Memory
Working and long-term memory files preserve agent context across runs.
Embodied AI system project
A modular agent stack exploring memory, perception, task planning, and Unity-based interaction for an artificial life simulation.
Project demo
Pekingman v1.0.0 is a multimodal AGI-oriented agent system designed for environmental perception, long-term memory, human-like reasoning, emotional consistency, and real-time behavioral response. Equipped with a high-capacity persistent memory system, it can store, retrieve, and revisit historical events, giving NPCs authentic human-like behavioral logic.
System shape
Working and long-term memory files preserve agent context across runs.
Input folders and collection utilities bring text, video, and environment signals into the system.
Module orchestration, task selection, and Unity-facing queues connect decisions to visible behavior.
Functionalities
Collects text, video, and environment input so the agent can interpret current conditions.
Maintains working state and long-term context to support continuity across decisions.
Turns goals and sensed conditions into selected tasks, module activity, and next actions.
Connects planned behavior to simulation-facing controls for visible embodied interaction.
Provides a web panel for inspecting module progress, shared state, and system activity.