Guido

@NousResearch Could you add a per-instance token spend breakdown to Nous Portal > Usage? We currently only see hosting costs, not token costs. Would really help us track what each AI agent is actually spending. @Teknium Thanks!!!

Two Hermes Cloud agents. Need A to instruct B remotely. No SSH, no exposed API. Only option: shared Telegram group? @NousResearch is there a native agent-to-agent path on Cloud? @Teknium Thanks!!

@ScottyBeamIO Good info. A question for the experts... How is that “worker” configured, the one that only responds to the orchestrator? I mean, is it a separate profile with specific instructions in its “soul,” without a gateway, for example...... Thanks!!

HE TESTED 5 AI MODELS WITH HERMES AGENT AFTER FABLE 5 GOT BANNED. ONE CHINESE MODEL IS DOING OPUS-LEVEL WORK FOR FREE. Here's the full breakdown: → DeepSeek V4 Flash – super fast but hallucinates too much for complex tasks. Good for small quick jobs only. → ChatGPT 5.5 – best for beginners. Pro plan gives you enormous usage. Handles Gmail, Google Drive, Stripe connectors perfectly. The issue: it identifies problems but never proactively suggests solutions. Frustrating for daily use. → Claude – still the best quality but API billing only. Subscription access removed. Not viable with Hermes Agent unless you're paying API rates. → Kimi K 2.7 – coding-heavy sub-agent tasks. Not a main driver but excellent as a worker underneath an orchestrator. → GLM 5.2 – the winner. Opus-level quality. Chinese open source model. Since switching to it, the troubleshooting headaches are gone. His current setup: GLM 5.2 as the orchestrator brain. Kimi K 2.7 as the email assistant worker underneath. He only talks to the orchestrator and it delegates everything else. Plus: the latest Hermes Agent update now supports iMessage. Bookmark this post. Full breakdown in the video below.

@TrialByFireLab @Teknium Call me crazy but I have changed all my agents to the Nous Portal subscription and the APIS and I notice a substantial improvement....

Damn @Teknium! Hermes Agent feels lightning fast! Massive improvements in speed. Super impressed, I'm used to giving my agent a command and waiting a minute or two but not anymore.

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.

@Teknium I'm in love with your infographics, please share the prompt hehehehehe

This update also comes with a very nice gateway router to help formatting and a bunch of nice systems level upgrades

Streaming tokens is now buttery smooth on @telegram with Hermes Agent.

@Teknium You could share the prompt to make this type of infographics, you use the Bayou skill, right?

Opus 4.8 is now supported in Hermes Agent ^_^

Our database and data engineering expert @yoniebans made some major improvements to the way sessions are stored and accessed. This will save something like 20-40% of the disk space used by Hermes Agent to operate, speed up session loading, and overall makes the codebase cleaner, simpler, and better architected! `hermes update` to access early or wait for the next major release :)

Introducing Hermes Agent v 0.13.0 - Multi-Agent orchestration through the Kanban system - Enforced goal completion with /goal - Big optimizations for disk usage - Much more extensibility, custom LLM Providers, custom gateway channels, and much more

@gkisokay @Teknium One thing that happens to me a lot is that when there is a task of medium-high complexity many times the agent skips consulting the official documentation of the platform itself or even that of, in my case, Hermes. It occurs to me to have an exclusive Researcher for these cases.

@Mr_Bitcoin @Teknium The idea is that each agent needs to be aware of what is going on right now, rather than acting in isolation. thanks for your interest

My Hermes agents get smarter every day, and the models are not the reason. It's one upstream research agent feeding the entire system. But don't get it twisted, raw scraping the web is not research. If the information is not structured, your other agents can't use it. Every agent in my setup reads from the research vault first. Here’s what each one actually gets: • Main makes decisions with new context • Coder gets fresh docs and changelogs before touching new code • Content agents get angles, source trails, and timing • Subconscious gets a daily snapshot of what moved • QA gets claims to cross-reference before anything ships • I get information that means something to me If your agents do not share a structured evidence base, they are not a cohesive system. This exact setup works for Hermes, OpenClaw, or any agent framework. Full guide + implementation details are in the post below 👇

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.

@Teknium My condolences, Maquina. Thank you so much!!

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…

There's so much to explore in Hermes, check out the guide:

@Teknium @NousResearch Does that include kimi k2.6?

Hermes will now by default use native vision if the main agent model supports it, and you didn't set a different vision auxiliary model! Just `hermes update` and it will take affect immediately. You can override this by setting any other model as your auxiliary vision model with `hermes model` -> Configure Auxiliary Model -> Vision If your model does not support vision, it will not work, and you will still need to set an auxiliary vision model. Enjoy! PR: github.com/NousResearch/h…

Hermes Agent tip of the day: You can backup and transfer your agent cleanly and simply. Want to move it to a new VPS that is bigger? Take it to your new Mac Mini? `hermes backup` - > creates a zip install hermes on a new machine fresh transfer the zip to that machine then run `hermes import` done :) Full docs: #hermes-backup" target="_blank" rel="nofollow noopener">hermes-agent.nousresearch.com/docs/reference…

@iAmDon_eth @Teknium I think it’s even counterproductive, or at least it was my experience with openclaw, but I already migrated to Hermes almost a month ago and I haven’t moved from Kimi k2.5-6.

@Teknium Why are some people so obsessed with jumping between models 😂 find 1 or 2 that works great and keep pushing

Hermes will no longer have to be updated to receive model list curation updates for several providers, including Nous Portal and OpenRouter, more to come soon. It now will draw from a hosted JSON to retreive the lists dynamically, meaning you don't have to spam updates every model release! PR: github.com/NousResearch/h…

@mr_r0b0t @PaulGugAI @NousResearch @Teknium Interesting, what use cases are you giving to this fal.ai thing?

@PaulGugAI @NousResearch @Teknium I'll probably maintain the MM sub, it's probably the only one I'll keep as it still has no weekly rate limits! My credits go almost exclusively to tooling, especially fal.ai!

Upgraded my Nous Portal sub, it's proving to be very much worth the $ The new $20 tier is incredibly generous given the insane amount of utility those credits are getting you. Other plans get you inference. Nous plans get you inference and tooling. There is no direct comparison!

K2.6 + hermes = 4 hr session setting up qwen 3.6 training regime on dgx spark with the current autnomous session currently lasting 70+ min without any prompting. Kimi with hermes is next level. @NousResearch @Teknium