multimodal 相关的 DSH 插件

dsh-vision-router

Eyes for text-only DeepSeek Harness agents: built-in free vision chain + pixel-level tools…

dsh-video-storyboard

Turn a video into storyboard images you can cite: one frame per shot, cell size follows cut density (1/1 … 1/8), row-pac…

dsh-crew

DeepSeek Harness plugin: dispatch work to DSH agents from Claude Code / Codex, as native subagents with live progress

dsh-AuthInOne

Self-contained DeepSeek Harness plugin for Provider login, model switching, image fallback, usage analytics, and same-po…

dsh-vision

Near-native image understanding for text-only DeepSeek Harness models

dsh-read-animation

Let a DeepSeek Harness agent actually see an animated GIF or animated WebP: decode every frame, sample the animation acr…

dsh-iris

A multimodal workspace for Agents: Core Web, MCP, CLI and native DSH tools with model pools, durable media tasks, ComfyU…