Show HN: AI memory with biological decay (52% recall)

1 sources1 storiesFirst seen 4/26/2026Score25Mixed Progress

Single Source

Bigness

Coverage

Recency

Engagement

Velocity

Confidence

Clipability

Polarization

Claims

Contradictions

Breakthrough

Sentiment Mix

Positive0%

Neutral0%

Negative100%

Geography

North America

Expert Signals

SachitRafa

author • 1 mention

Hacker News

source • 1 mention

AI-Generated Claims

Generated from linked receipts; click sources for full context.

Show HN: AI memory with biological decay (52% recall).

Supported by 1 story

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 approach by using the Ebbinghaus forgetting curve to manage context as a living substrate.

Supported by 1 story

Memories are assigned a "strength" score where each recall reinforces the data and flattens its decay curve (spaced repetition), while unused data eventually hits a threshold and is pruned.To solve the "logical neighbor" problem where semantic search misses relevant but non-similar nodes, a graph layer is layered over the vector store.

Supported by 1 story

Benchmarked against the LoCoMo dataset, this reached 52% Recall@5, nearly double the accuracy of stateless vector stores, while cutting token waste by roughly 84%.Built as a local first MCP server using DuckDB, the hypothesis is that for agents handling long-running...

Supported by 1 story