modlens

modlens

Adds visual capabilities to pure text models; paste an image to get structured JSON evidence (OCR, layout, semantics).

Agent SkillDevOpen source
Type
Agent Skill
Open source
Yes
GitHub Stars
★ 1.3k
Source
skill-github

Overview

ModLens is the first visual plugin for DeepSeek Harness, adding visual abilities to pure text models like DeepSeek and GLM. Simply paste an image to receive structured JSON evidence including OCR text, layout information, and semantic analysis. The plugin installs easily with no additional configuration required and supports multiple platforms such as Claude Code, Codex, Pi, and OpenCode. Ideal for developers and researchers needing to convert image information into structured data.

Capabilities

  • OCR text recognition
  • Layout analysis
  • Semantic understanding
  • Image-to-structured JSON conversion

Use cases

Image content extractionDocument automation processingVisual-assisted programmingMultimodal data analysis

Setup

Requires: Node.jsAPI Key (可选)
npx -y @deepseek-ai/dsh plugin --profile web add @liustack/modlens@3.16.5

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to install ModLens?

Install using the npx command: npx -y @deepseek-ai/dsh plugin --profile web add @liustack/modlens@3.16.5

Which platforms does ModLens support?

Supports platforms such as Claude Code, Codex, Pi, and OpenCode.

Is an API Key required?

You can use a free Gemini API Key or any other OpenAI-compatible API Key, or choose not to use an API Key at all.

Related skills