DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
39 个项目，匹配「vision」
TNTsama11
DeepSeek Harness (DSH) plugin that lets a text-only agent call DeepSeek-V4-Flash-Vision-Exp to see images on demand, without manually switching models.
YJLTF
一个 DeepSeek Harness 插件：为纯文本主模型补上识图能力。它把图片理解委托给你配置的一个小参数多模态模型，再把结果以文本形式交还给主模型；当活跃模型自身支持图片输入时，插件完全退避，原生多模态体验不受任何影响。
ankye
Give your DeepSeek Harness agent eyes. dsh-client-vision is a screen-capture + external image-recognition plugin for DeepSeek Harness: the agent takes a screenshot (or points at any image), hands it to a vision-capable model through a pluggable channel, and gets back plain text it can actually act on — no multimodal model required.
doublehappy123
DSH plugin: auto-tiles oversized chat images into labelled grid tiles for DeepSeek v4Flash vision, with Python tiling engine
jorinyang
ClawShell vision as DeepSeek Harness plugins: self-perception, closed-loop self-adaptation, trust/niche swarm, insight mining, knowledge genome
pureexe
DeepSeek Harness plugin: transcodes images to a base64-safe format (PNG) before a vision request, so gateways like LM Studio (which only accept PNG/JPEG/GIF data URLs) do not reject WebP images.
shenyan-008
dsh visual aid plugin: lets text-only main models handle images via a vision model
xiaozhengdeng
GUI agent plugin for DeepSeek Harness: OmniParser screen recognition, desktop automation, and an OmniVision vision dock
xie129716
Unofficial fork of computer-user: fixes the silent load failure on DSH >= 0.1.2, and returns screenshots as real images to vision models with an exact image->screen coordinate mapping.
yan5236
让不支持图片输入的主模型通过已配置的视觉模型理解图片的 DSH 插件：自动桥接、像素坐标描述、vision_ask 追问工具与设置页
Jessie-1939
WhalePal — a desktop whale-girl companion that understands what you're working on via cloud vision, with local-only data and no telemetry.
dmsobtl
DSH 插件：消息含图片时自动路由到多模态模型，无图片时继续用便宜的 DeepSeek。
h-k-c
DeepSeek Harness 图片插件：贴图不会让对话报错，模型自动判断是否需要看图（支持智谱/魔搭免费视觉模型，图片在聊天窗口正常显示）
motongv
给 DeepSeek Harness（DSH）加视觉能力的插件：装完就能拖图识别——图片交给视觉模型识别、文字交给 DeepSeek 推理，聊天入口完全不变。DSH 专属插件。
uAcharGG
该仓库暂未提供项目说明。