Hermes Agent

Did some Googling, turns out, Hermes has hard coded guardrails against designing or modifying firearm related parts, supposedly not limited to 6.1-Sol. Guess I should have just told Hermes to mind its business instead of giving a legit answer. Asked ChatGPT Work to do it, made the changes no problem.

The handoff is the bit I'd want fixed first: start a task on desktop, open the same conversation on my phone, and approve or reply without those 'started elsewhere' errors. A nicer chat screen doesn't help much if those are separate sessions.

Yes, I have no idea why I am becoming an expert in telegram just to use hermes sessions

Eh, the Nous team doesn't really understand (imo) that sometimes - like, right now - it would be better to focus on a proper, Windows-native installer (Tek said it will be out soon ages ago, didn't happen), a dedicated stable update branch that doesn't crack on every update, a mobile app and easier user onboarding rather then all the Cool Tech Updates. Basically everything that would make it easier for the less techy crowd to access Hermes is ignored, to the point where its reputation on the internet is "fantastic, great devs, the possibilities are wild but it WILL break on you and if you don't already know what you're doing, just forget about it".

Basically everything that would make it easier for the less techy crowd to access Hermes is ignored, to the point where its reputation on the internet is "fantastic, great devs, the possibilities are wild but it WILL break on you and if you don't already know what you're doing, just forget about it". Amazing work, really, and open source is great but they just don't care about being user-friendly at all.

Basically everything that would make it easier for the less techy crowd to access Hermes is ignored, to the point where its reputation on the internet is "fantastic, great devs, the possibilities are wild but it WILL break on you and if you don't already know what you're doing, just forget about it". Amazing work, really, and open source is great but they just don't care about being user-friendly at all. Which is a shame, because it will redirect people into closed ecosystems.

As student I can't afford frontier models only the GPU I've already got, sadly Qwen3.6 is the best I can go with for now :( Browsing websites actually is my only issue, working on my pc itself is fine.

I basically just tell hermes to wrangle the Claude cli. Which works fine, since I usually only want Claude for coding tasks.

Does the desktop app still install a full Hermes Agent setup or is it client only by now? I have Hermes running on a different server. I wanted to install the desktop app as a client interface for that server setup but it wanted to install Hermes on my MacBook. I know I can point the desktop app to my server install later but I don’t want or need to have Hermes installed on my MacBook just to use the desktop app as a client.

Is there a way you keep the gateway running. I noticed that not the hermes gateway btu the photon gateway or something ended (thats what hermes said). the hermes gateway start was on but not the connection to photon or something like that

Only Claude, other models work fine (OpenAI and opencode)

That is the problem, it didn't have root access anyehere, it took my ssh key from my user acc it is running on a vps somewhere in german OVH DC

Also, Hermes guardrails / approval tool call relies on regexes, and changing ansible config or similar isn't just within the cases those catch.

The scores could use some sharpening up for sure

Dont blame Hermes for what could be the fault of the AI model

I like the multi thread experience of grok bot, it's slick without context rot like you get when trying to recreate that in telegram for your Hermes agent.

If you could get me a good mobile app that will let me seamlessly continue my work on the move, I will cancel all my other subscriptions and go for Nous.

After spending some time learning to use hermes properly, I'm really impressed. It's almost perfect.

The process that works for me right now is leveraging Claude code to get a Hermes capability and any supporting process(es) to production, and then Hermes with deepseek or glm to execute day-to-day, learn, and marginal improvements. I still rely on Claude for bigger functional leaps, though. It works for me and seems to get me to a working solution faster than just Hermes solo.

I have mine note problems in a to-do list so he can research them later in a cron job. That was the entirety of my suggestion. Here is the last update I got (the table didn't cut and paste well from telegram), and this is just the flash model. It's basically become a running system health and the small stuff gets fixed automatically. He leaves the bug stuff for me, which is usually "file a bug for that so Neo can fix it". I could never keep up with all this without him!