Well, that's just one implementation (the easiest). You may have the harness automatically inject stuff into the ongoing conversation, in which case most of the work is not done by the working agent (though you may still end up using, possibly a smaller model to help with deciding/forming the to-be-injected context).

Just retrieving usually doesn't count as memory. "Memory" tends to imply writing too.

And I agree: it's not a very special thing. That's why I propose: Markdown + a simple embedding.

Agents have to decide to search files, and they don't always know that they should. For example, if the agent sees the database, it may miss detailed instructions on how to access the database deeper in the repo. Behaviorally, humans want to be able to say "hey, here's how to access the DB. Remember that." Or better yet, for it to happen automatically.

That's agentic memory.

You could think of it as a more efficient indexing format for data the agent has access to. It’s badly needed as a better representation or pointer map would improve recall time and comprehensiveness dramatically without having to invest further in model training.

they just want to reinvent information retrieval from first principles; also the fact that everyone forgets to check what currently exists and reinvents hexagonal wheels for the sake of agentic development

Memory isn’t the same thing as rag it’s usually just a text based index of past events and the llm reads it and decides what’s important rather than querying a db