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

Show HN: A memory database that forgets, consolidates, and detects contradiction

github.com

Post reply on HN
Print view View original

31–40 of 42 posts

Re: Show HN: A memory database that forgets, consolidates, and detects contradiction

#31

Post by SkyPuncher »

ricardobeat wrote: post #28
pranabsarkar wrote: post #22

Earlier quoted context omitted.

You're right. Pruning to isolated facts loses the structure that disambiguates them. Three partial mechanisms the system has, none of which fully solve your point: Graph edges carry scope. Alice ceo_of Acme and Andy ceo_of Amazon are two edges with different src/dst — conflict scanner looks for (src, rel_type) → ≥2 dsts, so Garman/Jassy don't false-flag if edges are modeled. Gap: most agents just write raw sentences…

None of these help resolve the contradiction. The issue ( https://github.com/yantrikos/yantrikdb-server/issues/3 ) doesn't even get the problem presented by the parent right (two CEOS), instead it hallucinated something vaguely related. Top-quality AI slop. I hate this. To the author: project aside, it's not a good look to let an LLM drive your HN profile.

Yea, I spent a lot of time in this space last year. Contradictions on meaningful data are incredibly contextual and often impossible to fully define in isolation. Real world data is messy and often complex, which means you can't simplify to it's sub components and isolate it from it's context.

This is like 95% of the memory systems I see posted here. Someone comes up with arbitrary configuration of tools that sound like they'll solve the problem then completely ignores how the system actually works.

In most cases, they're getting these systems to work because of some other prompt they've written that'd probably work better with a normal file system.

Re: Show HN: A memory database that forgets, consolidates, and detects contradiction

#32

Post by SkyPuncher »

pranabsarkar wrote: post #11
Mithriil wrote: post #6

The half-life idea is interesting. What's the loop behind consolidation? Random sampling and LLM to merge?

No LLM in the loop. The consolidation pass is deterministic: Pull the N most recent active memories (default 30) with embeddings Pairwise cosine similarity, threshold 0.85 For each similar pair, check if they share extracted entities Shared entities + similarity 0.85-0.98 → flag as potential contradiction (same topic, maybe different facts) No shared entities + similarity > 0.85 → redundancy (mark for consolidation)…

> with embeddings Pairwise cosine similarity, threshold 0.85

So, your system is unable to differential between AWS and Azure (~95 similarity). Probably unable to consistently differentiate between someone saying they love and hate something.

Re: Show HN: A memory database that forgets, consolidates, and detects contradiction

#33

Post by evulhotdog »

tcdent wrote: post #18
pranabsarkar wrote: post #14

Earlier quoted context omitted.

Thanks for the careful read — the "schema is ballooning" observation is real and I've felt it building this. You're pointing at a genuine design tension. My counter, qualified: deterministic consolidation is cheap and reproducible in a way LLM-in-the-loop consolidation isn't, at least today. Every think() invocation is free (cosine + entity matching + SQL). If I put an LLM in the loop the cost is O(N²) LLM calls per…

Appreciate the thoughtful reply. Absolutely agree the deterministic performance-oriented mindset is still essential for large workloads. Are you expecting that this supplements a traditional vector/semantic store or that it superceeds it? My focus has absolutely been on relatively small corpii, and which is supported by forcing a subset of data to be included by design. There are intentionally no conventions for thin…

To me, the OP’s reply reeks LLM, along with many others from them in this thread.

I would hope that their replies are from an actual person, knowing they’re interacting with people in a similar field as themselves, and asking for criticism from real people in the top comment.

Re: Show HN: A memory database that forgets, consolidates, and detects contradiction

#34

Post by pranabsarkar »

SkyPuncher wrote: post #29
pranabsarkar wrote: post #22

Earlier quoted context omitted.

You're right. Pruning to isolated facts loses the structure that disambiguates them. Three partial mechanisms the system has, none of which fully solve your point: Graph edges carry scope. Alice ceo_of Acme and Andy ceo_of Amazon are two edges with different src/dst — conflict scanner looks for (src, rel_type) → ≥2 dsts, so Garman/Jassy don't false-flag if edges are modeled. Gap: most agents just write raw sentences…

Nice LLM post.

