Plugins

Union IM bridge for DSH — an independent implementation uniting the capability sets of community peer plugins (xmanrui/dsh-im, MichengAI/dsh-im-connect). Drive your agent session from 15 channel adapters across 12 platforms (including email; WeCom/DingTalk/QQ each contribute two: bot + self-built app or notify tier) — WeChat (official iLink QR bind), Feishu/Lark (long-connection + streaming cards; the voice tier requires system ffmpeg), Telegram, Discord, WeCom intelligent bot & self-built app (signed callback), DingTalk (stream + AI Card and custom-robot notify), QQ official bot (plus notify tier), Slack (Socket Mode), WhatsApp (Baileys QR pairing; the dependency ships as an optionalDependency of the plugin package), Matrix, iMessage (macOS only), Email (IMAP/SMTP thread routing). The cross-version narrow waist auto-adapts settings gen1/gen2/gen3 across hosts 0.1.2-rc.1→0.2.1-rc.2 (12-tag enum; rc.2 verified by a real desktop-profile install with double read-back) using capability probing only, never version branches. In chat: a 25-command panel, tool-approval and question loops answered in the originating chat (deny-by-default, initiator-only, 5-min expiry), image/file input gated on host model metadata, deliverable file return, a delivery log with bounded retry (uncertain is never re-sent), proactive delivery and fragment composition. It also splits the native sidebar into self-owned Tasks / Channels tabs (standing down entirely when another plugin already owns the slot), registers an `im-concise` agent preset plus reply sanitisation that keeps GenUI fences and raw HTML out of text-only chats, renders `svg` fences to PNG images, guards model choice with an allowlist, and mirrors each turn's final answer to notify channels via `/relay` (addressed by account ID or alias, never guessed on ambiguity). Secrets are one-way into the vault and never echoed back. npm: `dsh-im-union`.

Real-time local TTS for DeepSeek Harness: voice presets, auto-read, engine setup assistant, a read-aloud button, and a settings panel for the GSV-TTS-Lite engine.

QQ (NapCat / OneBot 11) bridge for DeepSeek Harness: chat with your harness from QQ, with persona presets and custom personae, a grouped sticker library plus web sticker search, edge-tts or custom HTTP TTS voice notes, pluggable lookup engines, periodic memory compaction, an owner-only relay mode, and an eleven-tab management panel with live monitoring and per-turn cost tracking.

Codex-style window capture for DSH Desktop on macOS and Windows: press both Command keys (macOS) or both Ctrl keys (Windows), or the camera button, to grab the frontmost window, attach it to the current chat, and inject a VoiceOver-style accessibility tree as hidden context.

Voice input for DeepSeek Harness: speak into the microphone and the recognized text is submitted as a normal chat message, via local or browser speech recognition.

Rings your phone over CallKit: `call_me` and `text_me` tools, plus optional turn-end and approval calls whose spoken answer is transcribed back into the session.

A whale companion with configurable roles, emotional speech through local TTS, persistent file-based memory, QQ messaging, and half-duplex voice calls. QQ requires a NapCatQQ-compatible OneBot v11 gateway, and the emotional voice requires a local VoiceStudio + audio.cpp + Breeze TTS 2 stack (or a compatible TTS API); FFmpeg is needed for non-1x speech speed.

Full-screen boot animation covering the loading page until the app UI is ready. The same library doubles as an appearance theme behind the interface, and desktop pets float over it on their own. Ships multiple built-in videos, wallpapers, voices and pets; upload your own files to customize.

Drive your local DSH from WeChat: a self-hosted iLink bridge over a persistent ACP session (context lives in DSH and is resumable), phone conversations grouped into the desktop workspace, with image recognition, file messages (Excel/Word/PDF, parsed by the agent itself) and voice transcripts. Tool approvals are answered inside WeChat itself (numbered card; ask/allow/reject policy; 120s timeout means reject), and any process can push a message to your phone through the outbox helper. Access defaults to strict (only registered devices are served); the phone channel's permission preset is configurable - see the README security section before sharing the bot.

