Visionby liustack
Modlens
Turn images into structured evidence for text-only models, with OCR, layout, and semantic understanding.
96 evidence Updated Aug 14, 2026
Visionby Anionex
DSH Vision Toolkit
Native image Q&A, long-screenshot OCR, interface restoration, grounding, and pixel comparison.
Excellent compatibility evidence Activity snapshot Repository test evidence
What it does
A DeepSeek Harness-native vision bundle built for repeatable visual work. It provides typed image tools, managed credentials, previewable artifacts, Web cards, and the same structured results in Web and Headless profiles.
134 automated tests
Web and Headless support
Credential isolation
Visual diff workflow
Install
Use the command for the supported profile.
dsh plugin --profile web add ./dsh-vision-toolkitReview 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 Supported
Independent latest-build check Not tested
Platforms
macOS Supported
Windows Not tested
Linux Supported
Repository test 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