AI memory with biological decayRepository40/100 via “biological decay-based memory forgetting”
Most RAG setups fail because they treat memory like a static filing cabinet. When every transient bug fix or abandoned rule is stored forever, the context window eventually chokes on noise, spiking token costs and degrading the agent's reasoning.This implementation experiments with a biological
Unique: Uses biological forgetting curves (Ebbinghaus decay model) to probabilistically fade memories over time based on recency and frequency, rather than fixed TTL or LRU eviction. Decay is parameterized and continuous, not discrete, allowing smooth degradation of memory confidence.
vs others: More cognitively plausible than simple vector DB retrieval + fixed context windows; enables natural forgetting without explicit memory management, but trades determinism and recall accuracy (52%) for more human-like behavior.