dsh-pianist
Piano performance plugin: ask the agent to play a piece and it renders on a Canvas2D grand piano with real Salamander Grand samples, an immersive stage, and an interactive 88-key keyboard.
让 Agent 弹一曲真钢琴：Salamander Grand 真实采样音色，Canvas2D 三角钢琴与沉浸式舞台渲染，88 键可弹。
How to install
dsh plugin add dsh-pianist About
dsh-pianist dsh-pianist 为 DeepSeek Harness（dsh）Web UI 带来一台会弹琴的 Agent：写代码累了，让 AI 弹一曲放松；它弹得多好，就是模型的本事。是玩具，也是考卷。 项目主页：<https://laplace-bit.github.io/dsh-pianist/> 效果 点上面封面看演奏短片（docs/showreel.mp4），或者到在线 Demo 点一曲，听实时渲染。 它弹起来什么样 音色来自 Salamander Grand Piano V3 的真实录音采样，六层力度、键释放、弦共振、踏板动作都有，不是合成器那种"哔哔"声。 两套皮肤随时切：曜黑鎏金，黑色高光三角琴配暖金内饰，落键泛金光；樱花珍珠，珍珠白琴身、玫瑰金细节，头顶一片樱色天光。 全屏沉浸式舞台里有瀑布音符、水光倒影、流星和薄雾，跟着演奏起伏。 88 个键都能弹：鼠标滑奏、电脑键盘、方向键选音，想自己上手也行。 底层是一条确定性时间轴。暂停、拖动、重播，同一份乐谱每一次都分毫不差。所以它能当考卷用：模型会不会弹琴，一弹便知。 安装 在 DeepSeek Harness 源码仓库里： sh pnpm dsh plugin --profile web add dsh-pianist 如果 PATH 上已经有 dsh： sh dsh plugin --profile …
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 1
- mo. downloads
- 330
- Last push
- 2026-09-10
- Created
- 2026-08-17
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin, curated:0xsline/awesome-deepseek-harness
- Topics
- ai-agent, canvas2d, deepseek, dsh, dsh-plugin, llm-benchmark, midi, music, piano, plugin, typescript, web-audio, web-component
Related plugins
dsh-voice-scribe
PensiveFei/dsh-voice-scribe
Voice input for the web UI: tap Alt (or Alt+Space) to start/stop dictation, browser Web Speech (zero-config) or OpenAI-compatible cloud ASR, optional polish through DSH-configured LLM, settings UI.
dsh-tts
GooDAnDReaDY/dsh-tts
Speaks agent replies in the DeepSeek Harness web UI through a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak), so a failing or rate-limited provider falls through to the next instead of going silent.
dsh-ears
WizisCool/dsh-ears
Voice input plugin for DeepSeek Harness (dsh): a microphone button in the composer turns speech into a draft transcript, with a choice of speech-recognition backends, optional polish through dsh own LLM routes, and a native settings page.
dsh-omi-voice
PolinniZhong/dsh-omi-voice
In-chat read-aloud for DeepSeek Harness: tap to read, pause and resume AI replies with natural Doubao TTS voices (BYOK), reading only the final answer with code, tables and diagrams filtered; local engine, plugin keeps no API key.