Balaji B

@outsource_ both of course.

What do we like better for Hermes-Workspace Mobile? Light/ Dark Mode 🌙

@Teknium @autogame_17 oh man, those bots have more followers than me 🤣🤣

Now, go look in the replies who are egging this on. Ask @autogame_17 where they got this botnet here. Go check out their accounts, and see who is being disengenuous here.

I have literally never heard of this person, their project, or anything they are doing in my life. Today is the first time I've ever heard of or seen this project at all. To claim without evidence that I took their work is a lie. Their article comparing us is completely braindead, like this one?? How does anyone say "OMG THIS IS MINE" to this comparison? lmao This will be my only post on this completely false claim against me.

@NousResearch I can not close my eyes, you guys will release an update.

Close your eyes and let the mind expand. Let no fear of death or darkness arrest its course. Allow the mind to merge with Mind. Let it flow out upon the great curve of consciousness. Let it soar on the wings of the great bird of duration, up to the very Circle of Eternity.

@brayaON20 @Teknium hey, do you want to add a skill? Also do you have ports - like input and output ports that will be useful for engineering diagrams.

@Teknium @Teknium this one is similar but more general because it can generate other styles github.com/yizhiyanhua-ai… I've been using it on CC and it produces very good diagrams. At first, I saw your screenshot and thought it was the one you had added, but it isn't. Could you check it?

This skill is now built in to Hermes! Use /architecture-diagram <prompt> after updating hermes, and you're good to go! Thanks to the author of the skill making it MIT we were able to port it over directly into Hermes Agent as a built in skill!

@RyanLeeMiniMax @TheZachMueller @MiniMax_AI If I am right, you can make money with your self hosted MiniMax as a LLM model. You can make money with your app - that app should not use MiniMax as an AI provider without consent from MiniMax.

@TheZachMueller @MiniMax_AI Sure you can. “software on your own servers for coding” meaning that u could coding to do anything include make money.

@TheAhmadOsman @DegenApeDev For a second I thought Gemma 4 is going to be next level (if G3 already beats Q3.5), but good to know Gemma 4 is better than Qwen3.5. Have you tried with any of the Agent Harnesses (openclaw/Hermes) - better prompting probably better handled by it?

@DegenApeDev Man, I meant Gemma 4 Typo

I changed my mind Gemma 3 31B is better and more capable than Qwen 3.5 27B Requires better prompting but it’s more capable, intelligent, and token efficient

@Teknium but instead of delegating task, is there a way I can directly chat with them - like (at)mention for example -

Nice quick tutorial on multi agent profiles with Hermes!

@farzyness Neat analysis with usage from a big account @Teknium fyi

My super early impressions of OpenClaw vs Hermes Agent: Hermes seems WAY more reliable at executing actual tasks - even on GPT 5.4. It also feels way more stable. And I absolute love that it shows which tools it's calling as it's executing a task. I also really like that the personality with GPT 5.4 is FAR better on Hermes as well - after a bit of tweaking. With OpenClaw, I was finding it impossible to get GPT 5.4 to stop talking like a sycophantic idiot. On Hermes, I can get it to be direct & push back with little effort. I'm also finding that GPT 5.4 is FAR more reliable on Hermes vs OpenClaw (thanks @heyitsyashu for the tip). It really does feel like Opus 4.6 level performance on OpenClaw, but with even better execution on long-running tasks. Not sure what the Hermes team has done (I'm not technical at all), but it's obvious that the way they've constructed the back-end is far easier for LLMs to figure out what they should be doing. Because of OpenAI oauth being allowed, Hermes + GPT 5.4 os now EASILY the best intelligence per $ 'AI brain' for Agents. I think the @openclaw team needs to deeply study @NousResearch and what they've done because it can likely benefit MASSIVELY. Gut tells me OpenClaw has become FAR too bloated and FAR too 'jack of all trades, master of none'. When it comes to actual execution of tasks, Hermes feels WAY better equipped, and TBH I wouldn't be surprised AT ALL if it becomes adopted by actual businesses/operators at a far greater rate than OpenClaw. I'm also starting to really worry that the days of OAUTH with 3rd party tools is coming to a screeching halt very soon. I don't think OpenAI is going to allow their oauth tokens to be used on an AI agent competitor when they've invested a lot of money on OpenClaw's creator. What I think is gonna end up happening is OpenAI will stop allowing oauth use for 3rd party apps all together (including OpenClaw) and they'll likely release their own OpenClaw v2 to try and compete against Hermes/Computer/CC. Hope I'm wrong, but these tools are far too powerful to be "allowed" to be open source + heavily subsidized tokens, especially as the public outcry re: AI's cost to electricity continues intensifying. But this will give way for ultra-capable, ultra-efficient opensource models that will give 90%+ Opus 4.6/GPT 5.4 performance for 1/10th of the cost that are SPECIALIZED for agentic harnesses like OpenClaw/Hermes. It's starting to get REALLY interesting, folks.

