DSH插件商店

dsh-vision-router

ysr666

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

dsh-vision-toolkit

Anionex

[dsh]为纯文本模型设计更强大的视觉工具箱：安装免费使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

dsh-tool-diff

omdsh-dev

DSH Diff 工具插件：文本/JSON/CSV/Markdown 结构化比较与 unified diff，零依赖只读，注册 diff 工具

dsh-filelens

Han-Yao94

该仓库暂未提供项目说明。

dsh-workbench

lee259

Right-side file workspace for DeepSeek Harness Web.

dsh-vision-primitives

zouyuanqing

Native interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid / zoom / annotate / measure / diff / color / OCR) + MiMo V2.5 multimodal backend, zero external MCP servers.

dsh-profilespanel

lingxin-maz

DeepSeek Harness (DSH) plugin status panel & profile ops console: pending-restart (SSE), one-click restart, multi-profile sync install (web+desktop), supply-chain preview, rollback/undo, updates/align, health, diff, boot report, audit log & agent tools.

sidesight

ZhuXinAI

CLI-first vision sidecar for text-only coding agents. Analyze screenshots, diagrams, charts, UI diffs, and videos with OpenAI-compatible multimodal models.

dsh-vision-suite

princefrogdida-ux

Windows-first vision suite with image understanding, OCR, screenshot diffing, and multi-provider routing for DeepSeek Harness.

dsh-smart-router

rouyiemei

Automatic model routing for DeepSeek Harness: three difficulty tiers (hard/normal/easy) plus vision routing, picking models you already configured under Settings ? Models. ???? + ?????????