Plugins

Microphone voice input for the composer: browser Web Speech API live transcription, dedupe/auto-continue, smart punctuation, language and auto-send settings.

A fork of dsh-livestream (MIT) - install it instead of that plugin, not alongside it. Lets DSH host a Bilibili livestream: chat and gift replies, queued viewer video requests on a skinnable stage, Doubao TTS voice, and automatic OBS/Bilibili streaming setup; needs OBS Studio 28+ and a Bilibili live room, and the voice stays silent until you add a Doubao TTS API key (Python + faster-whisper optional for transcribing subtitle-less videos).

Bundles five TIA Portal skills (Siemens PLC docs lookup, ladder-logic generation, SimaticML-to-PNG rendering, scan-cycle simulation with PASS/FAIL scenarios, and a TiaLink gateway skill for driving a real TIA Portal project) and wires five MCP endpoints. Requires TiaLink (paid; Windows + TIA Portal V19/V20 + Openness) for real-project work, API keys for the four cloud services (100 free calls each, then paid; rendering is billed per call even on failure), Node 22+, and network access; program snippets are uploaded to tia.hubwiz.com.

Five-layer intent recognition pipeline (rules, pgvector retrieval, Jev scoring, fine-tuned arbitration, LLM fallback) with scenario management UI, PostgreSQL storage and distributable API services.

Turns DSH into a local OpenAI- and Anthropic-compatible gateway endpoint that puts one persona and long-term memory in front of every client pointed at it; requires your own DeepSeek API key — the DSH login credential is rejected upstream.

Windows terminal dock inside the DSH web GUI. It is the occupant of the shipped shell.bottom slot: showing it splits the screen (the columns shrink instead of being covered), hiding it returns the space and keeps the PTY session alive. Each session is a local ConPTY child spawned through node-pty and rendered by xterm.js over a loopback-fenced WebSocket (backpressure, debounced resize). Other plugins can add terminal or DOM views through a host registerView API and a window CustomEvent channel.

DSH 插件：按配置调用后端 HTTP 接口、启停/重启本地开发服务、增量读取日志并等待日志特征，让模型能"改完自己验"。

Routes DeepSeek Harness model API requests through a system, custom or SOCKS proxy; requests outside the configured domains stay direct.

Reuses stored Responses IDs for continuation, with retry and branch isolation and verified history replay.

DSH text-to-image/image-to-image plugin: compatible with OpenAI-style image generation APIs, with 多米API as the default; standard OpenAI endpoints may require protocol, image-to-image mode and size adjustments; text-to-image and URL reference images do not use COS, while local reference images can be compressed and stored in COS; custom prompt suffixes are supported.

Sends excerpts from recent Chinese Markdown conversation exports to the DeepSeek API (API key required) to generate a dream, saved as a local Markdown file.

DSH 启动时默认拉起 WorkBuddy2API Hub（127.0.0.1:7863），可切换 wb2api；幂等、静默、退出时只停自己拉起的进程。

Design-first PowerPoint builder: six pptx_* tools turn a deck.json design draft into an editable .pptx with AI backgrounds, cutout illustrations and decoration pieces, run layout and contrast checks, render slide previews, and review pages with a configurable vision model; chat cards and a settings page in the Web UI. Requires DSH Desktop 0.2.1-rc.2+ (pptx_render uses its bundled LibreOffice Kit) and an Agnes or ModelScope API key for image generation.

Image generation for DSH in two modes — an image_generate_lite tool the model calls from chat, and a right-sidebar studio for manual runs; up to five reference images, the OpenAI images API format, keys kept in the DSH credential service.

Aggregated web_search and web_fetch providers for DeepSeek Harness, sitting behind the built-in tools. Search fans one query out to AnySearch, Zhipu and Zhihu concurrently, dedupes URLs, fuses ranks with Reciprocal Rank Fusion and optionally reranks through SiliconFlow. Fetch is URL-aware: static pages pass through the built-in HTTP fetcher, dynamic ones fan out to Firecrawl and AnySearch extract and pick one body by quality. One shared circuit breaker skips an engine for the day after a quota or 429 signal, and a settings card keeps each engine API key in the credential store without ever showing its value.

Image generation through eight provider APIs (Labnana, OpenAI, Gemini, Seedream, DashScope, xAI, Zhipu, ComfyUI) with multiple saved profiles, a per-conversation gallery, and credit tracking on Labnana.

Local-first memory and persona plugin for DeepSeek Harness: four file-backed memory layers (pinned, memory, facts, experience), editable SOUL/MOOD persona, zero-LLM session capture, BM25 recall and a themed mood card; no standalone web panel, Python service, vector database, or API key.

Switch the current session's agent preset (mode) at any time, including after the conversation has already started, from a session-header dropdown backed by a fenced POST /preset-switch/api route. The route also repairs sessions whose recorded preset was deleted. Fork of jeffcwj/dsh-preset-switcher updated for DSH 0.2.1.

Model-linked characters and a shared world for DSH, with separate editable personas and memories, optional AI diaries and sleep consolidation, Chinese/English controls, task-aware desktop pets, themes and usage statistics; updates preserve user customizations. Supports Windows, Linux and macOS; see the guide for each system's installation requirements. Diaries and consolidation consume tokens. Before installing or updating, we recommend closing visible desktop pets and bubbles; open files may cause installation to fail. Codex and OpenAI API account queries have been user-validated; other sources await user validation and feedback.

Reads a running workbuddy2api-panel over its HTTP API and syncs its models into the DSH model picker with credit multipliers, CN/international realm labels and per-model reasoning-effort levels; also shows remaining credits and usage in a settings page and a sidebar badge.

Use TRAE account model quota in dsh, with multi-account management, daily check-in, rotation, usage statistics, reasoning levels and model visibility. Requires Python 3.10+; the first run downloads Python dependencies.

Tavily backend for the built-in web search: an in-process endpoint at 127.0.0.1:8787/v1 turns its requests into Tavily searches; up to 10 API keys stay in the DSH credential store, rotate per request and switch on auth, rate-limit or quota errors; a settings card manages keys, runs a test search and points web search at the endpoint.

Runs the standalone opencode2api backend (jasonxu114514/opencode2api, Windows x64/ARM64, no Docker or OpenCode CLI) with DSH and on exit stops only the process it launched; its settings card installs, updates or rolls back the backend from checksum-verified GitHub releases, copies the initial admin password and syncs /v1/models into an opencode2api provider with context, vision and reasoning efforts, re-syncing every 10 minutes.

Reads each third-party endpoint's own model listing and keeps llm-pi-ai's per-model reasoningEfforts in sync, so the composer offers the thinking levels a model actually has.