151 results
Desktop computer use for DeepSeek Harness (DSH): macOS app listing, accessibility-tree window capture, screenshots, and synthesized input — the seam, the local Swift-daemon provider, the computer_use_* tools, the approval policy, and a standalone MCP server in one installable plugin package
Minecraft Launcher built on DeepSeek Harness: full-screen launcher UI (root slot) with Microsoft device-code login, version download/install, and game launch from the DSH host process.
Focus Mode for the dsh web GUI: a full-screen reading overlay that hides chrome and folds the AI tool-call flow into summaries, reusing the official Markdown / image primitives.
Widescreen mode for the DeepSeek Harness session detail page: a General-settings toggle that lets the chat use the full browser width instead of the fixed 748px content column.
Kimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the local kimi-webbridge daemon
dsh 插件：给文本模型补一双眼睛 + 给多模态模型补一对观察 UI 渲染的眼睛 —— 设置弹窗选视觉模型 + meow_vision 工具 + meow_preview 组件截图工具
Windows Computer Use for DeepSeek Harness: window-bound screenshots, robust OCR, verified clicks, pure-OCR mode, pluggable vision models.
Kimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the local kimi-webbridge daemon
手机端 UI 适配：窄屏下把 DSH Web GUI 重构为全屏聊天布局（侧栏/右侧面板改为抽屉，顶部悬浮操作条 + 全屏按钮），默认 ≤860px 生效
Vision-only desktop automation plugin for DeepSeek Harness (fusion refactor)
DeepSeek Harness plugin: one-page mobile access setup — Tailscale/LAN detection, scan-to-pair QR, direct/HTTP-2 connection modes (Tailscale Serve toggle), API trust-fence guidance, persistent device credentials, PWA home-screen, and a live SSE notification channel.
DeepSeek Harness plugin that turns UI screenshots into implementation-grade web specs using OCR, deterministic geometry, scene graphs, assets, and render comparison.
通过 QQ 消息远程控制 DeepSeek Harness：命令执行(/exec)、任务派发(/ask)、阶段进度汇报、屏幕截图发送(/screenshot)、AI 聊天(/chat)与聊天特化会话(/chatbind)、会话标题化管理(/newsession /title /session)。OneBot 11(NapCat/Lagrange/go-cqhttp)，零 npm 依赖。
DeepSeek Harness bundle for a Windows desktop UI context picker and MCP server for Codex, DeepSeek Harness, and AI agents
DSH web plugin: GitHub-style daily token-usage heatmap on the new-session screen with a selectable calendar-year view, green/blue color schemes and a display switch (设置 → 插件 → 插件配置), plus today / this-month / all-time totals.
SSiD (思灵) quick screenshot capture: tray/hotkey → fullscreen box-select overlay → cropped image into the current conversation composer
Paper Design MCP bridge as a DeepSeek Harness bundle: paper_* tools, image screenshot support, design skills, OAuth auth, and Cursor-parity design guidance.
Select a range of a DeepSeek Harness conversation and share it as a branded PNG long image, with draggable magnetically snapping range markers.
Codex-style computer use for DeepSeek Harness (DSH): read the screen and drive the mouse & keyboard. Pairs with picturereader (image_scan/image_ocr) to close the look-act-verify loop. Windows.
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
macOS Vision OCR tool plugin for DeepSeek Harness: read text from screen capture, clipboard images, or image files (zh-Hans + en-US). Unofficial community project.
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
Vision + Android UI automation plugin for DeepSeek Harness: gpt-5.6-luna screenshot understanding and real-tap mobile app testing via adb
Local vision 'eyes' for DeepSeek Harness (DSH): screen tool (capture screen or image -> local OpenAI-compatible VLM description) and ocr tool (Windows built-in OCR, zero model / GPU / cloud).