Plugins

MCP client hub (stdio / Streamable HTTP / SSE) with a web console for DeepSeek Harness — manage MCP servers, agent skills, slash commands, project & global memory, and prompt sections.

A DeepSeek Harness web plugin: set a background image and adapt the UI's text, background, brand and border colors to the image palette automatically.Built with DeepSeek Harness

Vision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.

Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section

WeChat Mini Program automated testing for DeepSeek Harness (dsh): selector-addressed actions, build-freshness gates, geometry-first assertions that work on text-only models, and screenshot image blocks on vision routes. 微信小程序自动化测试 dsh 插件：选择器寻址、构建新鲜度门、面向纯文

DeepSeek Harness plugin for bounded, provenance-linked context steady state with recoverable raw history

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。

Surgical rewriting of the model-visible conversation history of a DSH session (surface replacement); edit reply and reasoning chain separately. 上下文手术刀：强制改写会话的模型可见历史，回复与思考链分开编辑。

DeepSeek Harness OCR plugin — offline image text recognition powered by PaddleOCR-json (primary) and RapidOCR-json (fallback). 让 DeepSeek Harness 直接识别图片中的文字，无需视觉模型、完全本地离线运行。

Deterministic context-pruning compaction backend for dsh (DeepSeek Harness) — zero-LLM summaries, /dcp command, works out of the box. Design references Opencode-DCP/opencode-dynamic-context-pruning.

Dynamic multimodal-to-text projection and cross-model vision bridge for DeepSeek Harness (dsh), allowing seamless hot-switching between vision models (Gemini/Claude) and text-only models (DeepSeek).

Anthropic Model Context Protocol (MCP) client bridge plugin for DeepSeek Harness (dsh).

DSH Web GUI paperclip button: a 📎 button in the composer opens a file picker (drag & drop supported) and inserts file contents into the textarea.

DeepSeek Harness git development workbench: captures git context (branch, status, worktrees, stash, recent commits) into every session, asks which branch/worktree to develop in at session start, and switches branches / creates and manages worktrees throug

Native dsh (DeepSeek Harness) Cordis plugin adapter for vision-translation: grounds images into <vision-context> via the Python CLI (PROTOCOL v1). Spawns cli.py, never re-implements core logic.

Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven OpenAI-compatible engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint) with health-aware fallback, durable w

Cross-platform native desktop control tools for DeepSeek Harness (Windows first): screen_shot, screen_read (accessibility tree + pixel description for text-only models), click/type/scroll/key, and app_list/app_launch — every mutating action gated by appro

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

A friendly status and context-pressure companion for DeepSeek Harness Web

Codex-style code and file selection for DeepSeek Harness Web: workspace file tree + file viewer; selecting code or a whole file adds it to the message as context automatically

Publish TXT, Markdown, HTML, PDF, Word, and PowerPoint files as ShareOne links with passwords, watermarks, text-page updates, and TXT/Markdown/HTML comments.

Read-only performance diagnostics for DeepSeek Harness: session load (open/restore) timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via the /fas

Self-owned vision bridge for DeepSeek Harness: pick the vision model yourself from the available ones. Image content blocks are rewritten into text markers at the agent boundary so text-only models never fail a turn, and a describe_image tool answers via

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.