offline 10

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

一个插件、两种角色：主服务端把 DeepSeek Harness 变成手机能安全访问的 PWA（移动端界面、配对码网关、Web Push），并把选定会话共享给已配对的桌面端；子客户端在另一台 DSH 桌面端的侧边栏里远程使用这些会话。One DSH plugin, two roles: the host turns DeepSeek Harness into a phone-reachable PWA (mobile UI, pairing-code gateway behind your own rev

Local OCR fallback for DeepSeek Harness (Web): when the routed model cannot accept image input, a pasted image is saved locally and its text read by PP-OCRv5 + ONNX Runtime — fully offline, no vision model required. / DeepSeek Harness 本地 OCR 兜底插件（Web）：当接入

UI/UX 设计智能库插件：内置 84 种设计风格、192 个调色板、74 组字体搭配、99 条 UX 规范、25 种图表类型与 22 个技术栈，提供 design_recommend / design_review / design_search 三个模型工具。数据库完全内置、离线可用、中文优先。 / UI/UX design intelligence plugin for DeepSeek Harness: 84 styles, 192 palettes, 74 font pairings, 99 U

躺着背单词 lazeword — cozy offline vocabulary & subject learning for DeepSeek Harness (dsh): 15,000 words (EDB math/science/geography, Oxford 5000, Chinese classics, engineers' words), FSRS-5 scheduling, Anki sync, word Gomoku & 3D racing games. Also runs stan

Complete mobile PWA for DeepSeek Harness (DSH): secure LAN/Tailscale remote access gateway + install-to-homescreen (manifest), offline-capable service worker, touch-first gestures, agent-done notifications, and dark compact mobile UI. 移动端 PWA 完整方案 for Dee

Fully-local OCR CLI for text-only LLMs: PaddleOCR-VL first-tier engine with tesseract fallback, dsh plugin included

Local OCR for DeepSeek Harness: read text out of images with Apple Vision on macOS — no network, no API key, nothing to install. Falls back to tesseract elsewhere.

Unsloth for DeepSeek Harness - a pure-client tool plugin that connects the harness online model to a locally running Unsloth Desktop (Unsloth Studio) server for repetitive text and vision (OCR) labor.

KoboldCpp for DeepSeek Harness - a tool plugin that lets the harness online model hand repetitive text and vision (OCR) labor to a local KoboldCpp (llama.cpp) server.