desktop-gui-automation-cua
可泛用的 macOS 桌面 GUI 自动化(computer use):cua-driver 做 AX→像素→桌面的三档降级,对任意 app 先 probe 判定模式再驱动;含识图定位、隐私处理、微信/iPhone 镜像案例。遇点击/输入/滚动/截图任意本机 app,或微信/IPhone 镜像/canvas 等 AX 空或稀疏的软件时用。
48 results
可泛用的 macOS 桌面 GUI 自动化(computer use):cua-driver 做 AX→像素→桌面的三档降级,对任意 app 先 probe 判定模式再驱动;含识图定位、隐私处理、微信/iPhone 镜像案例。遇点击/输入/滚动/截图任意本机 app,或微信/IPhone 镜像/canvas 等 AX 空或稀疏的软件时用。
Recurring/scheduled tasks (轮询任务/定时任务) plugin for DeepSeek Harness: cron-driven polling jobs as real sessions, natural-language creation, model tools (polling_create/list/edit/delete/trigger) and a web UI. Install-and-go via `dsh plugin add`.
测试工作台 Profile for DeepSeek Harness — 组装 UI 验证、会话分析、视觉路由为一体的 QA Agent。
DeepSeek Harness Cordis plugin: drive Vimina Windows GUI automation via stdio (serve/call). Registers 26 vimina_* tools (scan/click/input/key/VMA scripts/screenshot/window/mouse).
Browser + Windows desktop patrol automation for DeepSeek Harness: teach once, replay deterministic runbooks across managed Chromium and desktop applications with screenshots, checkpoints, selector recovery, UI Automation, OCR, keyboard, and coordinate fallbacks.
Windows UI Automation observation from WSL: enumerate top-level windows and read a bounded element tree with stable per-observation handles.
Safety-gated Windows Computer Use tools for DeepSeek Harness with ModLens visual grounding.
OmniVision for DeepSeek Harness: an OmniParser-powered GUI agent plugin — screen capture, element recognition, click/type automation and a browser vision dock with recognition history, diffing and summary
Exit the DSH CLI process automatically when the Web UI closes (equivalent to Ctrl+C). DSH plugin: 关闭 Web UI 自动退出 CLI 进程.
MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness
Desktop & web UI automation for DSH: full-screen capture, Windows OCR, mouse click/drag, typing, key press, window activate, plus battle-tested Paint drawing capability
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
智能体选择器:像模型选择器一样在输入框旁勾选委派目标+具体模型,把对话任务派给外部智能体(Codex CLI / WorkBuddy 内置模型活动价 automation 桥 / WorkBuddy 自定义模型直连 / Claude Code)执行,结果流回 DSH 对话。含 agent_dispatch 工具 + composer 两步下拉 + 设置面板 + 桥健康探活 + 反冒充出处凭证。
DeepSeek Harness plugin wrapping the GitHub CLI (gh) with a browser settings UI.
DSH plugin: cross-session call center for agents. session_message delivers messages between DSH sessions (idle: visible full-text wake; busy: mid-turn-safe notice; plus runtime-context notes) and contacts is a named directory over session ids. UI intentionally removed in v1.3.0.
Scheduled-task plugin for the dsh web sidebar: create tasks that run a natural-language prompt in dsh at a set time (one-off / daily / weekly / interval), with a sidebar manager UI placed between the New Session button and the Workspace list. UI language follows the dsh language setting (zh/en).
Headless-first managed Browser Use for DeepSeek Harness with isolated sessions, semantic refs, deterministic safety checks, and bounded evidence
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
DeepSeek Harness Computer Use 插件(Windows):让 AI 看屏幕、点鼠标、敲键盘操控电脑;控制时屏幕泛起橙色光晕并显示“DeepSeek Harness 正在操控你的电脑”,按 Esc 暂停 / 继续。
Cron scheduler plugin for DeepSeek Harness: schedule agent tasks via natural language or a sidebar UI, with fixed/new session strategies, run history, manual trigger, and live sync.
A browser that lives inside the DSH host: every session gets its own tab, the AI drives it with lazily published browser_embedded_* tools, and a human watches or takes over that same tab in an on-demand right-Sidebar tab — no GUI, no external browser, logins/2FA/QR codes/CAPTCHAs included.
Drive a Windows 10 interactive desktop from DeepSeek Harness: window/UI automation, trusted screenshots, offline OCR, and Chrome CDP — as tools, slash commands and skills.
dsh Web UI admin plugin: eleven management panels (extensions, skills, MCP servers, subagents, commands, hooks, automation - cron / webhook / workflow, sessions & web search, usage dashboard, todo dock) inside the official dsh settings UI
macOS desktop control for DeepSeek Harness: agent operates non-browser apps (CapCut/PS/WPS/native clients) like a human — see screen, move mouse, type text. 14 tools + vision closed-loop (see/locate/click/verify).