Plugins

Windows file search + document full-text search: names via Everything (es.exe), text inside PDF/DOCX/XLSX/PPTX/EPUB via Anytxt; both installed separately.

Aggregates every WorkBuddy account already signed in on this machine into one model pool, with manual and scheduled check-in, credits and expiry monitoring, per-model credit multipliers, and account switching with remaining credits right below the composer.

CET-4/CET-6 vocabulary trainer in a draggable, minimizable floating window: 5,805 words bundled from ECDICT; flip cards graded known/fuzzy/unknown and multiple-choice quizzes with look-alike distractors; Ebbinghaus spaced repetition; configurable daily quota; online human US/UK pronunciation with offline TTS fallback; an ambient "loop reading" mode (word / word+meaning / word→meaning→word, with example sentences from a dictionary API + Tatoeba). v0.2.4 adds a "Cut" action that moves mastered words into a low-frequency maintenance pool with 15/30/60-day checks and recall instead of deleting them, a maintenance-check badge, and a UI polish pass (design tokens, fewer borders, consistent focus/press feedback, reduced-motion support). Progress and window geometry stay in the browser profile and survive updates.

Your phone, live in the DSH right sidebar: one UI read costs 120 ms and 200-1300 tokens, where a screenshot costs 0.5-3.2 s and 1.5-2k image tokens; a tap lands on the real device in 61 ms, and a circled area comes back with its controls. You can tell what is on screen, and whether a tap landed, without a screenshot. Needs adb and ffmpeg on the host; the OCR fallback is macOS-only.

Adds a Restart button to the DeepSeek Harness title bar so newly installed plugins can take effect. The first click arms the button and the second one ends the current desktop instance and relaunches the executable. The restart runs in a PowerShell script created through WMI, outside the application job object and without a console window, and every step is written to $DSH_HOME/logs/dsh-restart-plugin.log. Windows desktop app only.

Layered long-term memory for DeepSeek Harness: a ~600-character hot layer that evicts its own overflow, month-archived cold entries recalled by keyword and ranked by usage, and extractive day/week/month summaries.

Folds oversized tool results into on-disk spill files with deterministic head and tail markers, indexes compaction summaries in a searchable ledger, and extracts cross-session memories with per-project scoping. Any folded content is restored byte-for-byte on demand through one tool call.

Registers the models bundled with the Xunfei Loomy desktop app as a `loomy` provider in DSH, reading the app's local sign-in session instead of an API key. Fork of gdrpzym/dsh-loomy-connect adapted to DSH 0.2.1, adding a per-model enable/disable switch. Requires the Loomy desktop app installed and signed in; it cannot be installed alongside gdrpzym/dsh-loomy-connect because both register the same `loomy` provider.

Brings the models available in the logged-in WorkBuddy desktop app into the model picker, reusing the app login and credits; the domestic and international builds appear as two separate provider groups. Continuation of the now-deleted corrinehu/dsh-workbuddy-connect; it registers the same workbuddy / workbuddy-ai provider ids, so it cannot be installed alongside other WorkBuddy bridges.

Multi-channel IM bridge for DeepSeek Harness: each QQ (SnowLuma / OneBot v11, official QQ Bot) or Discord group and private chat becomes its own agent session, bound to a role card whose domain carries knowledge bases with draft approval, shared memory, a read-only GitHub reader and group trigger rules; two built-in personas (customer support, group chat), unified push with broadcast, and human hand-off.

ShaderToy backgrounds for DeepSeek Harness: a WebGL2 player with a background library and five bundled presets, adjustable opacity, brightness, resolution and frame rate, playback options, and an in-app editor for the running shader.

Removes the inherited ELECTRON_RUN_AS_NODE variable from the environment the open-in-app package hands to launched editors, so the desktop host's "Open in ..." launches stop failing with HTTP 502 launch-failed; app.asar is untouched.

Draggable bubble graph of DeepSeek Harness workspaces and sessions in the Web UI: workspaces are large bubbles, sessions are small ones, and lines show real membership. The canvas supports pan, zoom and fit; filters cover workspace, status, type and archive state; search covers workspace names, paths and session titles; native actions open or create sessions, rename workspaces, and archive or restore sessions. Layouts are saved in the browser.

