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

Hermes Agent – Open-source AI agent with persistent memory

hermes-agent.org

Post reply on HN
Print view View original

11–20 of 46 posts

Re: Hermes Agent – Open-source AI agent with persistent memory

#11

Post by sergiotapia »

gabrielsroka wrote: post #8
sergiotapia wrote: post #4

I wonder why this new page exists, isn't this the same thing? https://hermes-agent.nousresearch.com/ Actually until the team comments, this page seems suspect. Why is the domain not in nousresearch.com?

> This is an independent information website about Hermes Agent, an open-source autonomous AI agent by Nous Research. We are not affiliated with Nous Research or any other organization referenced on this site. https://hermes-agent.org/terms-of-service/

Oh hell no. "Let me steal your secret keys" basically. This submission should be removed.

Re: Hermes Agent – Open-source AI agent with persistent memory

#13

Post by embedding-shape »

hank1931 wrote: post #9
eranation wrote: post #2

Surprised it wasn't on the homepage yet, my X / LinkedIn feed is non stop about it. I would love to hear from someone who actually played with all the FOMO harnesses / frameworks and actually did a first impression comparison on what to try out (I'm sure it's not even apples to apples) or discovered that it's all marginally better at best from just rolling your own via Claude Code / Codex / Cursor... - paperclip - he…

Check out Eve ( https://eve.new ). I saw it here on Hacker News after I decided OpenClaw was too raw for me. Eve is amazing. My theory as to why it's so good is that the founders have a strong background in design -- they met getting their masters in design at UC Berkeley. Their secret sauce is the harness they've constructed IMHO. Here is what Zach Dive said in the original HN announcement-- Eve is an AI agent harne…

> Check out Eve (https://eve.new).

> Continue with Google/Email

Seems very different from the other listed options in parent's comment if you need an online account with Eve to even use it.

Re: Hermes Agent – Open-source AI agent with persistent memory

#14

Post by throwaway67678 »

eranation wrote: post #2

Surprised it wasn't on the homepage yet, my X / LinkedIn feed is non stop about it. I would love to hear from someone who actually played with all the FOMO harnesses / frameworks and actually did a first impression comparison on what to try out (I'm sure it's not even apples to apples) or discovered that it's all marginally better at best from just rolling your own via Claude Code / Codex / Cursor... - paperclip - he…

Hermes is more general purpose, like openclaw. Pi and opencode are more specific to coding.

Hermes accomodates other coding agents pretty well and has in fact bundled skills for claude code and codex (for spawning subagents, delegating, etc.). They are not exclusive

I haven't tried these 'agent fleet' frameworks in depth and am not sure yet they are not just a gimmick. Both openclaw and hermes handle multi-agennt orchestration, fwiw. Gas town looks like a silly way to burn all your tokens in a day. Paperclip is just buggy. I'm waiting for them to become more mature

Re: Hermes Agent – Open-source AI agent with persistent memory

#17

Post by babelfish »

sergiotapia wrote: post #11
gabrielsroka wrote: post #8

Earlier quoted context omitted.

> This is an independent information website about Hermes Agent, an open-source autonomous AI agent by Nous Research. We are not affiliated with Nous Research or any other organization referenced on this site. https://hermes-agent.org/terms-of-service/

Oh hell no. "Let me steal your secret keys" basically. This submission should be removed.

What? This is just a documentation site. Everything points to the official repo/resources.

Re: Hermes Agent – Open-source AI agent with persistent memory

#18

Post by lxe »

KennyBlanken wrote: post #15

Why do these AI agents keep using Telegram as their channel for user communication? Telegram is literally a spying platform run by the FSB?

Have you tried setting up a bot for something like WhatsApp? I'd much rather use a KGB spy platform with actual user ergonomics.

Re: Hermes Agent – Open-source AI agent with persistent memory

#19

Post by hankbond »

eranation wrote: post #2

Surprised it wasn't on the homepage yet, my X / LinkedIn feed is non stop about it. I would love to hear from someone who actually played with all the FOMO harnesses / frameworks and actually did a first impression comparison on what to try out (I'm sure it's not even apples to apples) or discovered that it's all marginally better at best from just rolling your own via Claude Code / Codex / Cursor... - paperclip - he…

I don't really see how Pi is a FOMO framework. It's basically the minimal surface area framework for you to build other things on. I'm building some agent powered applications and I would have no ability to do that reliably on Claude Code/codex/cursor because they lack the integration depth I need, that Pi provides.
Post reply on HN