Mar 30 (edited) • 🛠️ Show Your Work
Multi-agent memory management with... folders and files
Open sourced a memory management plugin for Claude Code (and Cowork) a little while back. asked for the architectural specifics, so I'm happy to oblige.
Some interesting observations and findings in it, but I could really use a researcher's endorsement for publication on arxiv.org under CS.AI. Referrals are deeply appreciated.
Full disclosure: while I said "multi-agent" the reality of it is that the orchestration layer predominantly runs as a single agent roleplaying different agents depending on the folder it's running in. This is the main lesson means when he speaks of folders.
Being the over-engineer that I am, sometimes I am tempted to run tasks with multiple agents running in the background. PMM makes it quite context-window efficient (so I don't burn as many tokens or run into message limits on Claude Code).
6:54
33
73 comments
Multi-agent memory management with... folders and files
skool.com/quantum-quill-lyceum-1116
Jake Van Clief, giving you the Cliff notes on the new AI age.
Leaderboard (30-day)
1
+767
2
+658
3
+464
4
+392
5
+387
Powered by