Jordan Muir

@danthaeon @Rigario @honchodotdev Would also like to know, I’ve gone through $56 in 8 days just running a single Hermes agent

@Rigario @honchodotdev how do ur costs self hosting compare to their API?

If you've recently installed Hermes Agent and are having memory problems, you need @honchodotdev. It literally makes it go away. Hell, even if you're using openclaw, use honcho.dev. I've tried most of the other popular memory systems, honcho is the customizable, reliable, portable and requires the least tinkering. Use it with all your agents and never regret. I self-host, but their costs are reasonable and its easier to get started.

@Chris65536 @sandislonjsak Yep, I’ve developed a very bad habit of sending a prompt & instantly switching to X😂

@JordanMuirFS @sandislonjsak waiting on one, i wind up on x 😂

My brain simply can't run more than 3 agents in parallel and QA all of their work. I am sure I am not the only one. How do people manage 10 at once? Or they simply lie?

I really hope @OpenAI releases a $100 plan soon. Using codex and Claude would be a seriously good combo for only $200. The 2 models reviewing each others work catches so many gaps a single model misses. @garrytan Gstack skill has proved this massively

@furrkios I’m not too concerned, chat history is local and traffic goes direct to model provider. It’s definitely improved my workflow, instead of multiple terminals open, everything lives in one place. Then there are QOL things like creating PRs, Merging, Fixing test errors in one place

@JordanMuirFS I want to use that as well. But I have privacy concerns. Have you checked that part? Do you recommend?

I keep seeing posts about people using their weekly limits in 2 days. I guess Claude Max 20x is wasted on me, 15% used in 48 hours, 90% of my usage is in peak hours too

@furrkios I use conductor, I haven’t touched Claude code itself in a few weeks now

@JordanMuirFS What is your claude code version

@garrytan Would it not make more sense to have the skill generate actual HTML + CSS concepts of sections which follow proper web design principles? Or am I missing the point? How does it determine a design direction off of these generated images?

@garrytan I'm not sure with this feature, how do you decide a design direction based on AI generated slop images that don't really resemble good website hierarchy and layout. I've just tried it and got 6 variations of randomness thrown onto an image that make absolutely 0 sense at all

GStack is about to become a full design brainstorm tool called /design-shotgun Just go in any direction, see variations, tell GStack what you like, and we'll make beautiful things together

@vintrotweets @Inner_Axiom @xmovieking This definitely ruins it for me, probably unavoidable, but if there were clearer instructions on how my data is stored, protected etc then that would be better. I like the convenience of everything being managed, but I will likely be switching to self hosting soon

@vintrotweets @Inner_Axiom @xmovieking One thing that didn’t sit well with me is I can go into my Honcho dashboard and see my entire conversation history with my Hermes agent, so everything is stored on your servers, with no information anywhere that I could see about privacy. Can anyone from the team look at it?

i'm looking to talk to more hermes agent users running honcho 🫡 what are you doing with HA? how's it been working? any noticeable improvements from honcho? even if you're not sure how honcho's making a difference, i'd love to learn more about your HA usage. pls DM!

Loaded up Claude Code to get some work done last night, Opus was down. 14 hours later I get some time to go back to the project, Opus is down again. What is going on? @AnthropicAI

@jonathan_wilke @supastarter But with that said 349 is still a very fair price

@jonathan_wilke @supastarter But that is because I’m a sucker for a deal😂 It can make me buy something I might never use

What do you think is the better price for @supastarter ? $349 or $299 ?

@0xOrkward @paper I like it too, but struggle a lot to maintain design consistency between frames from the AI

i'm using @paper lately to quickly wireframe some designs that i want to code. it's been very helpful so far. paper+claude code is a good combo.