The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网第一个 DeepSeek Harness 视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
⭐1.9k536/day
Tracked by Kanon since Aug 15, 2026 · then ⭐1.6k · now ⭐1.9k
Signal source: GitHub
Visit official site →
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is liustack/modlens?
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网第一个 DeepSeek Harness 视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
How popular is liustack/modlens?
As tracked by KanonAgent: ⭐1.9k · 536/day (first indexed 2026-08-15).
What are the best liustack/modlens alternatives?
Similar AI agents tracked by KanonAgent: mattpocock/dictionary-of-ai-coding, CodebuffAI/freebuff, THU-MAIC/OpenMAIC, cordiverse/cordis, diegosouzapw/OmniRoute, earendil-works/pi.