Michael

@bcherny @sickdotdev But is that really how you want people to use Claude? I came from enjoying using your model to spending most of my time trying to figure out how I hit my 5h rate limit so fast and switching to other AI providers. Makes me sad.

@sickdotdev 👋 was this using Claude Code? If you wouldn’t mind running /usage and pasting the full output here, I’d be happy to help debug. We’re also actively working on making it easier to self-serve to see what exactly is using up your limits.

Opus 4.7 sure was fun for about 15 minutes

@itsolelehmann Livesync, couchdb on my homeserver (where Hermes is running too) and my devices sync my vault via couchdb. Hermes writes and reads in couch db directly

are you using obisidian with your hermes? if yes, what's your setup?

@itsolelehmann Im interested in the WhatsApp family setup - any best practices there? And why do you use discord AND telegram?

HERMES AGENT FOR DUMMIES Everyone on X keeps talking about Hermes Agent and I finally get why: Once you have an AI that's always-on, remembers everything, and you can just text from your phone, you're never going back to a regular AI chat window. That's Hermes. You text it like an executive assistant and it just handles things. Think of it like an affordable OpenClaw that actually works and is reliable. I was using OpenClaw earlier this year, but it kept breaking and the costs were adding up, so I quit personal agents for a while. Then I set up Hermes and it's what I wanted OpenClaw to be from the start. Here's how it works: > You can talk to it on 19+ messaging platforms (I use Telegram and Discord) > You give it a personality file called SOUL .md so it behaves how you want. > You give access to your email, calendar, full browser access, and whatever other tools you use through integrations. > And you plug in whatever models you want as the brain. I use GPT 5.5 for heavy thinking and DeepSeek for lighter tasks so I'm not burning tokens on every little request (under $20/month in token spend). And I run mine on a Hetzner server for about $5/mo, which enables Hermes to be always-on and persistent. So you can schedule tasks that run autonomously, even while you sleep and even while your devices are off. For example, I have one that scans my email for customer support tickets every morning, matches customer to stripe data, sends out missing links, checks refunds etc. Stuff that used to take me HOURS. And the part that actually separates it from OpenClaw and everything else: Hermes writes its own skills from experience. Every time it completes a task, it saves what worked and turns it into a reusable skill it can run again without you explaining anything. So it literally gets smarter and better over time for your specific workflows. Here's what other people are doing with it: > inbox zero and calendar management from Telegram on their phone > overnight coding that debugs itself while they sleep > a family WhatsApp bot where 5 people share one agent to get stuff done > daily briefings texted every day at 8am > smart home control through Home Assistant > etc Once you try texting an AI that already knows your whole setup and just does things when you ask, opening a chat window and starting from scratch every time feels broken. This is the first AI agent that feels like a legit Chief of Staff.

@ClaudeDevs Thank you!

Usage limits are up, effective today we're: 1) Doubling Claude Code's 5-hour limits for Pro, Max, Team and seat-based Enterprise plans 2) Removing peak hours limit reduction on Claude Code for Pro and Max plans 3) Substantially raising our API rate limits for Opus models

@Shpigford The 100$ sub? And what messenger do you use?

@Mike_alive locally on a mac mini and i use my codex sub.

sigh. my wife is very happy with hermes (with gpt 5.5, no less). i don't even know what i believe anymore. what even is reality. are we living in a simulation. the game has changed. rt + follow me + subscribe to watch my entire existence fade in to oblivion.

@mr_r0b0t @NousResearch @Teknium That’s exactly what I did but couldn’t get it to work 😕

@Mike_alive @NousResearch @Teknium I just used the API key I got direct from the Deepseek website and set it using the native model configuration!

Here's what 96 concurrent @NousResearch Hermes Agents (using 382,745,618 tokens over 171,136 API calls to deepseek-v4-pro) can generate for you in less than 3 days. From your M4 Macbook Air 24GB, on hotel wifi! 81% cache hit rate in case you're wondering!

@AlexFinn Is there a free tier to it?

OpenClaw + the X API is a match made in heaven It's an incredible way to stay on top of what's trending in the world, plus even make better content and go viral In this video I show you how to use OpenClaw to connect to the X API and 2 use cases that will blow your mind:

@gregisenberg Haven’t watched the video yet to be fair (will do though), but does it work with gpt plus (OAuth)?

how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of it like open claw but with built-in memory, 40+ tools out of the box, and 90% cheaper token costs. you install it with one command. 2. the 3 problems with open claw that hermes solves: no memory (you keep repeating yourself), constant gateway restarts, and zero visibility into what you're spending on tokens. 3. hermes remembers everything. every completed task gets saved to memory. it searches through past logs to find solutions. over time it literally gets smarter at your specific workflows. 4. connect it to open router. you see exact costs per model per task. free models rotate weekly. one founder went from $130 every five days on open claw to $10 on hermes. same output. 5. it comes preloaded with skills. apple notes, imessage, find my, browser, web search, image generation, cron jobs. no hunting for plugins. 6. connect it to obsidian so it reads your entire vault. connect it to gstack for your dev environment. create custom skills for your specific workflows. 7. the biggest money saver: have it write code once for recurring tasks. then it runs without burning tokens every time. stop paying an LLM to do the same scrape or report daily. 8. run it on android via telegram. name your agents. talk to them like coworkers. in this episode imran shows you how to set this up. 9. you can run it bare metal, in docker, or serverless on modal. pick your risk level. i begged @imranye to come on @startupideaspod and walk through the full installation live. he made it impossibly clear. if you've heard of Hermes Agent and want the clearest explanation of how to get set up like a pro let me know what you want me to cover on the next ep this is the best personal agent setup video on the internet right now. watch

@jasondoesstuff Im gonna try this! But it’s in Claude code right? And you run code in the cloud, not locally I presume?

