Visionby Anionex
DSH Vision Toolkit
Native image Q&A, long-screenshot OCR, interface restoration, grounding, and pixel comparison.
94 evidence Updated Aug 14, 2026
Visionby liustack
Modlens
Turn images into structured evidence for text-only models, with OCR, layout, and semantic understanding.
Excellent compatibility evidence Activity snapshot Maintainer evidence
What it does
Modlens gives DeepSeek Harness a native image-reading tool. It converts screenshots and images into structured evidence that the model can quote, reason about, and use for interface work without requiring a vision-native model.
Single-command install
Structured JSON evidence
Pasted image support
Active release cadence
Install
Use the command for the supported profile.
npx -y @deepseek-ai/dsh plugin --profile web add @liustack/modlensReview the repository and requested permissions before running commands from the internet. DSH is currently in developer preview.
Compatibility
Signals recorded from public repository and maintainer evidence.
Profiles
Web profile Supported
Headless profile Limited
Independent latest-build check Not tested
Platforms
macOS Supported
Windows Supported
Linux Supported
Maintainer evidence
Review method Evidence is tied to the current repository state and may change after DSH or plugin updates.
Security context
Observable capabilities and package signals, not a formal audit.
Source available Yes
License detectedMIT
Known critical advisories Not independently checked
Automated dependency review Scanner not connected