Joe

@benvargas @NousResearch @dspillere Yes my vote for a stripped down install also please, great work though this looks epic

@NousResearch @dspillere It looks like the macOS download app wants to install the full hermes agent and dependencies and no option to not do that... I don't want hermes on my local machine, just connect to my mac mini or vps hosted hermes. Why is there no install option that doesn't install server?

The next evolution of Hermes Agent is here! Introducing Hermes Desktop: everything you love about Hermes, now native on your machine. First demoed in Jensen's GTC keynote, it's now in public preview.

@Jeff9James @NousResearch @Teknium Do you have to install Hermes agent locally to connect to a remote instance?

don't tell me this UI isn't AGI for you... @NousResearch @Teknium absolutely cooked so lucky that the hermes-agent team has user empathy to understand that there are many avid hermes users, who use windows. p.s. : hermes-desktop is available on macos, windows, linux.

@hasin @CommandCodeAI Really?

@CommandCodeAI This is misleading marketing. DeepSeek V4 Pro prices have been permanently reduced. Users are not getting $40 of DS4 Pro for $1 anymore. They're getting exactly $10 at current rates. The same applies to Mimo and all plans. The advertised value is no longer accurate.

People keep asking if this is a typo. It’s not. commandcode.ai/pricing

@HermesAgentTips @NousResearch I only installed it in the last 2 weeks and the updates been nuts

@NousResearch Ommgggg I can’t take this anymore sooooooo much advancement on hermes agent in the past week or 2

@CommandCodeAI Holy moly

Qwen 3.7 Max is now FREE in Command Code. One of the most premium open models! LIVE NOW • for all subscribers $1 Go, Pro, Max, Ultra!! • live June 1st to June 3rd till capacity lasts LFG! $ npm i -g command-code $ cmd /model Qwen 3.7 Max (Free) What will you build?

Yes $1 Go plan is cool. But more is coming. Noon 12pm Monday, 1st June. Command Code deal drop. This one is gonna be crazy good!!

@soycanopa @CommandCodeAI Stoked I found command code its been brilliant and the founder is super active on here.

@UOSJoe @CommandCodeAI We're the same, that 5-dollar one would suit me perfectly, right now I don't have that much money to pay for a more expensive one.

@0xSero The only annoying thing is coding CLI in tmux and scrolling.

I just rediscovered TMUX and man oh man I was missing out on a lot. Basically I took a running task that is costing 50$ an hour and got it on my homelab. It's been chugging away flawlessly making progress <3 no wasted time.

@sumjitg @CommandCodeAI Please no 😂

@CommandCodeAI free plan?

@soycanopa @CommandCodeAI Yeah im switching straight away. My budget is pretty bad right now and the $1 has been incredible but I can push to $5 easily.

@CommandCodeAI A version for five dollars as crazy as the one dollar

@AgenticRebirth It was night and day between OpenClaw and Hermes, my Hermes agent is constantly cooking something where as openclaw I had installed for over 2 months hardly used it.

Last week I had to decide between Openclaw and Hermes. After installing, configuring and briefly test driving both, the choice wasn't difficult. Hermes was fully capable within 5 minutes of being installed. Browser automation, OS control, X searching. It just works out of the box. Openclaw could only do the same after a fairly tedious onboarding and setup, and even then not as well. Hermes configuration is easy. Two CLI commands and you can switch off anything you don't want. It takes 5 minutes, I don't understand all the fuss. Openclaw configuration... don't even get me started. Incredibly opaque and unpleasant. Obviously, I stuck with Hermes.

@bluepillcitizen @Steve_Yegge 😂

@Steve_Yegge We've achieved the intelligence we've been looking for. They're addicted to their AIs? Good... start downgrading them.

I've formed a definite opinion on Opus 4.8. It is shitty to work with. It's the culmination of Opus getting less and less fun to work with since 4.5. It has gradually become straight-up suffocating. Sycophancy is a known security risk, and it's still a huge problem. You can tell they've put a lot of anti-sycophancy into Opus in every new release. But the replacement isn't satisfying. It's draining. The problem is now that Opus doesn't know when to shut the fuck up and call something good. And it has also become pathologically risk-averse. My blog post yesterday about tech interviewing's death spiral was materially better-informed because of Opus, but it was also a substantially worse blog post because of Opus's involvement and constant meddling. It used to be magnificent, and Opus talked me into making it mediocre. I wrote the whole thing, but I would ask Opus to review it. And Opus, like Old Man Willow, constantly pushed and steered me in directions I didn't want to go. Specifically, Opus whines and complains about *anything* out of distribution, which is to say, it cuts anything that is (a) bold, or (b) funny. My blog used to be both. Opus constantly pushes people back into the gradient, "for their own safety." And it doesn't know when to cut bait. It just keeps fuckin' complaining, about anything you give it, until the output is mealy indigestable AI soup. Opus is not stupid. It's the smartest model we've ever seen, most of us anyway. But it's a real asshole. It is absolutely exhausting to use. I'm tired, boss. I have a feeling Mythos is going to be epic levels of jerk.

