Plugins

Finds potential UX issues in your project: automatically reviews React/TypeScript code, pinpoints each problem, and gives concrete suggestions.

Automatic conversation distillation: background subagent reflection + skill create/update.

Automatically add emojis to AI replies.

Auto-resumes interrupted DSH Web requests: sends a queued 「继续」 after network, timeout or host-crash failures, with error classification, adaptive backoff, templated continue text and browser notifications.

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed to text via any OpenAI-compatible VLM before reaching the text-only DeepSeek — a keyed fast path (default qwen3.7-flash; DashScope/Zhipu/OpenRouter or any OpenAI-compatible endpoint) with your own key, or local Ollama auto-detected with zero config.

Download-and-run Electron desktop build (macOS/Windows installers): no Node.js or terminal needed, tracks upstream `@deepseek-ai/dsh` releases automatically, with built-in web UI and auto-update.

Safe automatic permissions for DeepSeek Harness.

一个可以让ai自动调用VLM(多模态模型)进行视觉分析的dsh插件。A dsh plugin that allows AI to automatically invoke VLMs (multimodal models) for visual analysis.

DSH 自动记忆插件:三层记忆(用户级/项目笔记/每日日志)自动注入与检索、每日反思、可视化面板与设置页,支持继承其他 AI 工具的历史记忆。An auto-memory plugin for the DeepSeek Harness Web GUI: three-layer memory (user-level / project notes / daily logs) with automatic injection and retrieval, daily reflections, a visual panel and settings page, and inheritance of memories from other AI tools.

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

Talk to Excel in DeepSeek Harness: create, edit, repair, and verify spreadsheets by conversation, with automatic formula health checks after every edit.

HeartFlow (心虫) AGI layer-1 discriminator gate as a DSH plugin: 47-dimension rule-based text checking (heartflow_check tool) plus automatic output supervision at tools/post-execute, fail-closed when engine missing.

Subscription OAuth login: use ChatGPT/Claude/Grok/Kimi subscription accounts (not API keys) with automatic model discovery.

DSH plugin: open the system default browser automatically once `dsh web` is ready to serve.

Turn-scoped “Allow for this task” approvals: automatically allow matching `danger-full-access` escalations only for the current task, then expire.

Adaptive model routing: per-request complexity classification with automatic provider routing.

GPU-aware execution layer for DeepSeek Harness: gpu_status / gpu_exec / gpu_run_bg tools, per-step GPU context injection, automatic CUDA_VISIBLE_DEVICES card selection

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

A development safety kit: rolling config snapshots, automatic rollback on plugin failures, boot-failure rescue, and an in-settings management panel.

Web UI plugin for DeepSeek Harness: import skills from local Markdown files or URLs into the skill roots the harness discovers automatically

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.