Plugins

Observação e controle do desktop Windows: árvore de acessibilidade, capturas, OCR alternativo, mouse/teclado, aprovações por sessão e interrupção via ESC. Inclui alternativas para automação de GUI no DSH.

Seletor de contexto de UI do desktop Windows para Codex, DeepSeek Harness e clientes MCP: seleciona janelas, elementos de UI ou regiões da tela com destaque ao passar o mouse, UI Automation, capturas de tela e OCR local, e depois revisa e aprova o contexto Markdown/JSON antes da saída.

Personalize o cursor do mouse do PC para cada estado da interface no DeepSeek Harness.

On-screen test-progress HUD for DSH — a click-through panel drawn over the app under test, showing each step's expectation vs actual and whether the waiting human may take back the mouse and keyboard. Ships a universal prebuilt binary (arm64 + x86_64), so no Xcode Command Line Tools are needed; the panel itself requires macOS 14+.

A music dock for the DSH web GUI. A draggable capsule in the bottom-right corner opens into a player card with a queue, previous and next, a draggable progress bar, a volume knob driven by drag or mouse wheel, three loop modes and per-track cover art for resolved links (local files show a vinyl placeholder); audio files dropped onto the card play immediately. Paste a Bilibili, NetEase Cloud Music or QQ Music track or playlist link to resolve it: NetEase and QQ audio is signed by the host into an opaque HMAC token, so the browser never receives a plain CDN address and cannot forge one. A spectrum canvas along the page bottom reads a real AnalyserNode and draws in six styles (dots, bars, blocks, mirror, line, wave) with adjustable width, bar count, sensitivity, glow, height, frame rate and placement; the row is fitted to the container width, falling back to a slight overflow when the gaps would fall below half a pixel. Seven colour themes (whale blue-white, aurora, mint, sunset, rose, neon, mono). The settings section is grouped into interface, theme, playback, links and spectrum, and carries favorites and history tables.

Targeted Windows input from WSL: invoke a UI Automation element by name, or send keys, clicks and mouse wheel to a chosen window.

Page zoom for the DSH Web UI: Ctrl+mouse wheel scales the entire interface in 5% steps (30%-200%), remembers the zoom level locally, and shows a magnifier with the percentage in the bottom-right corner.

Shared browser panel for DeepSeek Harness via Better Sidebar, with local Chromium, human and agent mouse and keyboard control, page snapshots, screenshots, and per-chat persistent profiles.

Windows computer use forked from computer-user: 13 computer_* tools that read the screen and drive the mouse and keyboard. Image-capable routes get the screenshot as a real image with an exact image-to-screen mapping, so no external OCR; elements return as UI Automation refs so a click lands on the exact control rectangle; Ctrl+Alt+Esc stops every call.

Controle do computador no Windows para DSH: captura de tela, análise por modelo de visão e simulação de mouse/teclado com base de conhecimento evolutiva. Oferece ferramentas de plugin em modo duplo e alternativa pwsh somente com skill.

macOS desktop control for DeepSeek Harness: agent operates non-browser apps (CapCut, Photoshop, WPS, native clients) like a human — 14 tools for mouse, keyboard, scrolling, app activation, windows and screenshots, plus a vision closed-loop (desktop_see for image understanding + desktop_locate for UI element coordinates) that reuses dsh existing vision credentials. GUI-session service starts on demand, no login autostart.

Tema macOS Liquid Glass para a interface web do DeepSeek Harness: gelo flutuante, refração arredondada, borda do mouse e papel de parede personalizado.

Navegador de conversa em trilho de ticks: um tick por mensagem enviada, um pico iluminado que segue o mouse com queda uniforme, pré-visualizações ao passar o mouse, clique ou teclado para saltar.

DeepSeek Harness plugin: a desktop tool that screenshots the Windows screen (labelled coordinate grid), reads UI Automation and OCR, and drives the mouse and keyboard.

Windows x64 desktop tools for DeepSeek Harness to restore and foreground existing windows, observe screenshots and UI Automation elements, left-click, and type text or supported keys, with repeatable control sessions and physical Esc to stop.

Windows desktop control for DeepSeek Harness agents: window and UI Automation automation, local Windows OCR, direct browser reads over the Chrome DevTools Protocol (DOM text, JavaScript, selector clicks), humanised mouse and keyboard input, browser tab management, and a live control panel. It probes the machine on first run, writes its own config, and degrades gracefully when a capability is missing. Windows 10/11 only.

Lets an AI play Slay the Spire 2: screenshot plus mouse/keyboard tools, a local card lookup, and a readable play log. Requires Windows and Python 3.10 or newer with Pillow.

Send by dragging instead of clicking. Press the composer and pull up to arm the gesture; releasing sends, dragging back into the composer cancels, and dragging outside the conversation area cancels on the spot. Mouse and pen only.

Hold Ctrl and roll the mouse wheel to zoom the whole Harness Web UI around the pointer, 50-200% in 10% steps; Ctrl +/- and Ctrl 0 from the keyboard; a bottom-right chip and a Page zoom row in Settings → General show and reset the level.

Global back/forward navigation for the DeepSeek Harness Web UI: remembers every session and whole-page panel you visit, shows a configurable 1-7 entry history strip you can click, and supports browser-style shortcuts plus mouse side buttons.

Turns the right edge of the chat scroll area into a theremin-style strip: the vertical mouse position picks the pitch (higher up, higher note), and blue ticks mark your own messages so you can click one to jump to it. Includes a draggable on/off pill and volume slider.

Control Proxmox VE virtual machines from the conversation: 16 tools for the VM console over VNC (screenshots, mouse, keyboard, batched actions, Unicode text and clipboard) and for running commands and reading or writing files through the QEMU guest agent, all over one ssh connection to the node, so the host needs no X11 or Wayland.

Codex-style keyboard answers for the pending command-approval panel — 1 allows once, 2 rejects, Enter confirms the highlighted choice, arrow keys move it, and Esc rejects, with the buttons still usable by mouse.

Windows desktop control connector: through 10 agent tools it captures the screen (including occluded and partially off-screen windows), lists and focuses windows, moves, clicks, drags and scrolls the mouse, and sends key chords or arbitrary Unicode text. Built on koffi FFI: no compiler, no per-call subprocess, and its own GDI screenshot plus PNG encoder.