we’re huge fans of Hermes Agent and have been using it internally for a while. we ended up building a bunch of systems around it for our own workflows, and that’s really where we saw how powerful it can be when everything is set up properly. at the same time, a lot of people i talked to around SF had heard about Hermes and knew it was powerful, but either didn’t know what they would actually use it for or didn’t feel comfortable setting everything up themselves, especially when it came to data and permissions. we already had a lot of that infrastructure built internally, so we started packaging it into something much simpler. that’s how iHermes started. honestly, it was a fan project first. the goal was to let more people get the value of Hermes Agent without needing to understand or maintain all the technical setup behind it. iHermes is an independent service and isn’t affiliated with or endorsed by Nous Research. Hermes Agent is MIT licensed and allows commercial use. when we say “powered by Hermes Agent,” we mean that Hermes is part of the underlying technology we’re building on, not that there’s an official partnership or endorsement. we also really appreciate the feedback around our privacy policy, model usage, and data handling. we’re reviewing the points raised as a high priority and will update anything that doesn’t accurately reflect how the product works or could be communicated more clearly. privacy and security are a big part of what we’re trying to build correctly. we want people to have much more visibility and control over what the assistant knows, what data is stored, where it came from, and what it’s allowed to use or do. that’s also part of why we’ve been working on the memory layer and the GBrain integration. we’ve gotten some really good feedback since putting iHermes out publicly, and it feels like there’s a real group of people who wanted an easier way to use Hermes. that’s why something that started as a project we built for ourselves is becoming a product we want to keep investing in. the Hermes community is important to us, so genuinely, keep the feedback coming. if there’s something we’re describing incorrectly, something you think we should build, something in the privacy policy we should revisit, or something you think we shouldn’t be communicating at all, feel free to tell us directly. we’d rather fix it early and build this in a way that’s respectful to Hermes and useful to the people who want to use it.

Introducing iHermes A personal AI assistant powered by Hermes Agent, with GBrain for memory. You talk to it in iMessage. We're huge fans of Hermes. We've been using it to build internal systems and automate work, and we wanted more people to get that kind of value without having to set up the whole thing themselves. Start with one text. Connect the apps you use, hand off a task, and let it work through the steps. It keeps useful context from your earlier work and follows up proactively. Our goal is to make iHermes the most transparent and secure personal assistant in iMessage, built around the person using it. Your assistant should work for you.