Hacker News Reader

Comment by bensyverson | Hacker News Reader

It’s good that a lot of people are trying a lot of things when it comes to agentic memory. Sadly none of it represents a complete solution at this time. But we need the experimentation.

View on HN

I still dont understand what "agentic memory" is . agents can already call sql / rag and grep through files or whatever. why is "agentic memory" a special thing.

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

Right now you have an opportunity to enlighten everyone rather than talk down to them.

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.

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

Sounds like RAG to me.

How does it sound like rag exactly? Rag queries a database and injects the results memory doesn’t do this

"text based index" is just another way of saying "database".

No it isn’t? There is no database and no querying for specific words. An llm reads a big ass block of text and determines if any of those lines are applicable, that is nothing like a database being queried

i think you are confusing database with something like mysql

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.

yea ofcourse you have tell agent how to access you database. But why does it have a specail name, what the big deal about giving agent info how to call your db.

To not repeat yourself every time. If you taught one of your coworkers how to access your db, would you want to have to repeat that every time?

Now extend that to the rest of whatever system you’re working on. Do you want to manually have some preamble for every task you’re doing?

Even purely for convenience and dev experience it’s worth doing imo.

You’re right, we should manually tell every agent everything they need to know upfront at the start of every session.

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).

Reply on news.ycombinator.com