modlens

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). | 全网最强 DeepSeek Harness 外挂视觉插件，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）。

Install

GitHub: liustack/modlens
Website: liustack.dev
Stars: ★ 4.5k
License: MIT
Language: TypeScript
Last push: Oct 23, 2026
Topics: codex · cordis · deepseek · dsh · dsh-plugin

Good for

Give text-only models like DeepSeek and GLM sight, reading an image pasted straight into the chat
Turn an image into structured JSON evidence (OCR, layout, semantics)
Paste images directly in harnesses like Claude Code, Codex, OpenCode and Pi, with no save-to-file step

Getting started

Run npx skills add liustack/modlens; on DeepSeek Harness use npx -y @deepseek-ai/dsh plugin --profile web add @liustack/modlens@3.27.2
Reuse your existing Claude Code or Codex setup, or use the free Antigravity CLI or a Gemini key as the vision source
Paste an image into the chat and let modlens read it

Before you install

It only takes over models confirmed text-only (DeepSeek, GLM, MiMo Pro); native vision models such as GLM-5.3-Flash keep their normal paste behavior. Reading images needs a vision-capable source, via a free or OpenAI-compatible provider key.

Summarized by AI from the project docs; check the official docs before relying on it.

Similar tools

skillCommunity skills · ★ 8.7k
收录最全、更新最快的技能Skills商店：精选原创技能包（涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流），全部打包好可直接安装使用！同时自动抓取GitHub上万个Skills项目，按分类、更新时间、Star数量整理。The most comprehensive and frequently updated AI Agent skill library, featuring curated skill packs across document processing, content creation, programming, machine learning, automated workflows, and many more domains.
reaCommunity skills · ★ 386k
Reverse engineer anything with agents, from app behavior down to native binaries.
cherry-studioCommunity skills · ★ 53k
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
agent-skillsCommunity skills · ★ 111k
Production-grade engineering skills for AI coding agents.
open-designCommunity skills · ★ 104k
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate together in one workspace.