iroko

/status

@petergyang Last head to head round was openclaw vs Hermes, via Sonnet, gpt 5.4, nemotron, Kimi 2.5 and hunter alpha (now mimo). OpenClaw took 5x more time on average and 2x the tokens vs Hermes. The third time I did the test with a different model, Hermes created the skill and the memory

@petergyang Same anecdote I mentioned before. I have kind of a personal benchmark based on Google Ads Campaigns setup. When jumping (early March) into the "claws" I tested openclaw, nano, pico, null and Hermes. For different reasons I stayed with nano, open and Hermes.

Ok I’ll bite - wtf is Hermes agent? Is that like the luxury bag version of OpenClaw

@MiniMax_AI @Scobleizer @Teknium Hermes 0.9 I hope.

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…

@1littlecoder Sandbox needs some tweaking. Will DM via Slack (Leads.io)

@iroko live now - fal.ai/models/bytedan…

👀👀👀

@Teknium @turbo_xo_ yo, left this on the AMA, in case it's interesting. Really like the OpenRouter Broadcast openrouter.ai/docs/guides/fe… And Kimi CLI Vis kimi-cli.com/en/reference/k… For Posthog LLM analytics, a broadcast like feature, combined with wired tracing would be amazing. Maybe is already in hermes

@turbo_xo_ Yes

We zooooom!

@jiayuan_jy @NousResearch amazing news. Also, can someone get @jiayuan_jy on a podcast or talk to know pick his brain?

Multica will support @NousResearch Hermes Agent this week. Soon, you'll be able to deploy an army of Hermes Agents to boost your business.

@Scobleizer @openclaw @NousResearch @theemozilla recording, please

You have heard of @openclaw competitor from @NousResearch called “Hermes.” Tomorrow at 4 pm we will get nerdy with @theemozilla. Live. I will get people up who asks questions here first. twitter.com/i/spaces/1DGle…

@chillybrosriram @Scobleizer start with the free xiaomi mimo. free for 2 weeks now.

@Scobleizer what llms or apis r u guys using on m4 16gb pls lmk i need to hop in fast

@Scobleizer Running it nonstop for 2 weeks in a NUC with 4Gb ram, i5. no issues (kimi, and now mimo)

@Teknium @theemozilla mic to @Teknium !

Happening in 15 minutes! Come meet our CTO, @theemozilla

@Teknium @theemozilla podcast to listen later?

@NousResearch @MiniMax_AI free minimax?

We’re partnering with @MiniMax_AI across product and models to make their upcoming releases the best for Hermes Agent users. MiniMax models are already some of the most-used in Hermes Agent. If you haven’t tried MiniMax M2.7 in Hermes Agent, try it today in the Nous Portal!

@izhongyuting @ryancarson well, it helps having an export from editor

@iroko @ryancarson Google Ads is a pretty good stress test for agents because the hard part usually isn’t generating assets. It’s reading messy account state: search-term drift, change history, conversion quality, structure, and what actually changed.

Getting a lot of comments about this. Those of you who’ve used it - better than openclaw?

@yeahfortommy @91amin91 @ddkydesign @NousResearch @Xiaomi perfect! mimo is on! this was hunter alpha, right?

@91amin91 @ddkydesign @iroko @NousResearch @Xiaomi go into the hermes agent and select nous portal :-)

We have partnered with @Xiaomi to bring their excellent MiMo V2 Pro model to Hermes Agent via the Nous Portal - completely free to use for the next 2 weeks! Access now on the latest version of Hermes Agent: 'hermes update'

@AJamesMcCarthy Is Nasa publishing the RAW?

Btw, I believe that’s Venus in the lower right.

At first glance this looks like a daytime photo- but it’s not. I don’t think we’ve ever seen Earth at night photographed quite like this. Historic.

@inceptioncortex @Teknium @sudoingX @dotta what I'm lookig at here? looks too cool.

> Hermes-agent deserves way more hype. > Quick to build, daily new features; can even build features that aren't there (yet). 🤖👉 Paperclip-hermes adapter with multi-agent inner communication (A2A protocol) -- your agents don't just work, they collab! @Teknium @sudoingX @dotta

@IndraVahan TTS models and voices evaluation. And a little Into The Breach clone to test LLM models in logic and thinking. @JarMustard @subsetgames please, ITB is an amazing platform for AI model testing. But can not really make a mod for comms. Then, I had to go OpenITB.

please drop your hermes agent and openclaw usecases under this tweet. i really wanna see what everyone's upto