Agent Vision Toolbox
wangyang10/image-vision · skills
allows models without visual capabilities (such as pure text models such as DeepSeek) to "read images": it automatically calls the OpenAI-compatible image recognition model API (OpenRouter, SiliconFlow, Zhipu, Kimi, Tong.
★ 7GitHub stars
0Forks
2026-08-14Last updated
JavaScriptLanguage
MITLicense
Project overview
allows models without visual capabilities (such as pure text models such as DeepSeek) to "read images": it automatically calls the OpenAI-compatible image recognition model API (OpenRouter, SiliconFlow, Zhipu, Kimi, Tong.
Install command
dsh plugin --profile web add github:wangyang10/image-vision