...The core package can inspect images, videos, documents, and 3D models while providing OCR, grounding, segmentation, transcription, and visual question answering. Additional modules support long-video memory, audio-video analysis, media generation, video editing, Blender, FreeCAD, and educational content creation. Dynamic-resolution processing automatically adjusts visual inputs according to the detail required by the model. A guided installer configures supported environments such as Claude Code, Codex, Qoder, OpenClaw, Qwen Code, and Gemini CLI. Individual capabilities can be installed independently so agents only load the functionality they need.