Open-source operational brain that fuses an AI system's agents, memory, knowledge and automations into one rooted, privacy-walled graph, served over MCP with stats, search, node dossiers, neighbors and pathfinding. The same snapshot also renders up to a million nodes in a 3D browser view.
Provides screen capture, OCR text extraction, and visual language model scene understanding capabilities with continuous monitoring and automatic memory storage integration.
Provides a visual memory and attention layer for AI agents, enabling indexing of images and videos and then searching, inspecting, tracking, and retrieving the right frame in milliseconds via MCP tools.
