Earlier quoted context omitted.
What does it do?
In very simple terms it can provide a full and live audit on how any frozen model arrives to any answer.
What does "frozen model" mean in this context?
Universal Memory Protocol – a shared format for agent memory
41–46 of 46 posts
Re: Universal Memory Protocol – a shared format for agent memory
#42Re: Universal Memory Protocol – a shared format for agent memory
#43A lot of shaming and negative comments. Mainly people annoyed that this is created with LLM usage. Comments like, the author is grandiose, he/she is delusional, the repo was committed yesterday etc. It seems to be a lot of folks in the community are just lethargic to anything created by LLMs. But regarding the idea itself, the author basically abstracted and use MCP as the server/interface. I worked a bit on the memo…
> It seems to be a lot of folks in the community are just lethargic to anything created by LLMs.
I dislike "overpromise and underdeliver". LLMs can of course be used for other things, but for the type of person who overpromises and underdelivers, LLMs seem to be particularly attractive, and act as a force-multiplier.
> before LLMs, the author could have just said in a blog, oh why not have a universal protocol for memory?
a blog post would at least have been honest. "here's an idea I had, what do you think?"
likewise, a blog post plus a link to a GitHub repo containing a prototype would have been fine, as long as the prototype is clearly labeled as such. "here's an idea I had, plus a sketch of how a concrete implementation might work, what do you think?"
what LLMs enable is overpromise-and-underdeliver-as-a-service. this idea could have been a blog post, or a simple prototype, but what we get instead is a fancy-looking website, with its own domain, for this half-baked idea.
if you take the polished website at face value, you would be misled into thinking that the idea itself is also polished. hence the comments exercising some critical thinking and pointing out that this "universal protocol"...doesn't actually have any real-world usage, anywhere in the universe.
Re: Universal Memory Protocol – a shared format for agent memory
#44It is 2026. Average people build their own harnesses, and imagine themselves the pioneers of industry. They propose protocols. They code, feverishly, into the night, driven by their vision for the future. It used to be that 'idea guys' were limited by execution. We now feel the avalanche of these ideas, even maybe executed half-decently, fall upon deaf ears and zero market.
Yes https://github.com/space-bacon/SRT I can read any models every thought. No one cares. Not the narrative.
I'm afraid we've had to ban this account for the time being. We've been getting complaints from readers that the comments posted by the account are a combination of off-topic and excessively promotional. After looking this over, I agree.
I have no idea if this is relevant, but sometimes HN commenters go through phases where they overdo this kind of posting for personal reasons. If that is the case here, then if and when it changes, you'd be welcome to email hn@ycombinator.com and we can look into unbanning your account at that point.
Re: Universal Memory Protocol – a shared format for agent memory
#45Earlier quoted context omitted.
Yes https://github.com/space-bacon/SRT I can read any models every thought. No one cares. Not the narrative.
I'm afraid we've had to ban this account for the time being. We've been getting complaints from readers that the comments posted by the account are a combination of off-topic and excessively promotional. After looking this over, I agree. I have no idea if this is relevant, but sometimes HN commenters go through phases where they overdo this kind of posting for personal reasons. If that is the case here, then if and w…
[dead]
Re: Universal Memory Protocol – a shared format for agent memory
#46This seems way too complicated and unnecessary. Agents are perfectly capable of discovering memories on the FS, following agent instructions. I guess this adds indexing and querying but most coding agents have good solutions for this already, and it works automagically for everything, not just memories. What we could use instead is a file system layout standard, which could subsume memories and a lot more. I don't th…
[flagged]