What’s one thing you wish your Hermes agent was better at? There may already be a Skill for it sitting in the Hub.

Oh My Hermes, what do we have here? 🔥 3K GitHub stars and growing. This community build packs A LOT into Hermes. Oh My Hermes adds intelligent model routing, coordinated subagent workflows, long-term project memory, 100+ specialized skills, and live visibility into what your agents are doing. And it’s not just for terminal users. You can benefit from it whether you use Hermes through the terminal, Desktop, messaging gateways, or a mix of all three. One install adds an entire extra layer to the Hermes setup you already have. Built by @rlaope.

Installed does not mean loaded into every Hermes session. Normal Skills load when relevant. `--skills` preloads one for a session. `skills.auto_load` loads selected Skills into every new session for that profile. That last one should earn its place.

Want to make sure Perplexity Fast Search is actually enabled in Hermes? 🔎 @tonbistudio put together this quick walkthrough showing exactly where to check and how to switch your web search over to Nous Subscription.

What was the first Hermes task that made you think, okay, I’m actually keeping this?

What makes something deserve its own Hermes profile instead of staying in your default setup?

This is what makes Hermes so fun. You can build it around how you actually want to use it. 🙌 Here’s Jamie using his Agent Squad project to have Hermes hand out tasks to his other bots through iMessage. Pretty damn cool setup.

Someone just built a personalized morning newspaper that can print itself before you even get out of bed 👀 And yes, you can do this with Hermes too. This is such a sick use case. A printed morning briefing waiting for you with whatever matters most: → email highlights → weather → today’s calendar → important news → reminders → task list → meeting notes → shopping or meal plans → a personal edition built just for you → a family edition with schedules, events, meals and reminders There are plenty of ways you could build this with Hermes. One simple route is using Tailscale to connect Hermes to a computer that already has access to your printer, then letting that machine handle the printing. Wake up, grab the page, and your whole morning is already lined up.

This is a BIG upgrade for Hermes web search. 🔎 Nous just moved managed search to Perplexity Fast Search, built specifically for agents, and it’s free across every Nous Portal tier. Perplexity handles search. Faster, better web search without paying for it. 🔥

Most Hermes setups probably need fewer permanent agents than people think. Temporary independent work? Delegate it. Separate memory, Skills, schedules, credentials or identity that needs to still exist tomorrow? Give it its own profile. Split durable state, not every task.

Someone just gave Hermes hands on an iPhone. 🤯 The crazy part here isn't that Hermes logged into GitHub. It's how it did it. Using Phone Harness, Hermes can see and operate the actual iOS interface. Taps, swipes, typing, apps, even the authentication flow shown here. No jailbreak. No app-specific API. Give Hermes the right tool + Skill and suddenly an entirely new interface becomes something it can operate.

If you could add one new Skill to your Hermes setup today, what would you want it to do?

What integration is Hermes still missing that would make a real difference in your workflow? What would you use it for?

Andrej Karpathy just gave one of the clearest explanations I’ve heard for how people should be thinking about their Hermes agents. Not one agent. All of them. “Remove yourself as the bottleneck.” That line is much bigger than better prompting. Karpathy is talking about arranging your agents so they can operate with less human intervention, keep work moving longer, and accomplish far more from the relatively small amount of direction you give them. That should be the direction you’re pushing every Hermes agent you build. Your research agent shouldn’t need you to tell it what to search next every five minutes. Your monitoring agent shouldn’t depend on you remembering to check something. Your content agent shouldn’t stop after step one when the rest of the workflow is already known. Your development agent shouldn’t need you sitting there approving every tiny action. That doesn’t mean blindly making everything autonomous. It means deliberately looking at every place where you are still unnecessarily sitting in the loop. Give the agent a clear objective. Give it the tools it needs. Give it the right Skills, memory, files and project context. Define the boundaries. Define what success looks like. Give it a reason to start working, whether that’s a schedule, an event, a recurring task or another agent handing work off to it. Most importantly, define what it can handle itself and what actually requires you. That’s the shift. You’re no longer just building something you can chat with. You’re building an operating workflow that can continue doing useful work after you walk away. Karpathy later puts the goal even more directly: get “more agents running for longer periods of time without your involvement.” That might be one of the best north stars you can use for a serious Hermes setup. Because the number of agents you have means almost nothing by itself. You can have 20 Hermes agents and still personally drive every single action. Or you can have five well-designed agents researching, monitoring, organizing, building and reporting while your attention is somewhere else. So instead of asking: How many Hermes agents can I build? Start asking this about every agent you already have: What am I still doing that this agent could be doing without me? That’s where the leverage starts.