genpark-multimodal-spatial-audio-visual-grounding-skill
Level FSourceReal-time Multimodal Spatial Audio-Visual Grounding Engine (inspired by Meta Ray-Ban & Meta Muse). Fuses 2D/3D visual bounding boxes, user head-pose gaze vectors, and acoustic beamforming azimuth angles into cross-modal focal salience scores and resolves deictic spatial references.
Installation
View source repo →Related servers
genpark-agent-hierarchical-episodic-memory-skillCognitive multi-tier memory kernel managing working scratchpad, sliding dialoguegenpark-ambient-vision-anchor-skillGenPark AI Agent Skill - Multimodal ambient visual anchoring connecting physicaln8nFair-code workflow automation platform with native AI capabilities. Combine visuoh-my-openagentOmO: Just type "mass ulw" keyword with your prompt. Now you are the master of grnanobotYour lightweight open-source personal agent.AstrBotAI Agent Assistant & development framework that integrates lots of IM platforms,