Plugins

给 DeepSeek Harness（DSH / DeepSeek Hermes）加语音能力的社区插件：输入框语音输入（可配快捷键）+ 回答朗读（微软 Edge 神经网络音色，可换音色、可试听），无需 API Key。

DeepSeek Harness plugin: serve LLM calls with the OAuth tokens your local Codex CLI and Claude Code already hold, instead of a separately configured API key.

DeepSeek Harness (DSH) plugin — inject context when user input or model output hits configured keywords, with toggleable/configurable rules and model-editable memory.

Silence Chrome/iCloud password-manager prompts over DeepSeek Harness API-key inputs: rewrites password-type secret fields into masked text fields so browser password managers never treat DSH API keys as account passwords.

LLMTR AI gateway provider for the DeepSeek Harness LLM seam: 170+ chat models and Türkiye-hosted LLMs behind one OpenAI-compatible key

DeepSeek Harness (DSH) 原生全功能终端交互界面 · Keyboard-first Terminal TUI for DeepSeek Harness

中国实时热点数据采集器：微博/百度/B站/知乎热搜、App Store 榜单、QQ音乐榜等，免 API Key。Tool + skill bundle for DeepSeek Harness.

DSH plugin: loopback WebSocket bridge that mirrors application frontend tools onto the agent's tool registry and forwards model calls back to the application — one bridge, many apps, key-based namespace isolation

S3-compatible backend for the spill seam: oversized tool output goes to object storage (S3, MinIO, R2) with hashed session prefixes and unguessable keys, instead of the agent's local disk.

Dependency-topology guard: pre-install conflict prediction and post-install detection of duplicate @deepseek-ai/dsh-* copies, version drift, and vendored core services that cause Symbol-key crashes like "Cannot read properties of undefined (reading 'prepare')".

Ecosystem trend dashboard (行情面板): snapshot the dsh-plugin topic and the awesome list into local history, then report weekly trends — new plugins, star gainers, category heat, awesome coverage — plus a keyword radar for new plugins and star surges.

Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).

Notes and todos as plain Markdown files in your workspace: type /ml plus a sentence to jot into today's journal; todos come in three flavors — deadline, sleep-until-a-date (auto-wakes when due), and anytime; /ml view fuzzy-opens any file with a few keystrokes. Zero tokens throughout — nothing goes through the model, and your notes stay ordinary local files that git and any editor can read.

Nexterm fleet maintenance in a DSH session: 6 agent tools (auth with password/TOTP/device-code login, fleet listing, single-host exec, parallel batch exec, preset health checks, CPU/memory/disk monitoring) over the Nexterm REST API, plus a minimal settings page; no SSH private keys needed on the DSH machine.

Desktop (native) control for dsh as a stdio JSON-RPC bridge over a Python core: capture the screen, inject pointer/keyboard input, drive accessibility-tree actions, and gate high-risk operations behind required confirmations.

Connects DeepSeek Harness to AsimovBox for creating, updating, rendering, and finishing videos through API-key-authenticated tools.

Education toolkit for DSH agents: lesson-plan skeletons by grade band, quiz scaffolding and answer-key validation, analytic rubrics, Anki/markdown flashcards, and readability levels.

Write notes and memos to flomo (浮墨笔记) from any agent via the flomo_send tool, configured once with the flomo API URL or API Key.

Two-phase session captioning: instant keyword titles while the conversation is busy, then cheapest-budget-model refinement plus a one-line summary once it goes idle.

Standalone arrow-key input history for the DSH web composer: ↑/↓ recalls sent prompts from one global ring shared across all sessions and workspaces, persisted to localStorage with an overridable cap.

Ein LAN-Passwort-Gate für die Web-UI: Smartphones und Tablets im selben Netzwerk melden sich mit einem gemeinsamen Schlüssel an und sehen dieselben Sitzungen in Echtzeit, mit integriertem randomUUID-Polyfill für reine HTTP-Origins.

Kontingent-Monitor für die DeepSeek-Harness-Web-GUI: OpenCode-Go-Tarifnutzung + DeepSeek-API-Guthaben/-Nutzung, als verschiebbares Monitorfenster unten links (die Host-Seite leitet API-Aufrufe weiter, Schlüssel bleiben auf der Festplatte).

Plugin zur Abfrage der OpenCode-Go-Tarifnutzung: das Tool opencode_usage fragt live die offizielle opencode.ai-Nutzungs-API ab (Nutzungsprozentsatz und Reset-Zeit für die drei Fenster rollierende 5 Stunden / wöchentlich / monatlich), der API-Key wird automatisch aus der opencode-Authentifizierungsdatei / Umgebungsvariablen / der Plugin-Konfiguration ermittelt, kein zusätzlicher Login nötig.

Tarif-Nutzungs-Badge: zeigt in der unteren rechten Ecke des Web-Dialogs drei Nutzungsfenster an — 5-Stunden-/Wochen-/Monatslimit (unterstützt die zwei Kanäle OpenCode Go und GLM Coding Plan: Z.AI International / Zhipu sowie das Kimi-Code-Mitgliedskontingent, das monatliche Mitgliedskontingent lässt sich über das kimi-auth-Cookie erweitern), und bietet unter „Einstellungen → Plugins“ für jeden Kanal einen eigenen Ein-/Aus-Schalter samt API-Key-Konfiguration.