image-to-text 4
Plug-in vision for text-only LLMs, powered by the free Antigravity CLI
dsh plugin add @liustack/modlensDeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery
dsh plugin add @chang416/deepseeDeepSeek Harness out-of-tree plugin: give a text-only coding model eyes by routing images to a Qwen-VL (DashScope) route through ctx.llm and returning text.
dsh plugin add dsh-plugin-qwen-imageFully-local OCR CLI for text-only LLMs: PaddleOCR-VL first-tier engine with tesseract fallback, dsh plugin included
dsh plugin add local-ocr-cli