Justin

I'm Founder #46 of 100 at Shipper Club — a private club for modern builders with taste. shipper.club @orcdev thank you for building this. I’ll have to grow into it, but I’m investing. 🦞

@AlexFinn Outstanding

Pretty incredible You have to try the new '/goal' feature in Codex It worked for over an hour and built me an entire complex extraction shooter video game You give it a goal, then it works endlessly until the goal is complete. It's like a Ralph loop. Can run for days If you enable the image gen skill before you run the goal, it will even generate ALL the assets for your game autonomously. I didn't manually create ANY of the assets you see in the video Recommendations: enable the image gen skill, put on skip all permissions, and give the prompt as much detail as you can. It will accomplish ALL of it This has to be the sickest way to build games/ long running app tasks ever

@sudoingX @Teknium I gave up last weekend and decided to go all in today and let your platform lead the way. Made all the difference. 🪽

if you are running local ai or thinking to start, if i could give you one single piece of advice it is this: choose your agentic harness carefully. it matters more than the model. i have lost count of how many people have dm'd me saying their local model is "dumb" or "broken" or "not as good as the cloud one." then they switch from openclaw or some other bloated framework to hermes agent and the same model suddenly works. just clean tool calls and the agent doing the thing it was supposed to do. hermes agent is the best general purpose agent i have used in 2026. drives my single 3090 with qwen 3.6 27b dense q4, drives my dgx spark with nemotron omni q8, and the same harness handles coding, research, video editing, automation, anything you point it at. packed with skills out of the box (browser tools, code, github, jupyter, multimodal, more than i have used yet), full tool calling that holds across long sessions, persistent memory, sub agents. if you tried local ai once or twice and gave up because it felt half baked, the issue might not have been the model. it might have been the harness wrapping it. swap the harness, run the same model again, and watch what changes. hermes agent is the one i recommend to everyone running local. and especially to anyone who almost gave up on it.

@sama We’re happy for you!

never thought id be watching F1 via the kids broadcast cannot imagine being happier

@sama With @NousResearch it’s a delight.

5.5 xhigh in fast mode is really good i think i got psyoped by twitter on medium for a bit

@quxiaoyin Spent the day today building my fleet at home, your model recs help so much, especially balancing the cost, thanks!

who is starting their own one person company? comment your company below. Let's see how many unicorns we got from this list. 2026 is the year for one person unicorns!

@hthieblot Building my fleet today and prepping for an elderly services agent system to help people like my parents navigate the paperwork associated with aging. Would love a bump.

Just gave $175K to a founder who cold DM’d. He had bellow 200 followers. Completely unknown to me Who is next? Hit me up.

@everestchris6 MENU

this OpenClaw bot finds restaurants with ugly menus, rebuilds them as live web menus, and mails the owner a postcard...on autopilot. here's how agencies can land recurring contracts with this system: - scrapes every restaurant in a city in real time - filters by review count + rating + last menu update + photo quality - pulls the real menu items from the official site, PDF, or Google reviews - samples the brand palette from the restaurant's own visual identity - renders a 9:16 brand-matched menu, hosted live at a QR-accessible URL - writes a personalized postcard referencing a real reviewer and a real dish - mails it to the registered office addressed to the owner by first name every step from discovery to brand-matching to outreach is automated. reply "MENU" + RT and i'll send you a free guide so you can build this too

@DeeAutonomous @autonomous_labs Now that Minis are $800, I’ll keep my silly swarm until I hit M5 Studio land.

@StoneAutomation @autonomous_labs LOL You have the whole swarm! I’ll DM you in a few days. I think we have a pretty cool product that would make all of your machines work together! I’ll send you the beta access!

