Modlens
Turn images into structured evidence for text-only models, with OCR, layout, and semantic understanding.
Native image Q&A, long-screenshot OCR, interface restoration, grounding, and pixel comparison.
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, Headless, and Desktop profiles. The default install includes a free Gemini 3.7 Flash vision service.
Commands appear only when they are present in maintainer documentation.
dsh plugin --profile web add @anionex/dsh-vision-toolkitPublished npm bundle documented for the Web, Headless, and Desktop profiles. See the versioned verification fields for the current independent verdict.
Maintainer claims, external observations, and registry-run tests stay separate.
the browser driver failed while observing the Web surface: page.goto: net::ERR_CONNECTION_REFUSED at http://127.0.0.1:30880/ Call log: - navigating to "http://127.0.0.1:30880/", waiting until "domcontentloaded"
Evidence is tied to the current repository state and may change after DSH or plugin updates.
Where each registry statement comes from.
Observable capabilities and package signals, not a formal audit.