DeepSeek Harness Vision Bridge
liustack/modlens · skills
Add OCR, layout analysis, and semantic understanding to text-only coding agents, with structured visual evidence as output.
★ 1,573GitHub stars
41Forks
2026-08-15Last updated
TypeScriptLanguage
MITLicense
Project overview
Give a text-only model sight, and just paste the image.
🥇 The FIRST vision plugin for DeepSeek Harness (dsh) 🥇
The flagship DeepSeek and GLM chat models are text-only and cannot read images. ModLens is a plug-in vision engine that gives a text-only model sight. ModLens reads images pasted straight into the chat, no saving to a file and passing a path first. Talk to us
Install command
dsh plugin --profile web add github:liustack/modlens