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 think that's needed either, but it would probably solve more problems than this.

with apologies to Andy Warhol - in the future, everyone will have a universal protocol for agent memory that is on the HN front page for 15 minutes.

0: https://github.com/edihasaj/universal-memory-protocol/commit...

MCP came from Anthropic, A2A from Google so they had big tech backing from day 1.

As a developer, I wouldn’t touch this without confidence I can get gains down the line from interoperability.

What is a bi-temporal record? I don’t think I’ve heard the term before and I’d love to learn more.

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 memory issue of agents, and I do understand the pain point. So I just looked at the article as a source of aspiration, another interesting idea etc..before LLMs, the author could have just said in a blog, oh why not have a universal protocol for memory? But now the author can actually do it, try it, share it with others, and for one see this as a progress, it might inspire other people.

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.

> Memory is attacker-controllable input. The spec requires a verify, filter, frame rehydration pipeline. Never string-interpolated into the prompt.

Uhhh... so who wants to tell them how LLMs work?

For example, I would expect to see tables or figures showing task success rates on some benchmarks for agents augmented with and without this proposal, perhaps before and after fine tuning, or running against alternatives or to the extent that there are no alternatives against variations of this design that were considered and rejected.

Otherwise what reason is there to think that this design is better than some alternative or even any good at all? Perhaps it causes agents to hallucinate like crazy-- who knows if it hasn't been tested.

Work like that is what makes efforts like this worth sharing and worth reading about-- anyone can spend a few minutes and ask their favorite LLM to design such a framework and get something that looks "credible". But in a post LLM world credible alone is externally indistinguishable from anti-social time wasting slop.

UMP v0.1 is a shared format plus a simple way to read, write, update, and move agent memory across tools. The goal is memory that's user-owned, auditable, and extensible across agents and runtimes, instead of locked inside one vendor.

It's early (v0.1) and I'd love feedback on the format and where it breaks down. Repo and spec are linked from the site.