PROMPT // Build me a daily "Morning Edition" magazine. Every morning, fetch the Hacker News front page and curate the top 10 stories that fit MY taste — skip [TYPE THINGS YOU DON'T WANT]; lean into AI tools, creative software, dev tools, privacy, weird science, and anything actionable. Flag any story that directly applies to me. Render it as a single self-contained HTML file styled like an editorial magazine: huge display typography (Fraunces + Inter via Google Fonts), and give each of the 10 stories its own distinct spread — different background colors, layout, and numeral treatment (hero, dark/midnight, rose-alert-stamp, terminal, academic drop-cap, big-stat finish, etc.). No small fonts anywhere. Save it to a magazines/ folder, named YYYY-MM-DD.html. Schedule this to run daily at 7am. (Optional) Publish each issue to GitHub Pages so I get a real shareable URL, and Telegram-bot me the link every morning when it's ready.

I can't stop making Claude "Magazines." 😍😍 Super easy to create: 1. Told Claude to summarize Hacker News 2. Tell me if any stories apply to me/require action 3. Make it recurring each morning Now I have this beautiful personalized version of Hacker News! (Prompt below)

@jordymaui I used to build my OpenClaw, swapped to codex because of $ reasons and stopped using it out of frustration. Fully on Claude now and happier every day

are you using OpenClaw or Claude? or dare i mention it... Hermes. curious, so let me know⬇️

@petergyang Has anyone figured out a solution? Openclaw is useless for me at this point. It can’t execute the simplest jobs 🥲

I know OpenClaw isn't part of OpenAI but this feels like a mini-crisis for OpenAI if the GPT integration doesn't improve soon. The bar is GPT needs to be just as good if not better for OpenClaw as Opus.

@steipete @openclaw Can I try this fix now or does it come with the next update?

Two experiments in the next @openclaw to address some "GPT is lazy" issues: 1) Strict mode: agents.defaults.embeddedPi.executionContract = "strict-agentic" This tells GPT-5.x to keep working: read more code, call tools, make changes, or return a real blocker instead of stopping at “here’s the plan.” docs.openclaw.ai/providers/open…

@coreyganim I strongly disagree that Claude code is just for coders. Claude code can actually organzie your folders (just did it yesterday). For me it’s the better sparring partner + executor than Claude chat. How do you come to that conclusion?

@melvynx I thought it was just me. Stopped using claw altogether, too frustrating and the ROI of my time spent debugging is close to 0

Day 3 with OpenClaw: In all my tests, GPT 5.4 is consistently the worst model for agentic tasks. Lazy, stupid, never follows anything, feels like you are a baby sitter. I don't know how OpenAI manages to make such a shitty model but this feels terrible. I miss Opus.

@itsolelehmann Would you mind sharing your setup in Claude? Still haven’t touched cowork effectively and would be very interested

@ryancarson @openclaw That’s what I thought.

The cost to run a truly useful Chief of Staff @openclaw on Opus 4.6 is $100-200 per day on the API.

@philkellr I feel you! I spend more time bugfixing than actual using Claw. I experimented with free models and that was a disaster. Claude was best, but api costs were so high that I didn’t see the value over a regular sub. Using codex now to test, Claude code runs on the same vps to bugfix

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 🤷

@steipete @NoahEpstein_ Im an enthusiast but have no IT background. That means I can use OpenClaw with my Claude Pro sub? I thought that’s impossible / gets banned? I’d love Claude on my claw 🥹

@NoahEpstein_ models auth login --provider anthropic --method cli --set-default

openclaw without opus is actually one of the saddest things that's happened this year (ignore the war) i can't lie. i've been loving openclaw way too much to just take this on the chin and move on my actual plan is to try figure out how to get openclaw talking to claude code infrastructure instead (because i can't lie claude code is still actually unbelievable and i'm not giving that up either) might work. might be completely stupid. we'll see but i'm curious what people are doing right now because there are a few options and none of them are clean going local is the move long term but the thing is - you've ordered your mac studio, great, it's not arriving for another week or two. so what do you actually do in the gap? i've seen @AlexFinn preaching about local AI basically every single day and i respect it but i can also just tell that his openclaw is writing half his posts at this point so i dunno how much i trust the sauce what's everyone's actual plan? switching models? building workarounds? just eating the API cost? because i'm not ready to let this go and i refuse to believe i'm the only one