Long-Term Memory

A breakdown of memU focused on its main paths and ADR architecture documents, currently following through ADR 0008.

memU ADR 0007 overturns the earlier LLM mode: thoughts from a consumer-product developer and emotional-companion perspective.

Does your Agent keep repeating the same mistake before it finally remembers? A look at gotcha.md: which memories must be fully available as soon as a new session begins, and which can wait to be retrieved later?

An in-depth look at how MoeChat builds long-term memory for AI characters, including its time-and-semantic hybrid retrieval—written for people interested in memory systems.

A discussion inspired by MoeChat about RRF and Hybrid Search: how should time retrieval participate in hybrid retrieval, how should it adapt across scenarios, and where are the boundaries between wikimem and XnneHangLab?

Starting from a five-minute trigger and a ten-minute execution time, this article re-examines memU's multi-host worktrees, marker lifecycles, Recall File mirrors, and per-run isolation for proactive memorization.