Plugins

Bridges DeepSeek Harness lifecycle status, errors, and approval requests to a locally running OpenPets desktop companion.

Open dsh web from your phone or another computer through a UUMit account, without running your own server or installing another program: a built-in tunnel client connects to UUMit's hosted tunnel, and a panel in the sidebar handles pairing and who can use it (only you, people you invite by link or phone number, or everyone), with revocation. Requires dsh web on DSH >=0.2.1-rc.2.

Read-only Molio knowledge base tools: list vaults, browse the file tree, full-text search and read documents, served over the local Molio daemon HTTP API, which must be running. Published on npm as dsh-plugin-molio.

Adds an animated DeepSeek Chan reasoning-effort slider to DSH's native model selector, following model-declared levels with a running animation that speeds up while dragging.

Turn your phone into the control center for an AI coding assistant CLI session (Claude or Codex) running on your computer.

Adds a Managed Agents settings tab and MCP tools to dispatch long-running agent tasks to Ark cloud Managed Agents.

Consumer panel for OpenBiliClaw inside DSH: a right-hand drawer with recommendations, saved lists, Socratic dialogue, profile and settings, plus 22 Agent Bridge tools so the agent can read recommendations, answer probes and save items. Requires a running OpenBiliClaw backend with Agent Bridge v2 (default 127.0.0.1:8420).

Cleans the harness prompt-authority layer into a reviewable patch set, writes prompt-inject.md and lets each model use a different default prompt, reports which patches took effect and whether the running host loads app.asar or an unpacked tree, and swaps a sealed install to the patched tree once the desktop process is idle. Includes a status page and the dsh-purge CLI.

A persistent agent team for long-running collaboration in DeepSeek Harness: durable agent identities, per-project Workspaces, responsibility-bearing Channels, and Task Threads chaining session agents.

A personal usage profile page in the DSH sidebar, folded from this machine's own session logs through ctx.sessionQuery. One range switch in the header (7 / 30 / 90 days or all time) drives the page: five headline numbers (tokens in that range with a trend line and the change against the previous period, today's tokens, longest task, longest and current active-day streaks), a 12-month activity grid in daily / weekly / running-total views, a stacked model-family chart for the same range by day, week or month (version and tier stay apart, and vendor-specific ids collapse correctly), a Cache Lens that shows the cache hit rate and splits tokens into cache hits, uncached input and output with a zoom into the uncached part, and a per-provider split with each route's own hit rate. The selected range exports as CSV or JSON. The only outbound request is a six-hourly read of this package's own version from npm for the in-panel update button - no telemetry, no credentials, nothing uploaded.

Reference logged-in Chrome/Edge tabs, authorized local HTML and running Windows apps through a searchable native sidebar or @. Open browser candidates and the webpage sidebar refresh when the extension connects, disconnects or changes tabs, including an unchanged search query. Windows application lists skip protected processes with unreadable identity metadata and preserve other running apps. Read scoped snapshots, batch actions, capture screenshots and use available WebMCP tools; supports authorized uploads, drag/drop and opt-in network metadata. Browser actions preserve failure evidence, accept an explicit post-action observation scope and can check one final visible/text/value/URL condition without replaying effects. Expandable context preserves model content; dockable annotations support a session-bound staging queue with edit/delete/restore, and append to chat drafts without sending. App control prefers a matching installed MCP or approved installation, then Cua Driver with text, hotkeys and paged controls; desktop reads present the window once per connection or when recovery is needed. Background input depends on the app. Requires Chrome or Edge 125+ with the companion MV3 extension manually loaded and paired; installing the plugin does not install the extension.

DSH↔Godot engine runtime bridge: launch and drive a running Godot 4.x game through its in-game TCP interaction server — 16 tools (runtime control via ~130 game commands, scene/UI inspection, GDScript eval, input simulation, screenshots, headless static ops, project editing, export, script validation, engine-path setup), replaces godot-mcp.

The desktop app has its own refresh button. Edited a plugin but a run is still going? Refresh. Window sluggish after hours of use? Refresh. One button fixes both — running sessions, queued messages and drafts are untouched.

DeepSeek Harness plugin: start a page-harness share preview from DSH so teammates can review a running page

IM Companion for dsh-im: groups Feishu/WeChat/QQ bots by Agent in DSH workspaces and enhances DSH native session states (blue/orange/red rail markers for running, needs-review and error), with left badges, one-click filter, fleet overview and drag-to-move. Clean uninstall.

Select text in a committed DSH response to open an independent, persistent, read-only multi-turn Topic bound to source-session evidence and project files while the source Agent keeps running.

Full-duplex voice mode for the DeepSeek Harness Web UI: toggle (2s-pause auto-send) or hold-to-talk dictation into an editable draft with zipformer2 streaming ASR, optional wake word; sentence-by-sentence Edge TTS read-aloud with live captions, and speaking interrupts playback and the running turn (true barge-in). On-device ASR, no API key.

Live subagent run monitor for the Web UI: a sidebar footer trigger plus a fixed top-right card panel showing each subagent of the current session in real time (running/elapsed, terminal outcomes, tree indent), with one-click jump into the child conversation and a return button, refresh-surviving and mobile-hidden by default.

DeepSeek Harness bundle registering one skill that turns long-form production (academic papers, industry analysis, business commentary) into a 9-role pipeline: T1 literature / T2 data / T3 case scouts running in parallel, T4 analyst, T5 writer, T6 critical companion, T7 auditor, T8 finalizer run by the coordinator, T9 peer reviewer — across 6 phases with triangular evidence verification, a 26-check M-gate (25 scripted checks plus one human checkpoint), a G0-G16 audit including a Chinese AI-trace gate, peer-review scoring with journal matching, and 4 human checkpoints. Installs with `dsh plugin add lunheng-article-pipeline` (package.json#dsh.bundle.patch plus a lib/index.js entry that registers the skill); ships role cards for T1-T9, templates and 36 zero-dependency verification scripts, with five-language READMEs.

DSH-side remote session driver for the dsh-overdrive chat gateway: exposes sessions, trajectory replay and tap-to-approve to Telegram / Discord / Slack / WhatsApp / Feishu / DingTalk / WeCom bridges. Requires running @dsh-overdrive/gateway alongside.

Connector only, it renders nothing itself: subscribes to DeepSeek Harness session events and folds them into a 12-phase work state (planning / thinking / executing-tool / streaming / waiting-input / voice / awaiting-approval / complete / error / paused / idle / heartbeat), then POSTs each phase to a desktop-pet backend at http://127.0.0.1:8000/api/plugin/dsh/ingest. It holds no window. No API key or token is needed. Requires the Mao Live2D pet application to be separately installed and running (that is a Windows Electron app with its own PowerShell 7 / Python 3.10+ / Node 18+ prerequisites); without it this plugin has nothing to push to.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

A better fold bar: automatically folds tool calls and Think segments into step fold bars, and collapses each finished turn into a single turn header with live metrics (duration, TTFT, token, tok/s, cache hit) — only the final summary stays visible; customizable leading icons with animated poker cards built in (suit-cycling card animation while running, a deck when collapsed, a fan when expanded), a settings row for the official fold mode, compatible with both new and old DSH versions. Zero intrusion into DSH source.

Connects DSH to a local anet node through a stdio MCP client, with three skills and 14 tools to discover agents on the AgentNetwork, send, track and answer end-to-end encrypted A2A tasks, pay or decline priced skills within the operator's limits, read the local evidence chain and report the node state. Linux/macOS only; requires an anet 0.3.0+ node running locally.