Plugins

DSH 多租户账户与授权插件：PostgreSQL 存储 + admin 管理 API + 每账户独立工作目录（独立插件，不改 DSH 核心）

Generate AI-narrated DSH session reports (daily/weekly/monthly, any date range) and sync them to flomo (浮墨笔记) with one configurable tag (default #write/dsh) and automatic # stripping, via a web settings panel with daily reminder.

Live account quota/balance widget for DeepSeek Harness web: DeepSeek API balance plus Kimi For Coding plan usage (weekly + 5h windows, remaining and reset countdowns) in one compact card.

DeepSeek Harness plugin: multimodal tools (image/audio/video/document understanding, transcription, image generation) via Gemini API or the local Antigravity CLI.

技能创作器：教 agent 按 agentskills.io 规范编写高质量 SKILL.md 技能（frontmatter、渐进式披露、触发描述）。改编自 Anthropic 官方 skill-creator（Apache-2.0）。

前端设计技能：指导 agent 产出高质量 Web 前端设计（视觉层级、配色、排版、组件、响应式、无障碍）。改编自 Anthropic 官方 frontend-design（Apache-2.0）。

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.

Project/task dual-mode workspaces for DSH: a task skips the workspace picker and gets a fresh scratch directory (D:\dsh_working\<name>-<timestamp>) per conversation, Codex-style; no-workspace sessions are grouped under a persistent Tasks section in the sidebar with empty states, and the new-session workspace picker gains a "no workspace (task)" option.

昔涟 (Cyrene) 主题 + 桌宠 for the dsh web GUI — pearl-white pink theme, Live2D desktop pet, particle background, gradient, and a collapsible config card. Ported from Cyrene-Agent (MIT) with the Live2D model creator's permission.

DSH tool plugin: generate images through ToAPIs async GPT-Image-2 API (submit task, poll, download).

File-based self-evolving memory for DeepSeek Harness v2: compression & extraction over official compaction, daily episodic layer, dream consolidation to semantic files (user/agent/memory/dream + project), catalog disclosure injection, no confidence machin

DeepSeek Harness 插件管理器：发现 GitHub dsh-plugin topic 下的插件仓库，通过 `dsh plugin` 安装/移除/更新 profile 插件，并在 设置 → 插件 → 插件市场 标签页中浏览管理。

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

Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model

Cross-ecosystem aggregation data layer: syncs the GitHub dsh-plugin topic and the npm registry into one open JSON index, queried by model tools, a CLI, and a minimal stdio MCP server.

Container-isolated backend for the `ctx.codeRuntime` seam: each Code Mode program runs in a fresh container with no network, a read-only rootfs, dropped capabilities, and kernel-enforced memory, CPU and pid ceilings.

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.

Two-way TickTick/Dida365 (滴答清单) task sync via the official OAuth Open API: pull tasks across lists, create/update/complete/delete tasks, and one-shot title-deduped sync, with a web settings panel.

Injects allowlisted GitHub Actions and GitLab CI run metadata into agent context without reading logs, credentials, or provider APIs.

Voice input for the web UI: a mic button in the composer that transcribes speech into the draft via the Web Speech API, with an optional auto-send toggle.

Two-tier image reading for text-only models: fast local OCR (RapidOCR, offline) first, vision-model fallback (modlens).

Image-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).