Hacker News Reader

Comment by segmondy | Hacker News Reader

there is no debacle, ". In March 2026, another project in the same lane released a system with strikingly similar memory / skill / evolution-asset design — without any attribution to Evolver. " there is nothing new about memory (aka sessions saved), skills (aka prompt in a file), etc folks have been doing this for 2+ years.

View on HN

I'm sorry but if this is not a debacle, then we're operating under very different premises:

- teknium1 retitled the original issue to "." and edited the issue text to "."

- Nous Research deleted comments from 4 users, including the issue submitter, and blocked all of them.

- No formal response has been given by teknium or the Nous Research project. It appears they are trying their darndest to brush it under the rug.

Ref: https://news.ycombinator.com/item?id=48318706

Looking at their blog about it, I don't think Evolver has any claim to be honest. They make such generic claims as that session history was copied because they implemented their history in some `.jsonl` files while Hermes has a session history using sqlite FTS. Evolver better have some attribution crediting Anthropic for their session history feature, because as far as I can tell they've had that implemented since early 2025! Using .jsonl files no less, coincidentally the same way that Evolver decided to implement session history.

I was expecting them to show code samples or something, but to me it looks more like these were two projects that ended up coming up with similar looking features, even with different implementations of these features. I don't see how Nous Research owes them any explanation, especially since at least from that linked issue they were coming in really hot with accusations of plagiarism. If I owned a large OSS project that amassed issues/discussions/PRs at a rate of ~4k per month I would probably also treat this kind of thing as spam.

"Teknium" was also defending things on X like a Polymarket skill being pre-installed and stuff.

Seems like both projects are a bit unprofessional in terms of leaders. Hermes just tries to sound more authoritative with the "Nous Research" name and fancy site, etc.

Note that the polymarket skill was for using it as a research source, not for placing wagers, and has since been removed as part of a larger streamlining of the included set of skills.

I think they probably understand that those complaints hold weight within a <=2010s ethical framework but now we live in the brave new world.

I have no idea what these three things mean without more context.

This [0] is the issue in question. teknium1 replaced the entire issue text with a dot, and NousResearch deleted a bunch of subsequent comments.

Whether the claims have merit or not, attempting to make the claim go away in this way is at best unprofessional and childish.

[0] https://github.com/NousResearch/hermes-agent/issues/10232

> teknium1 replaced the entire issue

I guess I’m confused about (and more concerned with) the merits of the issue.

If the merits are serious, this is a cover-up. If they’re specious, this is like forum drama. From what I can tell so far, it looks like the latter.

Looks like the complainant blogged about it here:

https://evomap.ai/blog/hermes-agent-evolver-similarity-analy...

Ya I can't take them seriously after reading through that, they sound like a bunch of clowns. There was no evidence of anything other than 'this company had similar features that we offered'

Boo fucking hoo. The desktop agent space converges on a small set of features that overlap. Grow the fuck up.

Evolver claims are complete nonsense. Teknium has responded several times on Twitter. This is a closed issue.

Reply on news.ycombinator.com