Akim

@Teknium Can I use this on mobile?

Our first dive into Multi-Agent Coordination and Cooperation is here, with Hermes Agent Kanban Orchestrate tasks across multiple agent profiles and dependencies easily and visually. Achieve more. See the docs here: hermes-agent.nousresearch.com/docs/user-guid…

@LexnLin Interested to see what these would look on mobile

UPDATE for imagegen-frontend-web skill more "creative" outputs - different layouts - better understanding of the request skill: github.com/Leonxlnx/taste…

@ozgurozturknet Is it actually usable tho

Yav bu deepseek neymiş böyle. Claude ile merhaba diyorsun bismillah 25 dolar. İki gündür deepseek'i ırgat gibi çalıştırıyorum, gerçek ırgat olsa iki katlı evi tek başına dikmisti o kadar çok çalıştırıyorum daha yarım dolar yakmamış.

@liu8in @HyperFrames_ Is there something like a guide that I can feed my agent to get to know Hyperframes and it’s capabilities better so it can make better videos?

if you are building on or with @HyperFrames_ please tag our official X account when you post! we will be actively showcasing community highlights and broadcast your work 🫡

@liu8in Is there something like a guide that I can feed my agent to get to know Hyperframes and it’s capabilities better so it can make better videos?

@joestackss People are saying its really bad tho. Is it true?

Opencode x Deepseek v4 pro x High 800 million tokens = $10 The Chinese can have all my data

@geertjansloos @stripe Is that real

UPDATE: @stripe responded with a statement:

@marcelkargul Ragebait right?

Landing page design completed for a client for $10,000

@nicdunz Bro why did i get the exact same woman

IMAGES V2 IS IN CHATGPT NOW!!!!!!!!!!!!!!!!!!!!!!

@bridgemindai @matthewmillerai Are you trolling or?

Claude Opus 4.7 is so good I just bought two Max subscriptions. After vibe coding for over 12 hours yesterday I can confirm this is the best model in the world. It burns tokens fast. But the coding output is unmatched. Two $200/month Max plans so I never hit a rate limit again.

@sumi404_ai Does discount code expire today ?

Higgsfield is lying again, lol so they made a price comparison and conveniently left out the cheaper alternatives let me fix that for you Mitte is 4x cheaper. even *without* discount code x.com/VadimStrizheus…

@byteHumi So is there any explanation of the recent rate limits issues?

lmao claude pricing is fully hard coded the pricing in modelCost.ts they also have a fast-mode called "penguin mode" which is 6x the pricing of Opus 4.6

@thekitze Can anyone now explain the rate limits ?

what's your honest opinion about the claude code source quality 💀

@claudeai Why does Claude code dashboard say I am on Claude pro when I am on Max ? Therefore it says Auto mode is not available on my plan. How can I fix this ?

Auto mode for Claude Code is now available on the Enterprise plan and for API users. To try it out, update your install and run claude --enable-auto-mode.

@gkisokay There is a migration method from OpenClaw to Hermes but is there migration from Hermes to OpenClaw if I don’t like it ?

The founder of Hermes just confirmed something I missed. 'hermes skills browse' pulls directly from ClawHub and 7 other major skills hubs. That's every OpenClaw skill readily available for Hermes. Which means Hermes can do nearly anything OpenClaw can do, but with persistent memory. This won't stop people from locking themselves into OpenClaw as their first open-source agent framework, but Hermes will be there when they get frustrated enough to look for another option.

@boringmarketer What are your best use cases for it

hermes feels fundamentally better than every other agent harness I've tested it manages its own memory and it actually works it proactively writes what it learns about you, searches your full conversation history, and compresses context intelligently when sessions get long excellent so far with dev tasks, no errors on Cron jobs, keeps me in the loop, great response formatting every session it truly feels it knows you better than the last. what I was hoping for from openclaw

@bridgemindai Bro how do you always find what to code

Been running Codex with GPT 5.4 High all morning. 87% of my 5 hour limit still left. On Claude Code I'd be at 0% by now. OpenAI gives you limits you can actually work with. I've been shipping all day without a single rate limit or 529 error. This is what $200/month gets you on Codex.

@sarfraj_ab75685 SKILL

@oliverhenry So you didn’t like Codex ?

Larry is back on Claude Max plan! Here is what worked: When generating a key with: claude setup-token Both my terminal window I generated the key in and the openclaw SSH window were causing the key to split on two lines. There were no indications in my config files that this had caused errors, no added characters or spaces. (I remember this being in the patch notes at one point, because it used to add a hyphen) Stretching both windows to max width and trying again worked. Sharing incase this helps anyone else. I will look through the openclaw git repo later to see if I can help @steipete with this.

@TheMattBerman @openclaw @vishalojha_me @Meta ADS

I run my meta ads with @openclaw for $0/month 😱 here's the system that runs autonomously: step 1: daily health check → social-cli (major shoutout to @vishalojha_me) wraps @Meta's marketing API (token refresh, pagination, rate limits all handled) → am I on track? what's running? who's winning? who's bleeding? any fatigue? → the same 5 questions I asked Ads Manager every morning for 20 years step 2: catch dying ads before CPA spikes → @OpenClaw pulls daily frequency by ad → frequency > 3.5 = audience is cooked, CTR is about to drop → this one signal saves more money than any dashboard step 3: auto-pause bleeders + shift budget to winners → CPA > 2.5x target for 48hrs? auto-pause. no hesitation. → ranks every campaign by efficiency. recommends shifting spend. → last fri it paused an $87 CPA campaign at 3am and scaled my best performer 30% step 4: write new ad copy from your winners → agent analyzes what's working (hooks, angles, CTAs) → generates variations based on the patterns in YOUR top performers → copy modeled on what already converts in your account. step 5: upload ads directly to your account → new creative + copy → live in @Meta Ads Manager → no more downloading, formatting, clicking through the upload flow → agent handles the entire publish cycle step 6: content concepts + morning brief → spots patterns across winners and suggests what to test next → delivers everything to Telegram, Slack, wherever you want it → 90 seconds to read. reply "approved." done. input: your ad account + your target CPA output: an AI that monitors, kills, scales, writes, AND uploads your ads dozens of hours in ad manager → 1 text message I packaged the entire system as the Meta Ads Kit. 5 @OpenClaw skills: - meta-ads (daily checks + auto-pause) - ad-creative-monitor (fatigue detection) - budget-optimizer (efficiency scoring + shift recs) - ad-copy-generator (writes variations from your winners) - ad-upload (publishes creative directly to your account) giving it away free. comment ADS + like + follow (must follow so i can DM)