YourMemory, agentic memory is a pruning problem, not a hoarding problem
Ebbinghaus decay prunes memory automatically, unlike standard RAG hoarding.

Human-in-the-loop pruning beats auto-deletion for AI memory files.
Claude Code users with bloated memory files
It's for getting rid of all of the bloat and crap that builds up in your memory file so that it works better, because when it's too full it stops helping, and seems to actively hurt.
I built it because I noticed that over time my Claude sessions were missing some of the things that I'd asked it to remember.
The reason why this works is because it always asks you for your opinion, rather than pruning on its own.
If you don't trust the model to avoid bloating your memory in the first place, you shouldn't trust it to prune it either.
That's why it has to be an interview-like, diff process. And guess what? It works because it's done that way.
Anyone else noticed theirs bloat? Found anything daft still lurking in there? Mine was full of anecdotes :D
Ebbinghaus decay prunes memory automatically, unlike standard RAG hoarding.
Biologically-inspired memory consolidation that prunes unused facts and strengthens associations overnight.
Entity graph retrieval beats Zep Cloud 59% to 28% on LoCoMo-10 benchmarks.
Rubber-duck architectural review, but Claude asks the hard questions instead.
MoE pruning on MacBook without CUDA or PyTorch dependency stack.
Dual-threshold Dropbox retention (age + count) in pure Bash with dry-run safety, solves real pain.