@vee_dorrian @HarshithLucky3 @antigravity Their Gemini 3.1 Pro High is nothing but useless or sometimes even worse messes up the entire codebase if we are vibe coding.

@Balabo111 @HarshithLucky3 @antigravity Same. I am an Ultra user - Antigravity was amazing the first days, you could basically use 4.6 all day. Now they’re clearly trying to push their own models, which are much worse. Moved to Codex and with a few tricks use top models for free, and it’s much better than Gemini

am i dreaming? today i used Gemini 3.1 Pro (high) for 2 hours straight in Antigravity Why didn't it hit the limit? forget about hitting it, it didn't even consume ~40% of the usage Is it not showing the usage correctly or did they really increased the rate limits can anyone confirm?

@garrytan Why don't every traditional corporate follow this?

New item in my SOUL md tonight

@NousResearch @Su What does that even mean?

@Su It’s your lucky week :)

Hermes from @NousResearch just needs a dashboard and it will win against openclaw easily. Just everything about it is better

@AnjneyMidha 🤣🤣

Google and TPUs in a nutshell

My prompt to install GBrain in Hermes. After several tool calls, all done! @garrytan @NousResearch ------- Hi will you be able to install Gbrain by yourself? github.com/garrytan/gbrain

@outsource_ Wow! This is an awesome project. I hosted the app locally in my Mac, and my Hermes VPS @NousResearch stays somewhere in Italy which uses @MiniMax_AI token plan, but the response feels like 10x faster than local. My toy for this weekend! Thank you Eric!

@NousResearch Completely disagree with this post. Please delete it.

Have a great weekend everyone, don't forget to take a break from Hermes and touch some grass! We know it can be addictive

@garrytan Integrating GBrain in Hermes 3... 2... 1...

Integrating into GBrain in 3... 2... 1...

@supergera13 @MiniMax_AI @Teknium just ask your Hermes Agent to do it. if you already have MiniMax token key, it just works.

@MiniMax_AI @Teknium plis wen implementation in Hermes 🫂🥹

Introducing MMX-CLI — our first piece of infrastructure built not for humans, but for Agents. Your Agent can read, think, and write. But ask it to sing, paint, or show you a world it's never seen — and it falls silent. Not because it doesn't understand, but because it has no mouth, no hands, no camera. Today, that changes. MMX-CLI gives every Agent seven new senses — image, video, voice, music, vision, search, conversation — powered by MiniMax's full-modal stack, today's SOTA across mainstream omni-modal models. One command: mmxAgent-native I/O. Zero MCP glue. Runs on your existing Token Plan. Two lines to give your Agent a voice: npx skills add MiniMax-AI/cli -y -g npm install -g mmx-cli Then tell it: "you have mmx commands available." It'll learn the rest. Github → github.com/MiniMax-AI/cli Token Plan: platform.minimax.io/subscribe/toke…

@MiniMax_AI WTH - I just had to copy your post to my Hermes Agent. @Teknium @NousResearch - running in my fully sandboxed docker.

@Teknium Do we have One drive CLI? That will be an enterprise killer feature.

We now use the new Google Workspace CLI as our built in Google Workspace skill, much more comprehensive capabilities for all!