Modlens
Turn images into structured evidence for text-only models, with OCR, layout, and semantic understanding.
Projects whose repository evidence lists Linux support.
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.
Route image turns to a vision model with a free fallback chain and pixel-level tools, without Python.
A full-screen terminal interface with streaming thought, rollback, context progress, and activity status.
A plugin market inside DeepSeek Harness for browsing, searching, and one-click installs.
A complete sidebar workspace with files, terminal, Git, sub-agents, and extension tabs.
A practical Web UI bundle with task boards, Git graphs, mobile access, token stats, and skins.
Cited memory over lossless session logs with human-auditable facts linked to source events.
Render interactive charts, forms, quizzes, diagrams, and 3D scenes directly inside answers.
A focused terminal user interface for DeepSeek Harness with a compact coding workflow.
An architecture-aware method pack that installs into DSH as a thin skill-bootstrap bundle.
Operate Chrome through a sidebar extension using structured browser tools instead of vision.