#vector-search

3 posts

I Benchmarked My Homelab Memory Stack: Hybrid Search + Local Reranker Took LoCoMo from 63% to 80%

I Benchmarked My Homelab Memory Stack: Hybrid Search + Local Reranker Took LoCoMo from 63% to 80%

How adding BM25 hybrid search and a local BGE reranker to a vector-only agent memory stack moved LoCoMo accuracy from 63% to 80%, and what it cost in latency.

Silent Drift: Why Re-Embedding Only on Count Changes Rots Your Semantic Index

Silent Drift: Why Re-Embedding Only on Count Changes Rots Your Semantic Index

Count-based re-embedding leaves stale vectors pointing at edited text. Here's how semantic drift creeps in and how hash-based validation stops it.

Eviction Without Deletion: Running an ACT-R Decay Policy for Agent Memory

Eviction Without Deletion: Running an ACT-R Decay Policy for Agent Memory

Stop deleting agent memories to fight vector-store noise. An ACT-R decay policy lowers activation instead, so cold context can re-activate later.

← All tags