Plugins

Design-artifact skill adapted from Anthropic canvas-design / web-artifacts-builder: turns a design brief into a self-contained HTML/SVG artifact (posters, infographics, landing pages, charts, component mockups) with a pre-delivery quality checklist and an anti-AI-look pattern list.

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.

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.

Honcho memory bridge: auto-syncs every conversation turn to a self-hosted Honcho service, with recall/search/remember/context/status tools, context injection on session start, and a visual settings panel.

DeepSeek Harness record macOS desktop workflows by demonstration and turn them into agent skills (open-record-replay skill + orr_* tools)

Cross-session memory vault: remember / recall / forget tools, per-turn prompt injection, and a settings-page entry browser.

An edited fork of dsh-chat-editor from WZZNNE/DSH-CyberWorkStation (MIT), with -plus ids so it can be installed alongside the original. Rewrite or delete messages the model reads — text, reasoning blocks and tool results — without replacing the message on the session surface, and branch a session from any turn.

A writable, git-versioned self for DeepSeek Harness: persona files injected every turn, a persona-only memory layer, topic-keyed journal→dream promotion gated by your 👍/😑/👎 ratings, whitelisted self-upgrades, and a Settings persona tab.

Cheap enough to leave running in a QQ group all day. The lite reply mode bypasses the full agent loop and calls chat completions directly: about ¥0.0027 per turn, roughly ¥0.2 for 80 turns a day, around 75x cheaper than a full DSH session. Still includes switchable persona cards, image and video understanding, an auto-tagged image library built from group pictures, and keyword recall over archived chats. One-command SSH deploy with environment checks, credential-safe config generation, systemd units and a watchdog. Bundles a fork of Derpyu520/qq-bridge (MIT); do not deploy it to a host that is already running the upstream bridge.

Publishes the running DSH host as a Model Context Protocol endpoint, so other harnesses such as Claude Code, Cursor, Codex or another DSH can start and continue sessions, read transcripts, wait on or cancel turns, and answer pending approvals; every call is attributed to its caller, and owner-scoped sessions keep callers apart.

On the first real work message of each chat window, asks for the missing goal, deliverable, constraints and acceptance criteria, then turns the answers into a short task sheet and injects it into the chat. Pure greetings are ignored.

Injects a per-turn skill-selection preface chosen by the local JEV model of the jev-decision-kit workspace, so the agent loads exactly those skills instead of browsing. Requires a separately set-up jev-decision-kit workspace (Python .venv, host/preface_worker.py, models/jev/head.json); without it the plugin injects nothing.

Per-turn TPS and TTFT statistics for DeepSeek Harness: model time, tool time, time-to-first-token, and output speed per turn.

Watches a turn for long silences and, once the threshold passes, injects a user message asking the model to state in prose what it is doing before carrying on, so the turn keeps going. The same text is mirrored in a lower-left overlay above the composer. The silence threshold and the minimum gap between reports are set in minutes, the prompt can be replaced wholesale, and it runs with no runtime dependencies. Requires DSH 0.2.1+ and Node.js 18+.

Turn another computer into a remote Agent teammate: the worker runs its own DSH and a full Agent loop locally, so dispatched tasks keep running when the link drops and its model credentials never leave that machine. The hub dispatches through 8 remote_* tools, receives only a handoff summary plus an artifact manifest, and pulls finished products on demand — intermediate artifacts stay on the worker. Pairing-code onboarding, direct or relay transport for NAT, Web panel on both sides.

Executor/advisor workflow ported from pi-advisor-flow: the executor calls ask_advisor for a second opinion at key decisions, after repeated failures and before completion; equivalent repeated tool calls are intercepted before execution for an advisor review with a proceed/revise/blocked verdict, and hard mode force-reviews every turn before it closes. Per-call token and cost ledger with /advisor status readout, privacy tiers for repo context and file contents, six-shape secret redaction, and a web settings card; advisor failures never stall the main loop.

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.

Model failover and turn keep-alive for DeepSeek Harness: a request that fails with a model error before any visible output falls through the models of the configured provider groups (then the next provider) until one streams; transient failures retry with backoff under a liveness watchdog, a dead turn self-resumes with templated 「继续」 wake-ups, and an optional full-auto mode auto-answers permission, question and plan approvals with every decision appended to an AUTO-MODE.md audit log.

Restart button at the right end of the session header that restarts the whole client: the Windows desktop app (Electron shell and Host, through the Host's own graceful shutdown) or the dsh web server. It can wait until running turns and background jobs finish, reopens the open session afterwards with one-click continue for interrupted sessions, flags plugin updates that only take effect after a restart, and shows Host uptime and memory on hover.

Turns a local Obsidian vault into a dedicated RAG chat panel: a sidebar page with the note browser, the retrieval-augmented chat and the cited source side by side, answering from fully local BM25 plus CJK-bigram retrieval over your notes and streaming through the DSH model channel, with clickable \[n] citations and mtime-based incremental indexing.

Up to 5 clickable next steps under every reply: click one to send it, or fill it into the composer and edit first. The suggestions come from the main model as it closes the turn — no extra model call.

Simulated life context for DeepSeek Harness: every turn injects the past 24h of simulated life events from the workspace .life/ directory (sliding-window filter, session-level deduplication with delta updates, world summary) as a collapsed context notice, and the life_react tool lets the agent record feelings, thoughts and actions back into its life log for the next round of world evolution — turning a DSH agent into a roleplay character with a persistent daily life.

Shows a DSH session as a conversation canvas — every turn is a node, any turn forks a real child session, and a compacted context folds into one green node you can keep talking from; the left rail groups canvases by DSH workspace and renames them in step with the session titles.

Peer communication between conversations in one DeepSeek Harness process: list the conversations the workspace shows, link one under a nickname, message it without waiting for its turn to end, read its progress without waking it, and declare rules for your own tool calls.