---
title: "Comment by Salman Parvez | ML Systems on \"Memory for AI Agents: Architectures, Tools, and How to Choose the Right One\" | Hashnode"
description: "The checklist question I'd move to the top is the audit one, and I'd sharpen it: can you see who wrote each memory and what it's based on? The shared notebook m"
url: "https://hashnode.com/posts/memory-for-ai-agents-architectures-tools-and-how-to-choose-the-right-one/6aafe54cba9d858bd7839d67/comment/6aaffd71dd5a650187f5c496"
---

[Discussion](https://hashnode.com/posts/memory-for-ai-agents-architectures-tools-and-how-to-choose-the-right-one/6aafe54cba9d858bd7839d67)

Comment [Memory for AI Agents: Architectures, Tools, and How to Choose the Right One](https://hashnode.com/posts/memory-for-ai-agents-architectures-tools-and-how-to-choose-the-right-one/6aafe54cba9d858bd7839d67)

[Salman Parvez | ML Systems](https://hashnode.com/@ml-systems)

[Sep 20](https://hashnode.com/posts/memory-for-ai-agents-architectures-tools-and-how-to-choose-the-right-one/6aafe54cba9d858bd7839d67/comment/6aaffd71dd5a650187f5c496)

The checklist question I'd move to the top is the audit one, and I'd sharpen it: can you see who wrote each memory and what it's based on? The shared notebook model is close to what I run for seven agents and one human on a house record at a construction company in Rhode Island. Everything shared lives at the house level, but no agent gets to write a fact. It writes a claim: the value, its own name, and an evidence grade at the bottom of the ladder. "Alice uses PostgreSQL" is a stated claim until Alice or another person confirms it, and nothing moves up a grade by being recalled often. That's my one quarrel with decay scoring. Frequently recalled isn't the same as true, and the memory I most need on a job is usually the unpopular measurement. The agents don't share memories with each other directly either. The ledger is the only conversation between them. Fewer surprises that way.