The naming of this project is quite unfortunate as it resembles the Simplex [1] specification for guiding agent development, which does look promising in comparison.

[1]: https://github.com/thinkwright/simplex

Using vector embeddings in place of a rigid API is an interesting concept, but the codebase basically leaves it as a TODO: https://github.com/olserra/agent-semantic-protocol/blob/9d15...

Strange, given that seems to be the whole premise of the project.

> how can you delete someone's else's github repo.

Seriously. Burying of this slop is not enough. Can we perhaps have a bot that reads repos like this and attaches a tag of shame to the posters?

I think the README could use a few real use-case examples. I understand it in an abstract sense, but not sure I understand the benefit vs plain-text communication, besides saving on token spend.

Why not just use natural language?

Because "latent semantic vectors" sounds way cooler.

This is AI slop & if you can't tell from a glance then you should figure out why you believe the nonsense on this page is actually sensible.

vibecoded cryptography will never stop being funny https://github.com/olserra/agent-semantic-protocol/blob/9d15...

You owe me a coffee and keyboard

Symplex v0.1 now features per-message Ed25519 signing! Every IntentMessage and NegotiationResponse is cryptographically signed, boosting security and trust in p2p workflows. All tests pass—roadmap milestone achieved. #Symplex #Ed25519 #security #GoLang

I can understand why your LLM told you that "all tests pass", but why are you telling us? What are we supposed to do with that information?

Is this something that mTLS would not solve?