Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Core – open source memory graph for LLMs – shareable, user owned

github.com

Post reply on HN
Print view View original

1–10 of 43 posts

Show HN: Core – open source memory graph for LLMs – shareable, user owned

#1

Post by Manik_agg »

I keep running in the same problem of each AI app “remembers” me in its own silo. ChatGPT knows my project details, Cursor forgets them, Claude starts from zero… so I end up re-explaining myself dozens of times a day across these apps.

The deeper problem

1. Not portable – context is vendor-locked; nothing travels across tools.

2. Not relational – most memory systems store only the latest fact (“sticky notes”) with no history or provenance.

3. Not yours – your AI memory is sensitive first-party data, yet you have no control over where it lives or how it’s queried.

Demo video: https://youtu.be/iANZ32dnK60

Repo: https://github.com/RedPlanetHQ/core

What we built

- CORE (Context Oriented Relational Engine): An open source, shareable knowledge graph (your memory vault) that lets any LLM (ChatGPT, Cursor, Claude, SOL, etc.) share and query the same persistent context.

- Temporal + relational: Every fact gets a full version history (who, when, why), and nothing is wiped out when you change it—just timestamped and retired.

- Local-first or hosted: Run it offline in Docker, or use our hosted instance. You choose which memories sync and which stay private.

Try it

- Hosted free tier (HN launch): https://core.heysol.ai

- Docs: https://docs.heysol.ai/core/overview

Show HN: Core – open source memory graph for LLMs – shareable, user owned
github.com

Re: Show HN: Core – open source memory graph for LLMs – shareable, user owned

#4

Post by adamkochanowicz »

For those asking how this is different from a simple text based memory archive, I think that is answered here:

--- Unlike most memory systems—which act like basic sticky notes, only showing what’s true right now. C.O.R.E is built as a dynamic, living temporal knowledge graph:

Every fact is a first-class “Statement” with full history, not just a static edge between entities. Each statement includes what was said, who said it, when it happened, and why it matters. You get full transparency: you can always trace the source, see what changed, and explore why the system “believes” something. ---

Re: Show HN: Core – open source memory graph for LLMs – shareable, user owned

#5

Post by jadbox »

funnym0nk3y wrote: post #2

I don't see the advantage over a simple text file accessible by MCP. Could you elaborate?

I don't know this project, but the is probably simplicity/performance benefits to using a proxy over MCP as in theory there is less overhead.

Re: Show HN: Core – open source memory graph for LLMs – shareable, user owned

#7

Post by ianbicking »

I've been building a memory system myself, so I have some thoughts...

Why use a knowledge graph/triples? I have not been able to come up with any use for the predicate or reason to make these associations. Simple flat statements seem entirely sufficient and more accurate to the source material.

... OK, looking a little more, I'm guessing it is a way to see when a memory should be updated; you can match on the first two items of the predicate. In a sense you are normalizing the input and hoping that shows an update or duplicate memory.

I would be curious how well this works in practice. I've spent a fair amount of effort trying to merge and deduplicate memories in a more ad hoc way, generally using the LLM for this process (giving it a new memory and a list of old memories). It would feel much more deterministic and understandable to do this in a structured way. On the other hand I'm not sure how stable these triples would be. Would they all end up attached to the user? And will the predicate be helpful to establish meaningful relationships, or could the memories simply be attached to an entity?

For instance I could list a bunch of facts related to my house: the address, which room I sleep in, upcoming and past repairs, observations on the yard, etc. Many (but not all) of these could be best represented as one "about my house" memory, with all the details embedded in one string of natural language text. It would be great to structure repairs... but how will that work? (my house, needs repair, attic bath)? Or (my house, has room, attic bathroom) and (attic bathroom, needs repair, bath)? Will the system pick one somewhat arbitrarily then, being able to see that past memory, replicate its structure?

Another representation that occurs to for detecting duplicates and updates is simply "is related to entities". This creates a flatter database where there's less ambiguity in how memories are represented.

Anyway, that's one area that stuck out to me. It wasn't clear to me where the schema for memories is in the codebase, I think that would be very useful to understanding the system.

Re: Show HN: Core – open source memory graph for LLMs – shareable, user owned

#8

Post by lukev »

So, this is cool and a per-user memory is obviously relevant for effective LLM use. And major props for the temporal focus.

However, keeping a tight, constrained context turns out to actually be pretty important for correct LLM results (https://www.dbreunig.com/2025/06/22/how-contexts-fail-and-ho...).

Do you have a take on how we reconcile the tension between these objectives? How to make sure the model has access to relevant info, while explicitly excluding irrelevant or confounding factors from the context?

Re: Show HN: Core – open source memory graph for LLMs – shareable, user owned

#10

Post by khaledh »

I love how we have come full circle. Anybody remembers the "semantic web" (RDF-based knowledge graph)? It didn't take off because building and maintaining such a graph requires extensive knowledge engineering work and tools. Fast forward a couple of decades and we have LLMs, which is basically auto-complete on steroids based on general knowledge, with the downside that it doesn't "remember" any facts unless you spoon-feed it with the right context. We're now back to: "let's encode context knowledge as a graph and plug it into LLMs". Fun times :)
Post reply on HN