Plugins

Waifu mode for QQ: splits every reply into several short chat bubbles with a human-like typing delay, drops trailing periods, and keeps tables and code blocks intact. Works by patching @tencent-connect/dsh-qqbot in the desktop profile: run node outbound/apply-patch.mjs once, set im-qqbot streaming: false, then restart — until then only the waifu_* tools work.

Two columns for the dsh Plugins page, Minecraft resource-pack style: the left column holds the packs running together, the right holds packs that are installed but switched off, with arrow or drag moves between them, custom tags, search, scope filters, batch toggling and undo. Tags and display names live in a hand-editable packs.json under DSH_HOME instead of browser storage, so they survive a new browser or cleared site data.

The mobile client for DeepSeek Harness: use the DSH running on your computer from your phone. The Android app signs in with the same account, picks this computer from the device list and opens its DeepSeek Harness UI on mobile. The desktop plugin handles registration and the connection, and nothing on the computer needs an inbound port. The UI adapts on its own: on a phone it becomes a touch-friendly layout, and returns to the desktop layout when a foldable opens or the window gets bigger. A PC-side panel shows login state, device quota, device list and the app download QR code.

A Feishu/Lark channel for DeepSeek Harness: WebSocket inbound messaging, Markdown tables rendered as native Feishu table components, 13 Feishu tools, a web settings page, voice input/output, media upload and a model fallback chain.

Remote control for DeepSeek Harness over an outbound Huawei Cloud DevBridge tunnel: a sidebar seat and a standalone control page start and stop the tunnel and show its public URL, QR code and logs. The plugin's own gateway stays on 127.0.0.1, checks a rotatable access token or HMAC session cookie, rate-limits failures and strips external identity headers before forwarding to DSH, so no inbound port is opened. The tunnel is off by default; tokens and state stay under ~/.dsh. Requires a Huawei Cloud account and devbridge CLI v0.2.x. The relay terminates TLS and can see plaintext HTTP — this is access control, not end-to-end encryption.

Audits and evolves agent context at four scopes: a single repository, a group of related repos, a knowledge hub, or the whole machine. Discovers projects, instruction files, skills, tools, knowledge, project state, evidence and credential references; reports drift, duplicate facts, broken pointers, budget overruns, unindexed knowledge, stale state and unregistered credentials; scores each scope on the dimensions that belong to it; and turns findings into reviewable migration plans that back up every file before moving it. Also scaffolds a deliberately small hub for durable knowledge and project state. Ships a stdlib-only Python CLI plus two skills, with credentials referenced by path and never printed. Requires Python 3.9+ (stdlib only) and DSH 0.2.1-rc.2 or newer.

Screen frames, log lines and (on Windows) key/mouse input on one millisecond timeline: record, mark the failing seconds, box the problem on the frame, then hand the agent a keyframe strip, an animated GIF and the aligned log slice.

Sends DSH task summaries and host event alerts (approval, question, plan confirmation) to a saved Feishu recipient, with an enable switch, quiet hours, and status/test/configure tools.

Registers the github-push skill so every session follows one fixed commit-and-push flow, with a pre-flight secret scan, an abuse-resistant retry policy, and local-proxy discovery when github.com is unreachable directly. Runs on Windows only: the push skill uses Windows PowerShell 5.1+ and curl.exe.

AI-native iteration cycle: 24 anic_* tools and 77 HTTP routes that run evaluation, convergence gates, and auto-fix loops across projects, with a live white-box panel (interactive workflow graph, invocation feed, autonomy gauge, gate ledger, HITL queue) and an inline installable SKILL.md workflow kit.

Turns your local WeChat group chats into a followable todo board: a three-column kanban (todo / doing / needs you) with LLM summaries, automatic flagging of messages that @-mention or reply to you, drag-to-change status, and local-only storage. Needs a local Python 3 with sqlcipher3 and zstandard, plus the existing rion-wechat-reader config.json and keys.json for the WeChat databases; the plugin does not extract the keys itself, and summaries send the quoted chat text to the model you choose.

Configurable serial agent-team workflows with a Manager, role Actors, an independent Judge, and a visual workflow editor.

Todo plugin that records when each task is created and completed, with table, kanban, gantt and calendar views over the same data, categories, priority and type, @workspace-file links, JSON/CSV import and export, and a todo_time_log agent tool with /todo commands.

Manages reusable agent role templates (job prompt, model and reasoning effort, tool allowlist, skills) and starts role members through the native Agent Team interface to delegate and continue tasks.

Reusable experience for DeepSeek Harness: save a successful task as a structured playbook, recall it later as a native skill, and gate deliveries behind user-confirmed checks that require objective evidence before write actions are allowed.

Manage local skills across AI agents with version comparison, shared-directory consolidation, and recoverable migration and deletion.

Hold Space to record and release to transcribe and send, without focusing the composer first. Esc cancels and window blur auto-cancels. Requires the official voice-input bundle (`@deepseek-ai/dsh-experimental-voice-input-bundle`) enabled with its speech model downloaded; otherwise Space is left alone.

Ask a vision-capable model about a local image from any session, including sessions whose own model is text-only. On the default path the plugin calls the host's route in-process with ctx.llm.stream(), so the host's credentials stay inside its provider adapters; only the optional direct/custom OpenAI-compatible routes read one key (from the plugin config or an apiKeyRef into ~/.dsh/.credentials.yaml).

Image generation and editing with configurable APIs, reference images, and an on-demand annotation canvas. Requires your own OpenAI-compatible image API endpoint and key.

Zero-dependency browser hand & eye over CDP: drives your own Chrome/Edge with real clicks, Chinese IME typing, scrolling and text/selector element picking, and captures whole-page evidence into one replayable folder — DOM, accessibility tree, screenshots, cookies, storage, console, HAR, resource waterfall and perf metrics.

A self-justification gate for outbound claims: a claim needs a checkable source (an http(s) URL plus a quote of at least 8 characters), every number in the text must appear in a quote, and a quote whose vocabulary overlap with the post is under 10% counts as an invalid citation; absolute wording is rejected when the only evidence is second-hand. All verdicts come from deterministic rules — no model call, no network. The guard subcommand refuses to run the publish command when the gate fails (fail-closed), explains what is wrong and how to fix it, and requires an --ack note on the second attempt stating what changed; after three attempts it stops and hands back to a human. Ships check / explain / fix / guard, with 30 tests.

Run AI commands in real NyaTerm terminal sessions, reusing saved groups, jump hosts and local terminals, with a per-workspace allowlist; commands stay visible and auditable in NyaTerm.

Scans your Bilibili follow list, marks accounts that are closed or have posted neither a video nor a dynamic for a configurable number of days, and unfollows only the ones you confirm, skipping mutual follows and anyone who has streamed.

macOS computer use with eight computer_* tools: accessibility-tree and Vision OCR screen reading, actions by element index or visible label that also reach background windows, and CoreGraphics mouse and keyboard events with a resident low-latency daemon for game-grade input sequences; its Swift helpers compile on first use, so there is no runtime dependency.