Plugins

Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.

Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek), strips hidden text marks (zero-width characters, invisible layout; shadow scan catches markers split by invisibles), and rewrites the text into natural prose on request; 40 regex markers, 38 with full evidence-registry entries; 156 gates, 530 tests; offline, text-only bundle (binary metadata removal lives in scripts/).

Project-scoped cross-session memory: seven-layer SQLite store (soul/user/project/fact/lesson/rules/topic) on node:sqlite, cache-friendly first-message injection plus per-message keyword hits, memory_remember/search/find_similar/read/update/project tools, and idle-window consolidation ("dream") with peak-hour suppression. Prompt texts ship as per-language data files — the framework supports multilingual users.

Let Your Ideas Flow — Tydora is a modern desktop Markdown editor combining WYSIWYG editing, bidirectional links, mind maps, and an infinite canvas — empowering deep thinking and effortless expression.

Input experience enhancement: voice input, AI polish, anti-overwrite, prompt optimization with diff preview, and auto locale switching following DSH UI language.

Block-addressed document editing: an MCP server exposing geml_get / geml_set / geml_check and friends, so an agent reads or rewrites one addressed block of a Markdown or GEML document instead of the whole file. Ships the GEML authoring skill and a code-graph skill that builds and navigates a project call graph as GEML codemaps.

Agent-Native document handling for DSH — addressable blocks let an agent read and edit one section instead of the whole file. Ships the geml MCP server and the authoring and code-graph skills.

LSP action surface for DSH: diagnostics, formatting, completion, code actions, symbols, signature help, inlay hints and rename, all backed by real language servers.

Gives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.

Adds Russian as the third option in the native Settings - General - Language menu of the DeepSeek Harness web UI, with 100% coverage of the 30 DSH core namespaces (722 keys) plus 9 plugin namespaces (962 keys). The locale runtime snapshot is extended at runtime on unpatched cores; no files in the DSH installation are modified, and the choice is persisted through the plugin-owned russian-lang settings namespace.

Computer use through an external USB HID device: name a target in plain language, a vision model locates it in a cropped window screenshot, and a Raspberry Pi Pico 2 moves the real mouse and types on the real keyboard. 7 tools. Windows has window listing, per-window cropping and automatic window raising; macOS needs pyobjc and has neither; Linux is unsupported.

Display-layer translation for the DSH Web UI — thinking chains, task cards and answers in 8 target languages via local Ollama or Google/Bing, originals preserved.

UI harmonizer for DeepSeek Harness: normalizes unfinished or self-contradictory official UI, reconciles style conflicts between installed plugins, and unifies the visual language via official design tokens — with live-customizable chat width, markdown font size, workspace scale, UI font stack and a rounded center-column card from Settings → General; client-only dsh bundle, zero model cost, no host side, removable without residue.

DSH Web GUI right sidebar: VS Code-style file explorer plus source control (git status, stage/unstage/discard, commit, diff, commit graph, sync fetch/pull/push, branch management, remote management, git init, multi-repo switch, color-coded file status (untracked/modified/ignored), file-type icons, image preview) with an editable full-file diff view, a syntax-highlighted editor (15 languages), file operations (new/move/copy/delete), and save.

Make any project AI-agent-ready in one command. Adaptive tech stack detection (7 languages × 14 frameworks × 61 components), auto-generates AGENTS.md, docs skeleton, CI/CD, and testing infrastructure. 一句话让任何项目具备 AI 开发能力。

Web UI polish layer for DeepSeek Harness: normalizes unfinished or self-contradictory official UI, reconciles style conflicts between installed plugins, and unifies the visual language via official design tokens; live-customizable chat width, markdown font size, workspace scale and UI font stack.

The complete #dsh-plugin mall inside DeepSeek Harness: browse, search and score the full GitHub dsh-plugin topic catalog refreshed every 2 hours, AI pre-install review with install/caution/avoid verdicts, five-dimension scores with radar charts, nine-language UI, editor picks and personalized recommendations, one-click install/update/rollback with a global task panel, and an in-agent /dsh-mall skill.

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

Fetches any http/https page and returns title, description, main text, heading outline and links, with stats (char/word counts, reading time, language) and top keywords; can download content images to the session workspace for vision analysis and dispatch them to registered analyzers via the scrape.imageAnalyzer service.

Global Chinese mode: a compact pill switch beside the composer that injects a language requirement into any preset's system prompt (complete personas excepted); reply, thinking and tool output each toggle between Chinese and English, and anchored presets are supported.

A plugin manager tab in Settings → Plugins: Chinese names and plain-language descriptions for every installed plugin, one-click enable/disable, in-UI notes editing, and search/filter over the installed catalog.

Presentation skill and tools: one sentence or one document to an HTML slideshow plus editable PPTX, seven layouts (incl. quote and native PPTX tables), speaker notes (HTML S-key panel and native notes slides), five built-in themes, default theme/language config and bilingual support.

Injects one fixed system-prompt section so the agent thinks and replies in Chinese, regardless of the user's language.

Reads the files that AGENTS.md references with @path imports and injects their content into model context at session start, with byte budgets, compaction re-seeding and a six-language settings card.