Enables text-only coding models to read images, PDFs, presentations, spreadsheets, and other non-text files through a single analyze_media tool, combining local document extraction, OCR, and optional vision models with clear evidence labeling.
Enables AI agents to extract, analyze, and manipulate images, PDFs, video, and audio while conserving context through downscaling, truncation, and frame/page caps.
Provides image and video analysis capabilities for LLMs, with local preprocessing (ffmpeg/OpenCV) and any OpenAI-compatible vision model for understanding and Q&A.
Enables text-only AI coding agents to analyze images and videos via vision-capable models (Gemini, Grok, OpenRouter), returning text descriptions for reasoning.
Enables text-only AI agents to ask questions about images, audio, and video by passing file paths or URLs to a multimodal model and returning text answers.
