Plugins

Reads a Windows app's window list, UI text and single-window pixels without screen capture, focus stealing or cursor movement.

Drive a real Chrome and bundle the DOM, accessibility tree, HAR with response bodies, console logs, storage, screenshots, PDF and screencast into one self-contained evidence folder.

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.

Windows desktop control for DeepSeek Harness: accessibility-tree snapshots, click by control name, delivery verdicts, and repeatable task files.

macOS Computer Use for DeepSeek Harness: the agent reads accessibility trees, captures screenshots and drives real desktop apps, mounted on the 0.2.1-rc.5 line with a separately built native helper. macOS only.

Drive a real Android phone from DSH: screenshots, taps, swipes, typing and app launching. Requires Python 3.10+ with aiohttp and mcp on the computer side, plus the AutoX.js script running on the phone with screen-capture and accessibility permissions; the phone long-polls your machine, so no public port and no relay server.

Computer Use for every DSH session: screen capture, mouse and keyboard, app launch, plan and skill replay, an audit log, guards for dangerous actions, a background code agent, and an OCR workflow (text and coordinates) for apps whose accessibility tree is empty. Verified on macOS only: Windows has a basic GUI backend that is unverified, Linux has no desktop backend (calls fail with unsupported_platform), and the window/AX/browser/clipboard tools register on macOS only.

Ctrl + wheel page zoom for the DeepSeek Harness Web UI.

Control the user's own Chrome (or Edge/Brave/Vivaldi/Opera) from DeepSeek Harness by reusing the OpenAI Codex `chrome` plugin's browser runtime: tabs, logged-in sessions, accessibility trees, screenshots and input, exposed as native DSH MCP tools plus a b

Drives the DSH right-sidebar built-in browser from the agent side with 38 tools (open, navigate, read page text and interactive elements, accessibility tree, click, fill, select, check, key press, scroll, resize the browser frame by dragging its corner, with the page inside reflowing responsively so a narrowed frame shows the mobile layout, screenshot, full-page screenshot, PDF, markdown export, scrape to JSON, download, cookies, per-step operation records with replay and action whitelisting), serves the built-in web_search from a self-hosted SearXNG over an SSH tunnel with Tavily and a real-browser fallback, and registers a fetch provider that retries blocked GitHub URLs through measured mirrors and sniffs charset from the response header so GBK and GB2312 pages decode correctly.

Reads assistant replies aloud with Microsoft Edge neural voices and highlights the sentence being spoken, so you can follow along while listening. The highlight is yours to style: background colour, text colour and opacity are each adjustable in settings. Also adds a sound-wave play button to every reply, pause plus previous and next sentence, adjustable speed, and an auto-read toggle.

Requires macOS and AirPods with head tracking. Answer DSH permission prompts and questions with AirPods head gestures — nod to allow or confirm, shake to reject or shift the selected option — and install the companion macOS menu-bar app from a card inside the session.

Installs the codex-cua skill so DeepSeek Harness can use Codex computer use: drives Chrome and native macOS apps through the runtime bundled with the ChatGPT/Codex desktop app, ships a persistent session client and a doctor self-check. Requires the ChatGPT/Codex desktop app with its Chrome extension, Python 3.9+, and macOS.

Bridges the Cua Driver MCP server into DSH: installs the cua-driver executable when it is missing, starts it over stdio through the in-box MCP client, and registers its 60 accessibility-first window, input, menu, and browser tools with a bundled workflow skill and one-time macOS permission guidance.

Ctrl+wheel page zoom (60–180%, remembered) for the whole DSH UI, plus a bottom-right Settings entry that opens the host settings panel, with Ctrl+0 to reset.

Windows desktop control with window-bound screenshots and accessibility state, text readback, DSH approvals, and activity overlays.

个人解决经验记忆：保存问题、做法、来源和适用条件，下次相似任务可检索复用，并支持纠正与删除。搭配 dsh-bubble 提问、dsh-look 提供现场上下文。

Adds a UI effects page to Settings that switches off DSH Web animations and transitions, loading and progress animations, backdrop blur, smooth scrolling, hover title scroll, shadows, gradients and JS motion one category at a time, to cut browser rendering cost.

A headless-first macOS Computer Use driver for DeepSeek Harness with AX-first observations, window-bound multimodal evidence, host-owned approval, and evidence-backed action receipts

Scene-awareness probe for DSH on macOS: a privacy-first, pull-model `look` tool that reads the frontmost non-self window (app info, AX title/selection, gated local OCR), plus a summon-hotkey snapshot captured the instant you press.

Personal-experience memory for DSH: turns solved tasks into sourced problem cases with condition-scoped claims, recalls them into new tasks via hidden pre-step injection, and makes corrections/deletes cascade to future recall.

Speaks a short status line when DSH changes state — turn done, turn error, job done, job failed, goal complete, goal blocked, an approval waiting, or the agent needs your answer — using eight pre-recorded clips in Chinese (default) and English. The audio is played by the host process through ffplay, or through the Windows PowerShell player that ships with the OS, so it does not depend on a Web Audio tab. Windows only.

Computer Use for macOS desktop applications: reads any app's accessibility tree as text with element indices, then clicks, types, pastes, scrolls, drags, selects text and sets values through it, plus screenshots read back as images. Driven by a persistent JavaScript REPL — the agent gets two tools (`js`, `js_reset`) and calls an `sky` API inside them, so state survives between calls and the tool schema stays fixed as capabilities grow. Accessibility trees come back as diffs after the first read; actions address elements by index and indices from a stale read are refused rather than misapplied; typing waits for keyboard focus and reads the field back; paste restores the clipboard. Requires macOS 14.4+, Accessibility permission (Screen Recording only for screenshots) and Node 20+; ships a prebuilt native module, so nothing compiles at install time.