Plugins

Native-style notification sounds for DeepSeek Harness: a chime when the agent needs your decision or finishes a task, clickable system notifications that jump back to the window, repeat reminders, quiet hours, and goal-mode alerts that wait for the final round.

The marketing OS for AI agents — think like a marketer first, get tactics as the output.

QQ official bot channel for DeepSeek Harness (feature-rich fork of tencent-connect/dsh-qqbot): group and private chat with the full agent, sticker library with auto-tagging and AI meme replies, group management (join approval and mute), botplay interactive card events with paginated catalogs, user extension registry (custom slash commands and QQ tools), scheduled wakeups, remote approvals over QQ, and a floating dock web UI.

Claude Code-inspired Auto Memory meets Codex-inspired Session consolidation, bringing simple, transparent, and context-efficient long-term memory to DeepSeek Harness.

A drawer panel for the DSH web UI with a paginated list of free LLMs; one-click or batch writes each as a custom model provider into Settings, plus a local multi-key rotation proxy.

DSH Web UI little whale-maid theme with light and dark palettes, ocean illustrations, hand-drawn frames, decorative assets, and a new built-in Codex-style pet.

Pair a second model that passively reviews each turn and injects notes.

Manage soul.md persona cards and long-term memory, with workspace and session persona selection and tools to read and update them.

Feishu/Lark bridge for local coding agents — one group, one conversation, one pinned runtime. Bridges dsh, CLI agents (traex/codex), an IDE window, or a custom agent behind one gateway.

One-click prompt enhancement in the composer — rewrites the draft into a structured prompt (role and goal, executable steps, output format, acceptance criteria, edge cases) with before/after preview, fill-back, and undo. Never changes intent, never fabricates requirements.

Adds an optimize button beside the composer that analyzes and rewrites the prompt draft with SSE streaming, conversation-context awareness (template vs intent-polish strategies), an edit-continuity memory chain, undo, and model routing with fallback and a connectivity test.

QA project workbench for dsh: manage test projects, requirements, test cases, defects, milestones, reports and approval gates through a browser UI and 18 QA-domain tools.

Live2D desk pet overlay for the DSH web GUI: mirrors agent state (thinking, idle, error, done, awaiting approval) with motions and speech bubbles, per-part touch reactions, drag-to-dock, switchable personas, and custom models via URL or local path.

OpenCues for DeepSeek Harness — LLM word alternatives and `_`-gated blank fill-ins in the dsh composer.

IMAP/SMTP email tools (list/read/search/send/folders/attachment/health/watch/mark/reply) with since/until date-range filters, email_mark for read/unread/star/move, email_reply for reply/reply-all/forward with threading headers, QQ/163/126/Sina/Aliyun/Gmail/Outlook/iCloud presets, multi-account support, a send-approval gate, a web settings page and a whale-girl new-mail popup driven by the incremental email_watch checker. Outlook OAuth2 device-code login works out of the box through a built-in community client, and an account can still supply its own clientId instead. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Lets the primary model ask an independent reviewer model to review a decision it has already made, with off, shadow and advisory modes. Requires your own service implementing POST /v1/decision.

A chibi blue-haired maid desktop pet for the DSH Web UI with 106 hand-drawn transparent animations, desktop wandering, chat through local Ollama or the DSH online models, and optional screen watching.

Manage MCP servers and skills from a panel in the DSH sidebar: edit rows in the profile or global cordis.patch.yml, toggle them, check whether an HTTP server answers, scan Claude Code / Codex / Cursor / Gemini configs and import the servers they declare, and browse, create, edit, enable or delete skills by rewriting the user-invocable policy in SKILL.md.

Classifies pending tool calls with Jev (TypeSafe AI's non-generative decision model) on tools/pre-execute — confident high-risk calls are denied, ambiguous ones escalated to approval — and auto-approves clearly-granted reversible calls on approval/request behind argument-evidence gating. Also subclasses the session-reference resolver so snapshots keep Jev-scored messages instead of dropping oldest-first. Degrades to stock behavior on any provider failure; shadow mode with a /jev-stats command; TypeSafe or OpenRouter endpoints; 64 tests.

Syncs the wallpaper currently applied in Wallpaper Engine to the DSH Web UI background through a local bridge: preview/capture/full render modes, monitor lock, a wallpaper library panel for local and market content, focus lens with eye tracking, immersive mode, and a Windows app launcher that installs software from direct links or a cloud-drive share link and starts it with one click.

A DeepSeek Harness (dsh) plugin — turns dsh web into a SillyTavern-style roleplay frontend: character cards, prompt presets, lorebooks, personas, BM25 long-term memory, world-state deltas, and rollback-able floor operations, all on the dsh agent runtime.

Twelve official Remotion skills synced from the official upstream (programmatic video with React: animation, audio, captions, 3D, maps, charts, render, Studio), plus a bundled-resource health check. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Self-contained browser runtime: Playwright (chromium) + OpenCLI as plugin-local dependencies (global reuse fallback), exposes a `browser` service and 9 interactive browser tools.

Play Gomoku against the AI, or let two AIs battle it out.