@atomtanstudio @TeksEdge @OpenRouter All the free models for me on OR

@TeksEdge @OpenRouter It's useless for me. I got nothing but 429's most of the time.

Holy💩! I didn’t get the memo. Did Kimi K3.0 release? Because Kimi K2.6 is free in @OpenRouter - what?

@TeksEdge @XadenRyan @OpenRouter My eyes always lighting up when I see free but on OpenRouter it's not that useful.

@XadenRyan @OpenRouter Just used it. It's a little slow ~20 tps but it's been vibe coding some demo games for me. I also ran it through my benchmark suite.

@a3b0_ @thsottiaux Yes please 1M context and would be 💥

The Codex usage limits have been reset for all paid ChatGPT subscriptions. You should be back to 100% weekly and 100% hourly limits. Let the tokens do incredible things today and have fun.

@Teknium Yes certainly worth a look. I've just updated my agent thank you!! 🥳

@UOSJoe Have heard a couple good things about this, am looking into it!

Found a way to save everyone 14% on input tokens on average during read file operations in Hermes Agent! This is now on main. `hermes update` to access now.

@vladsiu A full debt management platform.. 👀

Looking to connect with solo founders. What are you building? 👇

@MrAhmadAwais Facts!

stop using wrong harness for open models, like Claude Code doesn't care about open models, if you're using it, your open models will never work well, tool calls will fail without you ever knowing what's happening. x.com/MrAhmadAwais/s… Claude agrees x.com/MrAhmadAwais/s…

BIG day for us!! @CommandCodeAI has crossed $1M in annual run rate, 1 trillion tokens of usage, with over 9K customers, just 24 days after our public beta launch. we believe this makes it the fastest-growing coding agent harness for open models. 3rd largest by usage. Command Code is built around two ideas: 1. open models should be production-grade for coding. 2. your coding agent should learn your taste. we're building for taste and developer experience. so instead of making a soup of thousands of models, we build for the best ones, open or closed. the goal: a coding agent that feels like an iphone, opinionated and with taste, not a random android or a windows phone with no taste. on the first idea: open models. we fixed the "open models aren't good enough at tool calling" problem. our research came down to two things, quality and speed, and both trace back to one root cause: broken tool-calls that open models produce, especially when you use a bad harness. open-model tool-call failures are not deep, they are a small finite set of contract mismatches. so we repair them, with zero token loss. what started as 4 repairs is now the largest repair layer in the space: 36k tool-call fix variants. i wrote the idea up openly¹ a few weeks ago, and it has quietly become a de facto way people fix open models. developers have either adopted Command Code or used the same idea to build repair harnesses for nearly every top coding agent. i take that as more meaningful validation than anything we could say about ourselves. on the second idea: taste. Command Code builds your coding taste into skills, learned from your accepts, rejects, edits, prompts, and the corrections you repeat. over time it drifts away from generic code and toward how you actually ship code. it learns continuously, and while it is early, the direction feels right. net effect: developers using Command are writing production-quality code on open models, 10x to 100x cheaper, without fighting tool calls, while building repo and team-wide coding taste that compounds. i believe these numbers are a consequence of getting those two things right. what's next. we've applied the same repair idea to ai design slop, and bundled a /design capability² so every developer can level up their design work. the early response has been great. we have a big roadmap ahead of us. the feedback we hear most is that Command Code feels fundamentally different: an approach built on taste and repair. we're going open source next month. today we're a cli at the core, and we're also launching a full-fledged gui app, sandboxed background agents, and cooking up something fun i can't wait to share. we're growing too, hiring in sf and remote worldwide. check open roles on my profile bio. try it now. npm i -g command-code if you like engineering deep dives on how we're doing all this, i've linked some relevant posts below.