Plugins

Shares one right-sidebar across every conversation in the same workspace, so you don't have to reopen it when creating or switching conversations, with a switch in Settings → General.

Desktop mode for the DeepSeek Harness web GUI: open sessions as movable, resizable windows with a taskbar.

A Plugin Market entry in the DSH settings sidebar that opens dshmarket.com, the community plugin market for DeepSeek Harness, in a new tab. The light-weight alternative to installing the market itself, for people who only want the button.

Bridges a OneBot QQ bot into DSH: the owner's direct messages open a session on the same home, answers go back to QQ, and files named with \[SEND_FILE: path] are delivered. Needs a OneBot v11 implementation with a forward WebSocket (such as NapCat) and ownerId set in the config, otherwise every message is ignored. The home it shares with the main session is provided by the separately installed dsh-wakeup plugin. It also runs an unauthenticated local status endpoint on 127.0.0.1:3002 with open CORS that returns the owner QQ number, the login QR code and recent log lines (including the first 60 characters of incoming messages).

Durable cross-session memory plus a fetch ladder that survives hostname-keyed blocking. Four tools: memory_recall, memory_save and memory_stats over a plain-JSON fact store at $DSH_HOME/memory/facts.json, plus resilient_fetch which tries plain fetch, then a same-service alias host (Wikipedia only for now), then curl over IPv6 and IPv4 (needs curl on PATH). No daemon, no npm dependency, no network at import time. (1.3.0 shipped a fifth tool, memory_prune; it was withdrawn in 1.4.0 because adding a tool to a running plugin breaks sessions that were opened before it.)

TypeSafe AI Jev decision provider for typed probabilistic choices and scores in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Ollama provider for language models and embeddings, with model discovery, loading, and unloading in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Alibaba Cloud DashScope provider for Qwen language models, embeddings, reranking, speech, and image generation through native APIs in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Open STL meshes in the right-Sidebar document preview: browser-side binary/ASCII parsing, a WebGL viewport, and size/volume/surface-area/watertightness statistics.

Open .blend files in the right-Sidebar document preview: cached Blender headless GLB export plus a dependency-free WebGL viewport and scene statistics. Requires Blender 3.6 or later installed locally.

Meta's Muse Code CLI inside DSH: a composer switch starts muse serve, a right-sidebar panel and five chat tools (muse_open, muse_prompt, muse_read, muse_status, muse_interrupt) share one Muse session, approvals are decided only in the panel, and a local spend guard hard-stops at $10 by default. Windows only; needs the Muse Code CLI installed and signed in. The $10 cap is a local estimate for the muse serve this plugin starts.

Adds a draggable lucky-block button to the DeepSeek Harness web UI. Single-click plays zero-cost little performances (popups, a fake blue screen, daily fortune, trivia, cold jokes, music, and a set of visual stunts); a 1.4-second long-press mines the block open and starts a new session to write a random paper, read the news, invent something, or spin a short story. It also appends a "lucky block" choice to the model's multiple-choice questions and rolls a random pick, reversible by saying "rollback". Block appearance and event weights are adjustable in settings.

Mobile web UI for DeepSeek Harness: a token-protected LAN server that lists all sessions, streams replies over SSE, and lets a phone continue any conversation; the desktop GUI shows a QR entry and, with dsh-whale-girl 0.3.0+, a phone held by the pet opens the same panel.

Synchronize DSH sessions, settings, attachments and project files using a user-configured private HTTPS Git repository or SFTP, with safe-scope online application, offline restore plans and user-confirmed plugin updates. Requires Node.js 24+; the SFTP path also requires OpenSSH (ssh/sftp).

Replaces detected secrets (OpenAI, AWS, GitHub, PEM, Bearer) with deterministic, structurally valid honey tokens before they reach the model or the session file; adds manual marking for values the detectors miss, explicit user-visible restore, a cross-session canary alarm, and an opt-in JSONL log of substitution counts that never records the underlying values.

List the LLM provider routes a running DSH process registered and run one real streamed call.

Turn-end quality gate: when the turn edited code or config it walks each file up to its project root, runs that root one check from a fixed whitelist (`pnpm check`, `cargo check`, `ruff check .`, `tsc --noEmit`) and, only if that check really ran and failed, opens a new turn carrying the failure output instead of letting the turn close.

Training Lens opens a local TensorBoard scalar dashboard with selectable metrics, explicit improvement direction, optional EMA smoothing and Chinese/English UI; requires an existing Python environment with TensorBoard.

Syncs DSH model providers and models across computers through any WebDAV server: the backup is sealed with a passphrase before it leaves this machine, so a new machine opens with the same model list.

Windows desktop notifications with selectable sounds: five bundled sound packs (45 clips) plus imported audio, one sound per event, and clicking a notification opens the matching session.

Daily AI digest by email: fetches ten sources (OpenAI, Anthropic, Google DeepMind, Hugging Face, arXiv, Hacker News and others), clusters near-duplicate stories, scores them in code and with an LLM, then emails the top three on a daily schedule with a four-part reading (facts, why it matters, impact, open questions). Adds four conversation tools and a sidebar panel for previewing the digest, sending it now and changing the schedule.

Reports DeepSeek Harness session state (working, done, error) to the agent-pet macOS desktop overlay and lets it open sessions or start a chat.

Bidirectional dispatch for DSH: opens visible desktop sessions for tasks dispatched in by Grok Bot / Yobiru, adds /dispatch-grok and /dispatch-zcode slash commands to send tasks out, and reports the session result back to the dispatching peer on completion (peers are user-configured; nothing is sent until configured).

Scheduled tasks: run a prompt on a fixed interval, each run opening a fresh session, with a run history.