Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do • Hacker News Board

Re: Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

#51

Post by eterm » Sat, Apr 25, 2026, 2:36 PM UTC

kuboble wrote: post #37

aprilnya wrote: post #30

I clicked this thinking “oh, cool, someone finally made a portable version of the Claude.ai* memory system!” Spoiler, no, it’s not it at all, it’s just a “store”/“remember” memory system… as opposed to the Claude.ai memory system, where it doesn’t make the model actively have to write memories on its own, but rather has a model in the background go through your chat history and generate a summary from it. I’ve found…

That's an interesting concept. So it's like if you're an agent chatting with a user, you have an army of assistants who overhear the conversation and record important facts, or search relevant facts on some database and decide on the fly when to interrupt you with "this memory X looks relevant". Sounds easy enough if tokens were free, but an interesting problem to do it efficiently.

That's exactly what claude-code does these days. If you AFK for ~5 minutes it also produces a summary of where you are, which is useful if you're juggling multiple windows.

Re: Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

#52

Post by zby » Sat, Apr 25, 2026, 2:42 PM UTC

Reviewed: https://zby.github.io/commonplace/agent-memory-systems/revie...

Together with the other hundred llm memory systems: https://zby.github.io/commonplace/agent-memory-systems/

I have also written a wishlist for these systems: https://zby.github.io/commonplace/notes/designing-agent-memo...

Re: Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

#53

Post by eleventen » Sat, Apr 25, 2026, 2:45 PM UTC

braiamp wrote: post #27

What the heck is happening on this site with the pointer disappearing? For some reason the body tag has "cursor: none" which is never good.

The traditional cursor is so 2025. It's predictable. Familiar. old.

AI is the future, so we need cursors of the future that simulate the frustrating lag and imprecision of LLMS. Dots chase other little dots around and do inscrutable little animations.

Actual answer: You need javascript to see their dumb custom cursor.

Re: Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

#54

Post by conception » Sat, Apr 25, 2026, 2:53 PM UTC

aprilnya wrote: post #30

I clicked this thinking “oh, cool, someone finally made a portable version of the Claude.ai* memory system!” Spoiler, no, it’s not it at all, it’s just a “store”/“remember” memory system… as opposed to the Claude.ai memory system, where it doesn’t make the model actively have to write memories on its own, but rather has a model in the background go through your chat history and generate a summary from it. I’ve found…

Just write a hook that runs claude -p after whatever you want and update whatever memory system you want. You can use a channel to inject back what topics were update or what have you.

Re: Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

#55

Post by milkshakes » Sat, Apr 25, 2026, 3:01 PM UTC

dwb wrote: post #48

looksjjhg wrote: post #43

Earlier quoted context omitted.

I’m sorry this sounds a bit too entitled - no one is putting a gun to your head to use this project and you know you can always read the code and review it yourself and make an educated decision on whether you want to use it or not

I don’t think I’m entitled to what I suggested, I don’t see how you’re reading that.

it's free code. if you're so concerned about the quality, you can read it yourself.

Re: Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

#56

Post by zby » Sat, Apr 25, 2026, 3:02 PM UTC

Incipient wrote: post #12

I still haven't found useful "memory". It's either an agents.md with a high level summary, which is fairly useless for specific details (eg "editing this element needs to mark this other element as a draft") or something detailed and explaining the nitty gritty, which seems to give too much detail such that it gets ignored, or detail from one functional area contaminates the intended changes in another functional are…

I have a wishlist for these systems: https://zby.github.io/commonplace/notes/designing-agent-memo...

Re: Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

#57

Post by OsrsNeedsf2P » Sat, Apr 25, 2026, 3:05 PM UTC

I'd like to use this for our locally running game agent[0] but the PostgreSQL and other dependencies is a show stopper. Why so complex?

[0] Ziva.sh is a desktop app that brings agentic features to game engines. We can't just bundle a running DB and we won't be sending this sensitive info to a cloud

Re: Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

#58

Post by mncharity » Sat, Apr 25, 2026, 3:20 PM UTC

kuboble wrote: post #37

aprilnya wrote: post #30

I clicked this thinking “oh, cool, someone finally made a portable version of the Claude.ai* memory system!” Spoiler, no, it’s not it at all, it’s just a “store”/“remember” memory system… as opposed to the Claude.ai memory system, where it doesn’t make the model actively have to write memories on its own, but rather has a model in the background go through your chat history and generate a summary from it. I’ve found…

That's an interesting concept. So it's like if you're an agent chatting with a user, you have an army of assistants who overhear the conversation and record important facts, or search relevant facts on some database and decide on the fly when to interrupt you with "this memory X looks relevant". Sounds easy enough if tokens were free, but an interesting problem to do it efficiently.

Burst-parallel non-frontier models can resemble "tokens were free". And there one might potentially augment not just conversations, but CoT - retroactively by submitting messages with altered reasoning strings, or inline with the inference loop watching CoT and attempting non-distracting injection.

Re: Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

#59

Post by dwb » Sat, Apr 25, 2026, 3:38 PM UTC

milkshakes wrote: post #55

dwb wrote: post #48

Earlier quoted context omitted.

I don’t think I’m entitled to what I suggested, I don’t see how you’re reading that.

it's free code. if you're so concerned about the quality, you can read it yourself.

And if anyone is so put out by my suggestion (that I said I'd hold myself to as well), they can just ignore me and move on. I posted a comment on a public forum about what I'd like, I'm not the boss of anyone.

Re: Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

#60

Post by devmor » Sat, Apr 25, 2026, 4:21 PM UTC

jFriedensreich wrote: post #28

All these agent memory systems seem so simultaneously over and under engineered and like a certain dead end. I cannot imagine any reality in which this does not rot and get out of sync with what the latest model need. For the one time you build a payment provider how many session will be tilted towards thinking about payments because of the "don't use stripe" memory?

I have a bespoke memory system that I wrote myself and it avoids this problem entirely by making every memory a contextual search space. The “don’t use stripe” memory would only be recalled into context if the model was prompted to do something with payment processing.