Control plane for the harness's own Agent Teams: members are ordinary independent sessions created through the same seam the GUI uses, each with its own model, so they open and continue like any other conversation while a sidecar roster and task board coordinate them. Task entries carry a definition of done, a member's completion is submitted and waits for the Lead's review, and availability tells idle apart from awaiting-review or a failed last turn. With delegationEngine=auto it uses independent sessions, continuable subagents, or the kernel roster depending on what the composition provides.

Builds presentations by driving the LibreOffice installed on the machine over UNO instead of writing OOXML in JavaScript: `lo_build` opens a real Impress document from structured slides and lets LibreOffice export editable PPTX/ODP plus PDF and per-slide PNG, `lo_render` re-renders an existing PPTX/PPT/ODP, `lo_convert` converts between Office formats, `lo_probe` reports the detected soffice path, version and UNO bridge, and `lo_config` edits the stored settings. Needs a local LibreOffice (verified on 26.8.1.1); it uses the bundled Python, so no system Python is needed, and it keeps one warm soffice process between calls. Fully verified on Windows only; on Linux it falls back to the system python3, which needs python3-uno.

Keeps heavy tool groups out of every request, and can scope tools per session or per role: the role key comes from the host's own session label, subagent marker or preset, so an orchestrator's child agents each see only their own group allow-list. Also auto-groups new tool families by name prefix, lets the agent classify ungrouped tools once, brings a hidden tool back when it is actually called, and exposes a health snapshot of what each session can really see.

Homepage-style chat background skin for DeepSeek Harness, ported line by line from deepseek.com/harness: WebGL fluid background (5-colour noise field, flow-field brush, light, bloom, vignette, grain), white 90px dot-line grid with mouse perturbation and spring return, and a digital point-cloud whale that assembles from particles, breathes, swims, is pushed radially by the cursor and brightened by a light beam. Dark theme only; disabled automatically under reduced-motion.

A Versions tab on the Plugins page: one-click upgrades that replace the plugin in place where they can (no uninstall, enabled state preserved, falling back to remove + reinstall with the reason logged when the profile writer lock is busy), live pnpm output with per-step timing and cancel, the full published version history with one-click rollback, every version checked against the running DSH so incompatible ones are marked and blocked, a rollback that installs the old version but cannot activate it reported separately from a lost package, profile manifest writes taken under the harness writer lock with one recoverable journal record per package after a failed upgrade, mirror-gap warnings, and a selectable npm registry saved in the profile.

Windows desktop notifications for DSH that speak the turn result by default: Windows TTS needs no download, and 13 VOICEVOX voice packs can be installed from the settings page. A completed alert waits until running subagents and background jobs finish; approval, question and error alerts fire immediately. Voice packs are downloaded from GitHub after a terms confirmation.

Windows toast notifications for approval requests, questions, completed or failed runs, and sign-in prompts; clicking a notification reopens the conversation that raised it, and toasts are attributed to the DeepSeek Harness app identity.

Eight academic skills bundled for one-command install — publication-ready academic figures designed from real data with visual review, AI-text humanization, paper polishing and rewriting, PubMed citation verification (DOI/PMID reconciliation), Chinese citation and medical-book reference checks, and WeChat medical article structuring. Three skills run fully local, five call external services only when used (NCBI E-utilities, DOI resolvers, publishing platforms), declared per skill. Zero telemetry, no install-time scripts. Skills run local Python 3.8+; the academic-figures skill also needs its pip dependencies installed.

A DeepSeek Harness (DSH) plugin that lets you control Universal Robots (UR) collaborative arms directly from natural language — by default an offline, kinematics-level simulated arm, with a real-robot channel that stays off until it is explicitly enabled. Needs a Python install with numpy and paramiko (pip install -r requirements.txt). Developed by Suzhou Nonead Robot Technology Co., Ltd. based on the same logic as the company's own nUR MCP Server. (Suzhou Nonead Robot Technology Co., Ltd.)

MCP server manager for DeepSeek Harness settings: add streamable-http or stdio servers, paste Postman-style headers, test connectivity, and toggle each tool so disabled ones never reach the model.

Continues work across coding agents inside DeepSeek Harness: six sessionflow_* tools query a local session index built by sessionFlow to find past work, show where the current project left off, and hand the goal, files and open items to the next agent. Requires the separate sessionFlow core, installed from its GitHub repo. Everything stays local — no cloud, no telemetry.