Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
248 plugin trovati
my-projects (desktop-pool-plugin)
lizzkkafei/my-projects
A 3D billiards game opened from a DSH session: an American eight-ball (8-ball) pool table on a 9ft tournament bed with three-stage friction physics so draw, follow and side spin are computed rather than scripted, WPA rules against an AI opponent, and fully procedural art and Web Audio sound.
dsh-getnote
magicbaobaoli/dsh-getnote
A local-first Markdown panel for a 得到大脑 / Get笔记 vault: folder tree, tag cloud, full-text search, and a renderer for tables, timelines, Obsidian wikilinks and image attachments. Recording notes get an audio player with drag seeking and a timestamped transcript. Notes are plain .md files on disk, so a synced vault stays readable offline; cloud sync is optional, and deleted notes go to a restorable trash. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-voice-hotkey
whiplashf/dsh-voice-hotkey
Push-to-talk remote for the official Voice Input bundle: a hotkey (default Alt+V) starts and stops its recorder — tap to toggle, or hold 0.5 s and release to stop like a walkie-talkie. An energy-based VAD ends the take after a configurable silence (0.5–10 s), and the caret is moved into the composer before recording so the transcript lands there and Enter sends it. Optional auto-send, a second hotkey that focuses the composer, a provider picker in the composer toolbar, and both hotkeys can be rebound or cleared. Recording, transcription and insertion stay in the official bundle; audio goes only to your own DSH server. Zero runtime dependencies.
my-projects (zhizhen-liyin)
lizzkkafei/my-projects
A music production workbench opened from a DSH session: multitrack MIDI and audio arrangement, piano roll, 16-step drum sequencer, grand staff score with chord symbols, stereo recording with weighted multi-take mixing, a mixer with volume/pan/reverb/delay automation curves, and master, stem, vocal or backing export normalized to -14, -16 or -9 LUFS. Instruments are synthesized with Web Audio; the bundled 68-bar example project plays on open.
dsh-video-insight
azerz/dsh-video-insight
Video analysis panel in the DeepSeek Harness sidebar. Paste a YouTube or Bilibili link to fetch its subtitles and generate a summary, chapters, a mind map and citation-backed Q&A over the transcript, with an embedded player whose timestamps jump to that moment and keep playing. Videos without subtitles fall back to local Whisper / SenseVoice transcription (audio stays on the machine); silent videos fall back to frame OCR with macOS Vision, or to vision-model frame descriptions. Per-video analysis caching, a 100-item searchable history, and two agent tools: video_digest and video. A Bilibili SESSDATA cookie, if you enter one, is stored in ~/.dsh/video-credentials.json (mode 0600), transcripts are sent to your current model, and its HTTP routes have no DSH access check.
dsh-complete-chime
423324324/dsh-complete-chime
Plays a chime or a short melody when an agent turn finishes, with five synthesized tones plus a custom audio upload, optional spoken announcement, optional system notification, and per-subagent control; settings are stored on the host.
dsh-breeze-speak
rirtue/dsh-breeze-speak
Reads each reply aloud through the BreezeBlue / Breeze TTS 2 API. Synthesis starts as soon as the reply first sentence is complete rather than after the whole reply, and the audio is streamed as raw PCM into Web Audio so it plays continuously while it arrives. Needs a BreezeBlue API key, entered on the settings page or via BREEZE_API_KEY; a key saved on the settings page is stored as plain text in ~/.dsh/breeze-speak.json. By default only the first sentence of each reply (up to 120 characters) is spoken, and that text is sent to api.breeze.blue. The default voice is just an example, so pick one available to your account on the settings page.
dsh-solmirror
cthulhu-tww/dsh-solmirror
Connects the Solmirror open platform to DeepSeek Harness as MCP tools covering image and video generation, a model catalog, cost estimates, reference uploads, result queries and media URLs. Generation jobs submit as native dsh background tasks that notify on completion and run in parallel within one message, with in-chat video playback and an image wall. A settings page takes the platform API key, server URL, per-group model visibility and a test-connection check; the key is stored in the local dsh credential store. Reference uploads (image, video, audio) return reusable ids kept one day unused or three days after last use — 50 MB per file, video up to 30 s, audio up to 60 s. Usage bills platform points at in-site prices, with quotes before a run and automatic refunds on failure. Files passed to upload_reference (jpg/png/webp/gif, mp4/mov/webm, mp3/wav, up to 50 MB) leave your machine: images and videos go straight to Volcengine ImageX/VOD storage with temporary credentials issued by Solmirror, audio through the Solmirror server; its HTTP routes (/plugins/solmirror/...) have no DSH access check.
dsh-skin-studio
ghostmss86-afk/dsh-skin-studio
Interface theme and wallpaper plugin: preset skins, gradients and image wallpapers, plus local video wallpapers that play with sound — audio Chromium cannot decode (E-AC-3, DTS, TrueHD) gets an AAC sidecar through ffmpeg. Videos are folded into season folders and play in order, with F7/F8/F9, fullscreen and a draggable progress strip above the composer. Glass surfaces reuse the app's own sidebar and layer tokens. Needs DSH 0.2.2-rc.1.
dsh-notify-lite
game25011/dsh-notify-lite
A lightweight task completion notification plugin for DSH (dsh-notify-lite). When the agent finishes its work, it delivers Windows native Toast notifications with the first paragraph of the latest reply (40 characters by default). Supports taskbar unread badges, audio alerts, and configurable notification options. With no resident tray or background service, it keeps you focused without interruptions. Fully open source under the MIT license, with continuous DSH compatibility.