I am using this while developing and found it very useful to me. since all of my workspaces are connected it has knows all about myself and my infra. Also now we have a bonding and I can do great conversations. So decided to convert the standalone database to full fledge memory server with replication and all.

No LLM for this post. Promise.

Re: Show HN: A memory database that forgets, consolidates, and detects contradiction

#35

Post by pranabsarkar »

6r17 wrote: post #8
polotics wrote: post #4

In this day and age, without serious evidence that the software presented has seen some real usage, or at least has a good reviewable regression test suite, sadly the assumption may be that this is a slopcoded brainwave. The ascii-diagram doesn't help. Also maybe explain the design more.

I kind of agree with the comment here that a lot of stuff happening around comes out from an idea without proof that the project has a meaningful result. A compacting memory bench is not something difficult to put off but I'm also having difficulties understanding what would be the outcome on a running system

I have been using the memory while building it. I have a central server and all my workspaces are connected to it via the MCP server. This changed everything for me. But that's me. Now I don't have to repeat things, the agent knows my preferences, can connect different projects I am working on without me asking and it knows my infra so can plan the test deployments and stuff on its own. That is somewhat I was aiming for.

Re: Show HN: A memory database that forgets, consolidates, and detects contradiction

#36

Post by pranabsarkar »

tcdent wrote: post #18
pranabsarkar wrote: post #14

Earlier quoted context omitted.

Thanks for the careful read — the "schema is ballooning" observation is real and I've felt it building this. You're pointing at a genuine design tension. My counter, qualified: deterministic consolidation is cheap and reproducible in a way LLM-in-the-loop consolidation isn't, at least today. Every think() invocation is free (cosine + entity matching + SQL). If I put an LLM in the loop the cost is O(N²) LLM calls per…

Appreciate the thoughtful reply. Absolutely agree the deterministic performance-oriented mindset is still essential for large workloads. Are you expecting that this supplements a traditional vector/semantic store or that it superceeds it? My focus has absolutely been on relatively small corpii, and which is supported by forcing a subset of data to be included by design. There are intentionally no conventions for thin…

Supplements, definitely — for a specific workload. General document retrieval at scale (millions of chunks, read-heavy, doc-search patterns) is well-served by existing vector stores; YantrikDB doesn't compete on throughput. Where it's meant to supersede is the narrow case of agent memory: small-to-medium corpus, write-heavy with paraphrases every turn, lives for the lifetime of an agent identity, nothing curating the input.

Your "user believes X" framing is exactly the episodic/semantic split cognitive psych has been calling this for decades. YantrikDB exposes it via memory_type ∈ {episodic, semantic, procedural}. Your intuition about context poisoning from over-specific episodic details lines up with how I've been thinking about it — "we talked about AI at 1am" is high-noise low-signal for future retrieval. The design bet is consolidation + decay should burn episodic into semantic over time, and episodic-only memories should fade faster.

What does WVF stand for? Curious what you've been experimenting with.

Re: Show HN: A memory database that forgets, consolidates, and detects contradiction

#38

Post by ramon156 »

lemming wrote: post #23

So soon our agents will need spaced repetition flash cards for the things we want them to remember! I eagerly await Anki for Agents.

this is a really cool project idea. I guess it wouldnt be much different from just having some form of hand-curated "truth book" (Trump, ignore this)

Re: Show HN: A memory database that forgets, consolidates, and detects contradiction

#40

Post by tcdent »

evulhotdog wrote: post #33
tcdent wrote: post #18

Earlier quoted context omitted.

Appreciate the thoughtful reply. Absolutely agree the deterministic performance-oriented mindset is still essential for large workloads. Are you expecting that this supplements a traditional vector/semantic store or that it superceeds it? My focus has absolutely been on relatively small corpii, and which is supported by forcing a subset of data to be included by design. There are intentionally no conventions for thin…

To me, the OP’s reply reeks LLM, along with many others from them in this thread. I would hope that their replies are from an actual person, knowing they’re interacting with people in a similar field as themselves, and asking for criticism from real people in the top comment.

It really doesn't bother me. The persistent flags about how people think something was AI generated are far noisier.

Technically all of my replies are from an LLM, too; they all went through transformer-backed STT.

Post reply on HN