Plugins

API Hub — manage and call local API providers (keys, models, balances) and skills from inside DeepSeek Harness

A searchable, provider-grouped replacement for the DSH composer's model picker.

Code-generated math and science animation for DSH: six tools cover environment checks and dependency self-repair, Manim/manimgx scene rendering to storyboard frames or MP4, contact-sheet probing of finished clips for black or overexposed frames, and formula identity checks with SymPy, together with three skills (topic routing, design spec, QA rubric), a project scaffold with timeline and narration, requirement approvals before rendering, and five animation styles.

DSH Web 插件：实时显示模型供应商额度与用量（DeepSeek / GLM Coding Plan / OpenRouter / Kimi Coding Plan + 自定义适配器）

DSH-Search-Contrl: a DSH skill/plugin for scoped web search and Chinese daily reports, with a settings GUI for custom search sources, arbitrary topics (not only tech), creator-link scoped search, and one-click rollback.

Read local EPUB, TXT and Markdown novels below selected native DSH chat regions on explicit expansion, preserving real reasoning and tool output without sending novel text to the model. Requires DSH >=0.2.1-rc.2 <0.3.0-0.

Reads one Genshin Impact account (characters, talents, weapons, artifacts, wish history) into a single snapshot, then exposes it as six agent tools and a six-tab panel. Artifact substats come from the public in-game character showcase; scoring ships both CV and per-character weight models with six grade tiers; wish analysis covers pity, luck tiers and per-pool progress. Needs a Miyoushe QR login to read characters, weapons and wish history; showcase data is public by UID.

A chibi whale maid desktop pet for DeepSeek Harness who eats white rice while the model generates, lives inside the DSH window or anywhere on a macOS or Windows desktop, and dives for treasure between turns. On Windows the desktop overlay is compiled at install time and skipped when swiftc or the .NET SDK is unavailable, so the pet stays inside the DSH window.

No longer updated: folded into dsh-lifeguard (last release 0.2.2). It checked a plugin against what was installed and flagged only real conflicts.

Turns a phone into a personal assistant for the DeepSeek Harness on your computer — pair once by QR code, then chat, send photos and files, watch replies stream, and collaborate from several phones at once over LAN, Tailscale or a public tunnel. Ships an Android app, an iOS build pipeline and a zero-install web/PWA client for HarmonyOS and iOS browsers.

Store SSH hosts in an AES-256-GCM vault and let the agent run commands on them by alias, with passwords handed to ssh through SSH_ASKPASS instead of the command line. Windows only.

Work on any machine in your ssh config as if it were local: persistent connections, native file editing, search, exec and terminals, with nothing installed on the remote host.

Open a Mac or Windows DeepSeek Harness Web instance from iPhone or iPad Safari: 8-digit pairing, a LAN gateway for loopback-only hosts, optional Tailscale Serve, and iOS-only Safari input and touch fixes. Installs with dsh plugin add.

Permission guard for DSH: four scopes with read/write/execute bits in the native permission menu, plus an optional Jev semantic classifier for bash commands.

Audits the skills and plugins you already installed: routes a task description to the tool it needs, flags version drift against the npm registry and runtime faults from host logs, and reports which of a plugin's tools you never call. Registers 9 tools: can, find, status, recommend, check, scan, probe, run and suggest. Runs on Python 3.8+ with no third-party dependencies. Registered tool ids all carry the skill_audit_ prefix, for example skill_audit_can and skill_audit_find.

Restart button for the Harness desktop app: one sidebar entry that closes every Harness process and starts the application again, launched without a console window and without a close-confirmation dialog. Windows only.

Restart control for the DeepSeek Harness desktop app on Windows. A session header button or a tray icon stops the app and its host process, waits for both to exit, clears a stale profile lock, and relaunches, so a newly installed plugin loads without quitting the app by hand.

Read-only static checks for DSH profiles, bundle resolution, version compatibility, patches and MCP name conflicts, with pre-install candidate checks.

Windows toast notifications for DeepSeek Harness: approve or reject from the notification while DSH is in the background, with an in-app fallback; foreground only skips the current conversation, while other conversations still notify. Also reports turn completion and errors; subagent sessions stay silent.

Message hub for DeepSeek Harness. Collectors for system health, weather, IMAP mail and market events feed configurable severity rules (critical wakes you, warn batches, info is only logged), and the surviving events are handed to the agent. Collectors run in-process, so nothing dies silently in a stray daemon. The weather collector is on by default and sends your IP to ip-api.com over plain HTTP unless a city is configured.

Nudges the main agent of a long-running DSH session to report progress at a configurable interval, with exponential back-off, stuck detection, a per-session Progress tab, and a manual "nudge now" action.

Desktop notifications for DSH Web sessions: browser notifications plus Windows toast when a session finishes, fails, needs an approval, or asks a question. Clicking one opens the session; browser notifications focus an open tab, Windows toasts open a new tab.

A Git graph plugin for DSH: repository tree and SVG lane history (curves, merge diamonds, ref badges, terminus notches, export) in a dsh-better-sidebar tab, plus conventions that reach the model - seven built-in frameworks (or your own templates, hidden built-ins), injected into every model step and checked against the last 20 commits. Shares the /git prefix with the upstream plugin, so pick one.

Novel writing panel for the DSH sidebar that binds a local manuscript folder, imports Agent Skills as analysis lenses, and scans platform rankings into story-structure outlines.