A Reg

@RcSteen76 @chrysb @openclaw Use Hermes instead

@chrysb @openclaw Yeah, been trying to get used to it. It’s seems to be working but it is like my agent had a lobotomy.

gpt 5.4 in @openclaw 2026.4.5 is a bizarre experience to say the least caveman vibes

@jwsaml Yes. Much easier setup. Daily use is better imo. Super happy I made the change.

Has anyone fully replaced their OpenClaw with Hermes?

@ElonFinkelstein @dansemperepico Oh yea Hermes can just go into those folders and work on them and then update whatever readme or handoff summary you have in those project folders so that OpenClaw knows what was done.

@CaptAlbertoR @dansemperepico No i meant can they work separately on the same projects? All of my openclaw projects are inside the claw folders. I realize This is prob a stupid question as Hermes can easily just open those folders

It’s actually hilarious that OpenAI bought OpenClaw but their models are 🐶💩 on it. This was their perfect chance to take back market share, but I bet most people would rather pay for Anthropic’s API than have to deal with this all the time.

@einefrau_happy Does it need extra usage? Or does it run within the paid subscription?

그래서 이미 Hermes 에이전트를 oauth 방식으로 Claude(구독) sonnet과 연결해 사용 중!… 인데 이것도 언제 막힐지 모름 🤔

@ElonFinkelstein @dansemperepico No, completely separate projects. OpenClaw is Node.js, Hermes is Python. Different architectures, different teams. They just both run on the same machine. Think like running slack and discord on the same computer.

@CaptAlbertoR @dansemperepico Do they work on the same code base?

@CieloBonit Do enough research into the early church and the apostolic fathers and you will see what its all about.

What’s with everyone becoming a Catholic?

@ashen_one Hermes keeps context of what we’re doing so much better and it doesn’t do the lazy agent thing of saying it’s gonna do something and the never actually doing it.

to all using hermes agent right now instead of openclaw what are your key differences you’re seeing? i’m gonna convert one of my boys to hermes tomorrow

@flow_goes_indie Option 3: Hermes

How to fix your OpenClaw: Option 1: panic, search Twitter and Google for hours, read the 48th blog post, and keep spinning Option 2: switch to openai-codex/gpt-5.4 and just try it

@BillyPrempeh Welcome Home 🇻🇦

I’m officially Catholic. Good to finally be home.

@jahel_beck24 Welcome home 🇻🇦

Finally, I got baptized and my confirmation!! I’m officially Catholic!! 🇻🇦🇻🇦

@keithtyser @openclaw Same. Switched to Hermes and it was night and day.

gpt-5.4 was basically unusable for me in @openclaw. it would explain what needs to be done, I’d say “ok do it,” and then… nothing. no action, no feedback, sometimes it would just go silent or say it’s “working” with zero visibility. felt like babysitting an intern that never actually touched the keyboard switched to @NousResearch Hermes agent and it’s night and day. same model, but now it actually executes. on par with opus-4.6 for me no idea why the gap is that big but yeah, huge relief after losing Claude OAuth in openclaw

@jescalan Been there. I recommend trying Hermes.

Transition to gpt in openclaw not going so great this far 😂

@JeremyTate41 Correct

I lost a lot of followers for posting about Catholicism, that’s fine, I don’t mean to push my religion on anyone, I only think the Catholic Church is right about literally everything.

To all the new Catholics- Welcome Home 🇻🇦

@chrysb @openclaw I set up Hermes in maybe 10% of the time it took to set up my OpenClaw

hermes agent setup is way more tedious than setting up @openclaw!

@philkellr Switch to Hermes agent. Same issues here. Hermes is night and day.

I'm tired of OpenClaw Every 2-3 days I have a major moment which I show to my friends: "look what AI agents can do", but then the other 90% is pure frustration and me cursing at my own AI agent for which I spent hours choosing a beautiful name and profile picture. I was fun at start: I added telegram, added voice input, then adding skills even with just voice prompting was a bliss. Then dementia hit. Facts from 48+ hours ago were forgotten. I installed a 3 level memory system. It felt like a huge hack, it barely works, I encounter bugs every day which I'm fixing. Then it breaks with every update. Not all of it, but little things. The WhatsApp integration is just insanity. After putting in every markdown file that it shouldn't reply to my friends (IN CAPITAL LETTERS) it happily started to chat with my wife and my goddaughter. And from today even claude subscription stops working. I feel like a failure! I see all the success stories left and right, YT vids and blog posts "I got it to work and here's what the AI agent does for me", and for me I'm still spending 5x the time fixing my agent than just doing the stuff by hand 🤷

Average input cost nets out to $0.087/m. This is INSANE for an American model at this performance. I think I found my daily driver. LFG

@arcee_ai @kilocode @openclaw @pinchbench This is wiiiild

Jensen showcased PinchBench (by @kilocode) on stage at NVIDIA GTC as the new standard for evaluating @openclaw agent capability. Trinity-Large-Thinking just hit #2 on @pinchbench globally (91.9%) behind only Claude Opus 4.6 (93.3%), which costs ~20x more per token. That's an expensive percentage point... To celebrate the ongoing Trinity partnership, @OpenRouter is running a promotion to make Trinity-Large-Thinking free to use for OpenClaw until Sunday, April 5th. Even when the promo ends, the Trinity economics are pretty incredible. Trinity is $0.25/m input tokens (OpenClaw uses A LOT of input tokens), but with a 60%-90% cache hit rate at $0.06/m cache tokens the average input cost nets out to $0.087/m. You no longer have to compromise on logic to keep your agent infrastructure affordable. We're excited to see what you build.

@hosseeb Night and day for me tbh. Hermes killin it

Anyone using Hermes Agent in the wild? What do you find it's better at vs OpenClaw?