Omni-modal workstation for DSH: analyze_image over an ordered multi-card VLM failover chain, a six-tool vision toolkit (zoom, colour sampling, pixel diff, OCR, element detection, inline display) sharing the same image resolver, generate_image over OpenAI/DashScope/ComfyUI protocols, multi-card async generate_video with a /build-video-tool builder, and speak/clone_voice TTS over seven providers, all driven by one auto-saving settings page.

Telegram bridge for DeepSeek Harness: bidirectional sessions, conversation steering, home-channel routing, and TTS voice notes sent as Telegram audio messages.

Big Fish Voice: makes the DSH web desktop pet speak. Whisper bubbles are read aloud automatically, left-clicking a bubble reads it, right-click/long-press reads it again, and clicking the pet replies with lines like 「主人，小鱼在这呢」. Default voice is a local offline replica of 鱼鱼酱; 鱼鱼姐 (experimental) is also included — no API key needed, voice packs download on demand (~58MB, China-accessible mirrors). Auto-reading can be throttled (unlimited / 30s / 60s / 3min); within one DSH instance only one page plays audio. About 35KB package, inference in a worker thread, no dsh-pet files modified.

Drive a dsh agent from Telegram: one chat topic per project directory, voice and photo input, ordered per-topic job queue, per-topic goals and task checklists, session forks and branches, live progress message, command menu in en/ru/zh, and control commands for models, plugins, sessions and logs. Search the plugin registry, read a package card before installing, and update every plugin with one tap. Requires a Telegram bot token and your numeric user id in allowedUserIds.

Local-first hands-free AI voice assistant plugin for DeepSeek Harness (DSH), with speech-to-text, text-to-speech, voice commands, and local speech engines.

Whale girl desktop pet for DeepSeek Harness: browser floating mascot plus Windows desktop pet sharing one data backend, with real-time balance board, task notices, head-pat interaction, 19 pre-synthesized voiced lines with per-line emotion, and presence-aware idle speech.

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.

Two-way WeChat bridge for DeepSeek Harness via the iLink protocol: bind your personal WeChat with a QR scan and chat with a local DSH agent from the chat box (text, images, voice-to-text, files); a web settings panel handles binding/start/stop/status, project-session binding continues the conversation on desktop, proactive wechat_notify pushes include throttling, and the pure-Node daemon runs on Windows/macOS/Linux.

Composer mic for the Web UI: 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.

Full-duplex voice mode for the Web UI: tap-to-toggle or hold-to-talk dictation (send key or `Ctrl`) with a live caption, host-side SenseVoice ASR via sherpa-onnx, sentence-by-sentence spoken replies, and speaking interrupts playback and the running turn (true barge-in). No API key.

All-in-one bundle for DSH: the native Windows desktop window (WebView2), DeepEye vision (GLM-4V-Flash), and voice input (mic button) in a single install.

Sword Art Online theme with two Link Start animations and Kirito/Asuna voices; full or startup-only mode with a true-alpha white-background transition into the loaded interface; independent light/dark accents and surface colours, local fonts, fully themed settings and clear control states; improved liquid-glass edge refraction and directional reflections with reduced white halos, or frosted glass; popovers sample the current page and only refract visible wallpaper; per-component transparency, continuous sidebar/context glass, compact tabs and single-line status readouts; nine wallpapers, local images or 4K/5K looping video with power-saving mode; model reasoning-intensity slider.

Selection quoting and anchored annotations across DSH chats and document previews: numbered quote blocks stay visible in the composer and in sent messages and click back to the source, notes from docx / PDF / Markdown / code / Excel-range previews collect into one batched send, and each note can be dictated by voice.

Plugin that turns a XiaoAI (Xiaomi) smart speaker into a voice assistant: hosts the local bridge process, listens for the wake word, runs speech recognition (ASR / STT) on what you say, keeps the conversation in the host session, and speaks the answer back through the speaker with text-to-speech (TTS) playback.

Doubao-style voice chat for DSH: press-and-hold mic in the composer converts speech to text and auto-sends, and AI replies are read aloud. Optional LLM condensing (long replies summarized into short spoken lines, following the current conversation model), TTS-friendly text cleaning, selectable Edge TTS voices, adjustable silence auto-stop, and settings embedded in DSH settings dialog.