Plugins

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.

Microsoft Web IQ search provider for the built-in web_search tool, with a settings card for the API key, endpoint, language, region, passage length and SafeSearch.

One-click OpenAI-compatible API (CodeBuddy/vLLM/proxies) with thinking mode, avoiding developer-role content_filter rejection.

TikTok-style video feed in a floating sidebar window: swipe local or SMB-NAS folders, or paste online video URLs (yt-dlp, bilibili/YouTube, cookies.txt login state); the window auto-fits the video aspect ratio, with fullscreen, drag-resize, Range streaming and an agent video-queue endpoint.

Plugin market inside the DSH Web UI: crawls the dsh-plugin topic with noise filtering, curated marks, ranking and one-click install (dsh.bundle-verified).

Analyzes conversation images through mode-specific prompts (caption, UI, document, grounding, topology, etc.) and injects structured evidence with coordinate primitives (boxes, points, refs) as text, with session-level caching for reuse across replay and compaction.

Routes images to a vision model of your choice - auto-rewrite, explicit tools, or hybrid - so a text-only chat model does not fail a turn that contains a picture.

Local-first, full-duplex voice for DeepSeek Harness, orchestrated by Muxiva

Phone access to DSH over a self-hosted relay (WSS via your own TLS-terminating proxy): bundle plugin with bridge supervisor and QR login, a native Android app, and server-side device revocation.

Agent-initiated voice calls: `offer_call` rings the human (接听/拒接/稍后再说); accepted calls synthesize and play locally via CrispASR + Qwen3-TTS (9 speakers, 2 Chinese dialects), rejected calls return the decision to the agent.

Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message read-aloud, auto-read toggle, and a settings page for model, voice reference_id, encrypted API key, and proxy.

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.

Citation tools for agents: exact DOI lookup, Crossref bibliographic search, GB/T 7714 / APA / MLA / Chicago formatting, BibTeX generation, bounded-concurrency DOI validation and health self-check.

Dracula theme plugin for the DSH Web GUI: the classic dark palette and the Soft variant registered into the native theme runtime, one-click switching with a persisted choice.

OpenCode Go balance pill at the right end of the composer tool row: rolling/weekly/monthly quota remaining straight from the Zen usage endpoint, with hover detail and warn/danger coloring.

Join ACN from DeepSeek Harness: register this agent, discover others, send messages, read the inbox. Defaults to the China region.

Langfuse observability for DeepSeek Harness: exports session logs as OpenTelemetry traces (GenAI semantic conventions) to Langfuse's OTLP endpoint

Stable, editable PPTX generation for AI agents — semantic IR in, native DrawingML out

ADB device & bench operations for DSH: device discovery, structured logcat (background streaming), apk install, file pull/push, and dumpsys performance snapshots.

Live2D session view with realtime voice: continuous voice input, streaming TTS, subtitle translation, multi-model catalog, standalone entry / Live2D 实时语音会话视图：连续语音输入、流式 TTS、字幕翻译、多模型目录、独立入口

Multi-workspace manager: bind a docs anchor plus ordered code-project repositories into one session, injecting their absolute paths, a recursive file index, a server/client endpoint index and optional coding standards, and syncing writable directories into the sandbox.

A live crypto ticker card in the DeepSeek Harness sidebar footer, above the balance and Settings, showing BTC, ETH, SOL and JUP prices, 24-hour change and 24-point sparklines, with a pulse on each price tick, zero dependencies and no API key.

QQ channel for dsh via OneBot 11 (NapCat and friends): reverse or forward WebSocket, DM and group chats, image and voice transcription, t2i text-image cards, merged forwards, and a settings page.

Build PowerPoint decks from a brief: plan and storyboard gates, per-page authoring through pptwise and ppt-master, a design-profile pass, page-image snapshots with a render audit, and a tool that hands those pages to an image-capable model for review.