Plugins

During long agent thinking, posts a hot-news or reminder message directly into the conversation stream.

Tiered model routing for DeepSeek Harness: think/build model tiers, vision delegation (the vision model only describes images; the working model acts), image generation, and a high-impact guard.

Rotates the model status line through a 53-phrase English/Chinese deep-theme pool: a random pick at turn start, event-driven switching on new thinking segments or tool calls (3s throttle), and a click on the status line toggles the language.

Type normally; about two seconds after you pause, it rewrites your draft into a clearer, first-person version more likely to get a good answer, leaving pasted code, links and long text untouched, marking missing details as placeholders instead of guessing, and keeping multi-part questions numbered.

WeChat iLink ClawBot bridge: official Tencent iLink protocol, Web UI settings (QR login / model / preset / permissions / session management with delete), 24h auto-renewal pushes a fresh QR before expiry, zero downtime.

Publish TXT, Markdown, HTML, PDF, Word, and PowerPoint files as ShareOne links with passwords, watermarks, text-page updates, and TXT/Markdown/HTML comments.

DIT.ai provider bundle for DeepSeek Harness: installs 29 OpenAI Chat Completions models and 10 Anthropic Messages models from one DIT_API_KEY, with protocol-specific thinking configuration.

Animated DeepSeek blue-whale desktop pet floating on the DSH Web page: draggable with speech bubbles and mood poses, a pet_say tool for the model to make it talk, and turn-start/end thinking and celebrating states.

A draggable mascot invites you to play Xiangqi (Chinese chess) while the AI thinks, with a built-in engine, move-record export, and optional multi-model commentary.

Dynamic Schulte grid waiting-time mini-game: click 1..N in order on a static grid or a spinning roulette wheel while the model thinks.

Track human decisions for related DSH session branches: keep, discard, or follow up with reasons, labels, and external links.

Ctrl+click file paths and links in chat: paths open their folder in the OS file manager (with the file selected), links open in a new browser tab.

Interactive terminal chat app for dsh: streaming conversation, tool cards, jobs panel, full-text search, trajectory replay, multi-session tabs, and A2A dispatch (Ink-based).

A hands-off safety net: directories the agent deletes go to a trash folder first and symlinks are never followed, with zero approvals.

Pi TUI (differential-rendering terminal framework) front end: streaming markdown, thinking collapse, tool cards, slash commands, approval/question overlays, shared dsh session store.

DeepSeek Harness plugin: per-request thinking-mode switch (enable_thinking) for Qwen3-family models on OpenAI-compatible endpoints

Multi-node DSH monitor and control hub: per-node status and read-only sessions, zero-config LAN networking via UDP discovery, one-click/embedded access to a real DSH UI, cross-network remote hub via outbound push, serverless invite links/IPv6, and opt-in plugin toggle/restart behind dry-run, confirmation and a JSONL audit log. By default it listens on :: / 0.0.0.0 for LAN discovery, with token-protected status and control routes; its HTTP routes have no DSH access check.

Create timed product video scripts with shots, voiceover, and captions, and link to the Zhixing Ark content workspace.

Cross-session memory for DeepSeek Harness: three-way recall (BM25, dense vectors, and Personalized PageRank over a memory graph) fused with RRF, emotion as a modulation multiplier, power-law forgetting with five sinking layers, and an interactive memory star map. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

Broadcasts the current session's effective model selection as a window event at the moment it changes, for consumers that need the selection before the first request round, such as a balance widget switching its accounting endpoint.

Video analysis panel in the DeepSeek Harness sidebar. Paste a YouTube or Bilibili link to fetch its subtitles and generate a summary, chapters, a mind map and citation-backed Q&A over the transcript, with an embedded player whose timestamps jump to that moment and keep playing. Videos without subtitles fall back to local Whisper / SenseVoice transcription (audio stays on the machine); silent videos fall back to frame OCR with macOS Vision, or to vision-model frame descriptions. Per-video analysis caching, a 20-item history, and two agent tools: video_digest and video. A Bilibili SESSDATA cookie, if you enter one, is stored in ~/.dsh/video-credentials.json (mode 0600), transcripts are sent to your current model, and its HTTP routes have no DSH access check.

Evolution mode in one package: a thinking mode that aligns on your goal and boundaries each turn plus the task tree, profile injection and panel, alignment-bar styling, self-check tools and plan-mode entry — install one package and you have the whole set. It helps the model understand requests more accurately, get noticeably better results at the same cost, and build a long-term profile of your preferences. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

Connects personal WeChat direct messages as a dsh-superagent Source, so private-chat text becomes a trigger for the orchestrator, accepted tasks run as work orders, and results are replied to the same chat; group and non-text messages are dropped. Only WeChat users on the superagent policy's allow-list are assessed; the list is empty by default, so every DM is ignored until you add your own ilink_user_id.