HomeAI Tutorial

Thing-Sandbox

Public

Autonomous LLM-powered simulation exploring LLM agent behavior with subjective memory and emergent narratives through multi-phase intention-arbitration-memory ticks. Arbiter resolves scenes, memory degrades via FIFO summarization, simulation mutates even in empty locations.

Creat2025-11-30T20:14:18
Update2025-12-09T00:29:24
1
Stars
0
Stars Increase

Related projects