标签主题词 (Topic)

# multimodal

探索包含 multimodal 主题特性的所有开源仓库、扩展插件与智能体组件。

提供12个多模态MCP工具,覆盖视觉理解、OCR识别、目标定位、ASR语音及音视频处理;Web设置页粘贴API Key即可启用,搭配内置技能与一键安装器,开箱即用,快速扩展Agent多模态能力。

deepseek-hsrness-devkit
2472786266-spec

DSH DevKit: multimodal gallery + multi-agent supervision console (DeepSeek Harness dynamic Cordis plugin)

tongflow
tong-io

TongFlow — multimodal workflow studio and engine (canvas + Python plugin engine) and dsh-tongflow, the DeepSeek Harness ...

为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed ...

modlens
liustack

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, ge...