1/ Building your own Personal AI Computer ChatGPT remembers your financial information. Claude knows your next big ideas. Gemini sees your inbox. You're not using AI. You're exposing yourself to corporations. Personal AI Computers are freedom. Here's how to build one: 🧵

My home lab: Mac Mini M4 16GB/256GB as the main automation/OpenClaw machine; 2019 iMac “headquarters” as dashboard/control station, 2018 MacBook Pro 8GB, Kamrui Ubuntu 16GB mini PC as nursery/experiments; Lenovo ThinkCentre M75q-1 32GB for Hermes; HP Pavilion w/ GTX 1650 32GB for heavier local model tests; HP EliteBook 16GB Ryzen as extra node; two Pi Zero for a desktop assistant concept for YouTube content. 🤓

@StoneAutomation @autonomous_labs super cool. can you share the specs of those machines? we may be able to help you configure them in a way to utilize all the compute resources of these units.

It’s happening. 3 months ago I predicted in the next 2 years all hardware costs would triple Base Mac Mini’s would go from $600 to $1,800 Top of the line Mac Studios would go from $10,000 to $30,000 Everyone called me insane. They said it was engagement farming. Yet it’s happening faster than I predicted. I urged you to buy your own compute. I said intelligence will not get cheaper anytime soon. Only more expensive (100% true) Now it’s all playing out in real time It all makes too much sense. As openclaw and personal agents get more popular and powerful, people will need more compute, all while hardware is facing shortages Even the top labs like Anthropic don’t have enough compute to serve models from months ago. Limits going down every week Own your own compute. Host your models. Localize your agents. Do it before having powerful intelligence is reserved only for the elite.

@NousResearch @Shopify Amazing

Shopify is the all-in-one commerce platform powering millions of businesses worldwide Thank you to the @Shopify team for building their own official Hermes Agent skill enabling your agent to manage products, orders, inventory, and fulfillments from any channel.

@simonsquibb To build an agent based program to assist low income elderly people, like my parents, including a veteran, manage the massive amount of paperwork and correspondence necessary to manage their lives on a fixed income.

Let me fund a dream this weekend! What’s your dream?

@sama @Makuh90 Boston wine sales professional here wants to know! Cheers! 🍷

@Makuh90 i have not been drinking YET but ollie got me a super nice bottle of wine to celebrate 5.5 so maybe there will be some tweets tonight...

He's not been drinking. But he's on the money.

@AlexFinn @Teknium How many agents out there are also called Ralph because of you, I wonder.

@Teknium ok this is awesome

I have to go out of town for a funeral thru the weekend but I am leaving everyone with one new cool feature inspired by ralph loops and Codex's upcoming /goal feature. If you use /goal , it will start a loop with a supervisor model determining whether the task completed at the end of an agent loop - if it hasn't it will force it to keep going until it's done! Enjoy and have a great weekend. PR: github.com/NousResearch/h…

@NousResearch Helps that y’all aren’t a bunch of pirates and goons.

@KSimback Helps that we have an awesome community that keeps us on our toes!

I am continually amazed at how fast the @NousResearch team ships improvements to Hermes Agent A few feature or skill pops up on the timeline and 24h later it’s built into Hermes and oftentimes done better Take notes - this is how you ship!

@NousResearch @quxiaoyin I love Nous York. 🖤

@quxiaoyin Glad it’s working so well for you!

I can’t believe I stopped using Claude Code max and entirely use DeepSeek and Hermes. It’s so fast, so so fast, 3x faster for the same task. So cheap. I spent $5 last week and never need worry about being rate limited or usage hit limits very two hours. For most tasks it’s perfect enough.

@Teknium @quxiaoyin This is the way.

@quxiaoyin Welcome to Hermes Gang!

@robinebers Thank you!

🔗 download here: github.com/robinebers/ski…

my /shepherd skill is completely free btw

@DeeAutonomous @autonomous_labs Got a fleet of machines that I’m working on with a 16gb Mini as the center. Best I could do on a budget. Would love a tip or two. Really enjoy watching your product grow.

@autonomous_labs And feel free to DM me too with any questions while building your rig!

@robinebers Hahaha. Amazing Mortal Kombat match we have going here in real time.

Codex can now import from Claude Code 👀