DSH插件商店

dsh-llm-vision-bridge

Einskyle

DeepSeek vision bridge for dsh: route image attachments to a vision model (Qwen3-VL via pi-ai/llama.cpp) and continue on a text-only LLM (DeepSeek)

dsh-vision-bridge

ximengxiaolan

Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text. ???????????

dsh-vision-bridge

GXX182

DeepSeek Harness plugin that bridges session images to pluggable vision APIs while keeping DeepSeek as the primary model.

dsh-vision-bridge

Xieweikang123

Give a text-only dsh model eyes: pasted images recognized into text via an OpenAI-compatible vision endpoint.

deepseekeyes

dttxorg

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness — strict evidence, health-checked failover, original pixels, and Token accounting.

dsh-vision-bridge

lium970320

DSH 视觉桥接插件：让无视觉能力的主模型看图（会话收图 + 自动转文字 + view_image 工具）

dsh-vision-bridge

AbdullahElTiby

Vision bridge for text-only models (DeepSeek, pi-ai routes): Gemini Flash describes attached images at the llm stream seam and provides a describe_image tool.

dsh-image-vision-bridge

Icestab

DSH 插件:聊天发图自动交给视觉模型 (mimo-v2.5) 分析,把文本描述悄悄喂给纯文本主模型,聊天记录保持原图显示。

dsh-deepseek-vision-bridge

KannaKuron

Eyes for text-only DSH agents: bridges chat.deepseek.com's vision mode into DeepSeek Harness — deepseek_vision tool, in-chat image transcription, WeChat-QR login in Settings.

dsh-vision-bridge-skill

LittleInk

一键式为dsh提供看图功能，借鉴了claude-vision-skill,先让agent读取了这个skill，后面尝试使用的时候发现平台会限制ds模型直接读取图片（只能剪贴板或者路径），所以做了一个桥接功能，VLM看完图后再把内容发送给DS并输出内容

dsh-vision-bridge

YuLee-314

DeepSeek Harness 视觉补全：孪生路由解锁原生图片体验，本地 Ollama 请求层看图，零云端依赖。Vision twin + local agentic vision tools for DeepSeek Harness.

dsh-vision-bridge

chou109

dsh-vision-bridge：在 DeepSeek Harness 聊天框粘贴图片，任意模型都能看懂——纯文本模型自动转成图片路径并调用 vision_chat 识图，支持图片的模型直接接收原图。粘贴即用，自动识别、自动回答。dsh-vision-bridge: paste any image into the DeepSeek Harness chat box — every model can see it: text-only models get an automatic vision_chat bridge, vision-capable models receive the image directly. Paste, send, done.