@nanmicoder/dsh-agent-teams
AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI
42 results
AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI
DSH Codex UI — 为 DeepSeek Harness Web 提供 Codex 风格侧栏、工作区会话树、全局搜索和轮次导航 · A Codex-style sidebar, workspace session tree, global search, and turn navigation for DSH Web
AI4Scholar for DeepSeek Harness (dsh): 38 native academic tools — Semantic Scholar, PubMed, Google Scholar, arXiv, bioRxiv/medRxiv, DOI resolution, PDF full text, auto-cite, scientific figures, credit balance — with an API-key card in the Web UI settings.
A dynamic Cordis plugin for DeepSeek Harness: let an AI control a real, visible Chrome browser via Playwright MCP, with a live view of every action inside the GUI.
Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.
Composer mic for DeepSeek Harness Web: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.
Verified plugin marketplace for DeepSeek Harness: discover, inspect, install, and remove DSH plugins from the Web UI
Liquid Glass & Live Wallpaper (Desktop Edition): a physical Snell-refraction fluid glassmorphism theme and dynamic wallpaper engine optimized for deepseek-harness-desktop
Dynamic skin manager for the dsh web GUI: discovers every installed skin (skin.json packages and no-skin.json market themes), lets you toggle the active skin from a dedicated Settings page, mutually exclusive, hot-reloaded without restart
Voice input for DeepSeek Harness Web UI: a mic button in the composer tool row that uses the browser's Web Speech API (Chrome/Edge) to transcribe speech directly into the message draft. Zero dependencies, no API keys.
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.
In-GUI skin center for the dsh web GUI — the single skin package: skins are pure asset directories (built-in plus $DSH_HOME/skins) loaded and rendered only by the skin center; live try-on and one-click apply switch atomically in the page (no reload, no cordis.patch.yml rewrite, no restart)
DeepSeek Harness plugin: a "comic" trigger in the sidebar foot that opens search/download, an importable local library, and an in-modal manga reader. Bundles the jmcomic source so it works without the jmcomic PyPI package.
Liquid Glass Dynamic Island for the DeepSeek Harness Web GUI — a dual-face shell.overlay client plugin (design prototype + plugin in one repo)
Browse, search, and install Dify Marketplace plugins from inside DeepSeek Harness, and register each installed Dify plugin as a standard DSH plugin.
DeepSeek Harness client plugin: a microphone dictation button to the left of the Full access control in the web composer.
A graph-based task management system with CLI and web UI for atomic, verifiable tasks
A compact DSH Web composer island that integrates button-style input extensions without user-defined positioning.
A pixel-art Plugin librarian for dynamic capability sedimentation in DeepSeek Harness Web UI.
Jina AI tools for DeepSeek Harness: search (incl. arxiv/ssrn academic domains), read (plain extraction, plus jina_read_pdf for jina-ocr-v1 document OCR), screenshot, datetime, primer — with a Plugins-page UI for several API keys (round-robin + automatic failover), the endpoint host pair (mainland mirrors / global / auto) and reader options.
Wallpaper Engine bridge for the DeepSeek Harness web GUI: browse your local Wallpaper Engine library and use any dynamic wallpaper as the GUI background — video, web, image and scene previews, with scrim and translucency controls. Hot-pluggable via cordis.patch.yml + profile, no dsh source changes.
Microphone speech-to-text input for the DeepSeek Harness Web UI
SenseVoiceSmall-powered local speech-to-text for the DSH Desktop input box: click the mic beside the composer, speak, and the recognized draft (with language/emotion tags) is written into the input.
Voice (speech-to-text) input for the DSH Web composer via the browser Web Speech API — tap the mic, speak, the transcript fills the input box. Zero server, zero API keys, nothing leaves the machine. · DSH Web 语音输入:点麦克风说话,识别文字回填输入框(Chrome/Edge,无需 API key)。