dsh-minimax-voice
sunshine334419520/dsh-minimax-voice
MiniMax voice studio for DeepSeek Harness: clone a voice from an audio sample, preview it from the audio returned by the clone request itself (no extra synthesis call, so the per-voice fee stays uncharged), synthesize text to local mp3 files, transcribe audio to text with asr-1.0, and manage the voice library, API key and these actions from a settings panel; four agent tools and a local HTTP API.
my-projects (zhizhen-cut)
lizzkkafei/my-projects
A single-window video editing workbench opened from a DSH session: multi-video import, magnetic timeline with trimming and skimming, audio roles with ducking, local silence-detection rough cut, script-based captions, nine color looks, and MP4 export (WebM where the browser cannot record MP4).
dsh-any-preview
actcwlf/dsh-any-preview
Previews what DSH does not cover, including video and audio, 3D models, archives, SQLite and model weights, and searches large CSV, log and JSONL files.
ai-voice
root-7-khx/ai-voice
A local AI voice studio for DeepSeek Harness with nine local TTS engines for voice design, voice cloning, emotional performance, a reference-audio library and audio export. It only registers /ai-voice/api routes; the UI lives in the companion-memory plugin's integrations page, and every engine needs its own Python virtualenv and downloaded model weights, which are not bundled.
dsh-go-local-voice
27synthesis/dsh-go-local-voice
Sintesi vocale per l’interfaccia mobile nativa di dsh-go: tieni premuta una risposta dell’assistente per ascoltarla con Xiaomi MiMo TTS o ByteDance Doubao Seed TTS. Dopo ogni turno la risposta viene suddivisa e sintetizzata in background, così un tocco avvia un unico MP3 continuo. Un lease stabile consente di fermare la riproduzione; barra di stato e avanzamento mostrano il progresso e l’audio si può esportare sul telefono. Le chiavi restano sul dispositivo con permessi 0600, senza essere mostrate, incluse nei commit o inviate al modello.
qiaomu-blog-publisher-dsh
joeseesun/qiaomu-blog-publisher-dsh
Gestisce le categorie del blog, salva le bozze e carica immagini, audio e video su R2 da Harness.
qiaomu-audio-dsh
joeseesun/qiaomu-audio-dsh
Legge Markdown ad alta voce, consente di dettare e trascrivere audio ed esporta contenuti multimediali narrati da Harness.
dsh-gallery
hope2023dcr/dsh-gallery
Galleria dei risultati nella barra laterale DSH. Per non mostrare i file solo alla fine di un’attività, controlla le cartelle di output su disco e visualizza i file appena compaiono, così puoi verificarli e intervenire durante il lavoro. Miniature delle immagini aggiornate automaticamente, con zoom e panoramica. Documenti, codice, dati, archivi e link si aprono nell’anteprima nativa DSH. Include filtri per conversazione e più cartelle per le sessioni con directory di lavoro fuori da quella di output predefinita. Nessuna dipendenza.
dsh-audio-tools
ren-xing/dsh-audio-tools
Strumenti audio per DSH: ispeziona file audio/video, converti o estrai la traccia audio, taglia, normalizza e trascrivi con whisper.cpp locale o API compatibile OpenAI. ffmpeg e ffprobe devono essere nel PATH (non inclusi); per la trascrizione locale servono anche whisper-cli e un modello ggml.
dsh-audio-rail-macos
blueteemo/dsh-audio-rail-macos
Solo macOS 14.2+. Controparte macOS di Lingwuxin/dsh-audio-rail. Il rail di conversazione DSH pulsa con ciò che il Mac sta riproducendo e mostra un vero spettro a 12 bande; cambia solo la lunghezza delle barre, lasciando intatti colori e lunghezze degli stati host. Al primo avvio serve il permesso di registrazione audio. Non installarlo insieme a dsh-audio-rail: entrambi controllano lo stesso rail e registrano le stesse route /audio-rail/events e /audio-rail/status.
media-suite (media-qwen)
do-nothing/media-suite
Strumenti multimediali Qwen tramite Alibaba Cloud DashScope: comprensione multimodale di video e audio, sintesi vocale con voci preimpostate e generazione di audio per scene.
dsh-speech-polish
keinsteinnus/dsh-speech-polish
Aggiunge una correzione attenta alla terminologia al riconoscimento vocale locale integrato. Mantiene il microfono DSH e il motore SenseVoice; l’audio non lascia mai il dispositivo. Corregge omofoni, termini di settore e numeri trascritti male nel testo finale.
dsh-video-vision
tests4gptplay/dsh-video-vision
Fornisce all'IA DSH fotogrammi video con timestamp, audio e analisi dei testi per Bilibili, YouTube e file locali. Importa sessioni browser crittografate, riprende la visione, salva resolver dei siti e gestisce la cache nativa. FFmpeg e ffprobe devono essere nel PATH o configurati nelle impostazioni del plugin.
dsh-puppet-memory
xingyuedanyang/dsh-puppet-memory
Memoria tra sessioni per DeepSeek Harness: archivio a tre livelli (note comportamentali, dettagli, archivio delle sessioni), scheda principale di 600 caratteri inserita a ogni passaggio, stati di lavoro/compagno/apprendimento, dati multi-persona e gruppi con partizioni di visibilità, soppressione o eliminazione di frammenti per sessione, riepiloghi e candidati di fatto inviabili a un modello separato, strumenti di backup e autocontrollo. Dati in testo semplice nella home; immagini e audio sono salvati tramite hash del contenuto.