ad_snapshot, ad_find, ad_click, ad_type, ad_press, ad_launch, ad_close_app) so an agent can list windows, read an accessibility tree, click a snapshot ref, type text, send keys, launch an app and close it gracefully. The plugin adds no automation logic of its own: it validates arguments, calls the CLI and returns the parsed JSON envelope, and asks the caller to take a fresh snapshot instead of retrying a stale ref, so a click never lands on a shifted target.

macOS computer use with eight computer_* tools: accessibility-tree and Vision OCR screen reading, actions by element index or visible label that also reach background windows, and CoreGraphics mouse and keyboard events with a resident low-latency daemon for game-grade input sequences; its Swift helpers compile on first use, so there is no runtime dependency.

Embeds a private local Sub2API gateway (Sub2API + PostgreSQL + Redis via Docker) into the DeepSeek Harness sidebar with automatic local login. Windows only, with Docker Desktop and its WSL2 backend already installed; the first start pulls about 250 MB of images and needs local ports 18080 and 18081 free.

Mirrors an Android phone screen to a Windows PC over USB or Wi-Fi with scrcpy, and exposes start, stop, status, connect (reconnect after a phone reboot) and screenshot as an agent tool and a /mirror command. Requires scrcpy and adb installed on the host (winget install Genymobile.scrcpy); the plugin does not bundle them.

Record lecture audio in a phone browser and transcribe it locally with faster-whisper; generates summaries, mind maps and quizzes with a wrong-question gate plus a focus report, and serves the phone UI over a built-in HTTPS tunnel from any network. Transcription needs local Python, ffmpeg and faster-whisper (the setup script installs them plus a ~460 MB Whisper small model); the public HTTPS tunnel uses a Windows cloudflared build and has no access code by default, so anyone with the link can open it.

Persistent Codex advisor threads for DSH sessions, with six native tools, a Codex trail, a sidebar status card, and explicit model/effort provenance. Requires a locally installed Codex CLI with app-server support and a logged-in ChatGPT/Codex account (the CLI is not bundled); tested on Windows 11 with DSH Desktop 0.2.1-rc.5.

Installs and opens PM Workbench, a local Electron multi-role project workbench, from a DSH tool. Windows only: the first load bootstraps Node, Electron and the app through a PowerShell installer. It does not embed the workbench UI in DSH.

Cross-session long-term memory for DSH: eight memory layers, four notebooks, hybrid SQLite FTS5/vector/graph retrieval, agent-driven automatic capture, write lifecycle hooks, optional write audit, project spaces, forgetting and a visual management page. Full FTS5/vector/graph retrieval needs the bundled Go service, which ships only as a Windows x64 prebuilt; on macOS/Linux, build it from source or the plugin falls back to Node SQLite without FTS5 and retrieval degrades.

Caps how many DeepSeek Harness conversations run at once, so extra conversations wait in a FIFO queue instead of piling up model requests. On Windows a bottom status strip shows physical memory, commit memory and disk usage; on other platforms only the queue and physical memory are reported. A plugins-page card changes the limit.

Deletes a whole workspace together with its conversations in one pass - session logs, projection caches and workspace registrations - and optionally sends the workspace folder to the Windows Recycle Bin (on other platforms deletions are permanent).

Declares two model routes in the llm-pi-ai settings section — a TLPro gateway and Z.ai's GLM-5.3 endpoint — with per-model context windows, output caps and reasoning-effort ladders, so the stock model picker can select and tune them. Requires your own TLPRO_API_KEY and a Z.ai coding-plan ZAI_API_KEY; the patch replaces the whole llm-pi-ai row config.

One collapsible sidebar widget stacking OpenCode GO, Command Code and GLM Code Plan quota windows, with reset countdowns, top-up balances, a settings page and a /provider-usage command.

Sticky-note wall in the sidebar with pasted images and text, due reminders, done state, shortcuts, a pin-on-top floating window, appearance skins, and a native always-on-top Windows desktop window.

Adds a pin button to the left of the Windows caption buttons that keeps the DSH window always on top of the desktop.

Window close behaviour for DeepSeek Harness Desktop — ask, minimise to tray, or quit, with a remembered choice editable in Settings, plus per-session and per-workspace child windows. Windows only: requires DSH Desktop 0.2.1-rc.5+ and a PowerShell installer that patches the app shell (resources/app); re-run it after every DSH upgrade, otherwise closing keeps DSH default behaviour.

Adds a restart button to the Windows desktop app title bar and replaces the cold-start "loading settings" overlay with an animated boot sequence.

DSH Harness plugin: keep preset skill directories and link their skills into the user skill root (directory junction on Windows, symlink elsewhere).

A desktop pet for DSH: a blue whale girl with 104 animations and built-in voice. It is standalone, but its pet runtime is a rework of dsh-dafeiyu — disable the upstream dsh-dafeiyu before installing, or both will run and fight over the control port. Windows x64 only, and the first launch downloads about 580 MB of assets.

DSH host bundle for the ShyPie privacy-first workflow: extracts attached images and PDF/Office files locally before they enter the session log (requires poppler pdftotext/pdftoppm on PATH and a local OCR engine — Windows OCR on Windows, optionally tesseract; without them attachments are rejected, not forwarded); default filter mode keeps text local (optional local masking); blocks unmaskable media/BLOB; provides local privacy_extract, privacy_ocr, privacy_scan and privacy_rehydrate tools; denies read_image and binary/document reads outside allowPaths; and enforces a fail-closed llm/stream egress guard before DSH dispatches a model request (the default provider allowlist is the local Magpie gateway).

Blinks the Windows notification-area icon the way QQ and WeChat do for an unread message — the app's own icon alternating with a fully transparent frame — and flashes the taskbar button, when a turn finishes or a session waits for an approval or an answer.

Video study toolkit for DeepSeek Harness: fetch a public Bilibili single part or YouTube video, sample every 3 seconds plus change-triggered frames, transcribe locally with faster-whisper, page through section grids, and render a 16:9 study deck. Windows only, and needs the DSH pwsh tool plus Python 3.12 x64 with Pillow and FFmpeg/FFprobe; fetching adds yt-dlp, transcription needs faster-whisper with your own local model files, and deck output needs python-pptx.

Windows-only sidebar panel that watches the CPU and IO of your AI desktop apps' process trees and shuts the machine down once all of them have been idle for a configurable time, with a cancellable countdown, a dry-run mode and an activity log; requires Python 3.10+.