Hermes + North Mini Code: New FREE API!

[00:00:00]There's a brand new free API and free local model that you can use with Hermes agent and it's called North Mini. I'm going to show you exactly how it works.

[00:00:10]We've run it both locally and also with the API. Pretty powerful stuff, super fast and it's designed for agentic coding. We've already plugged it into Hermes agent like you can see and we said like you working and actually replies like you can see right here. So, you can work with Hermes agent. It's pretty quick to reply and it can do all sorts of stuff. So, if we say for example, okay, schedule a Japanese practice session uh 5:00 a.m. today or 5:00 a.m. tomorrow plus daily as a scheduled task inside Hermes.

[00:00:43]We can plug that in and then Hermes will use North Mini to just go off and build this. Now, you might say at this point, okay, how does this work? What are the benchmarks like? How powerful is it? How do you get access? I'm going to cover all of those questions today. So, number one, how do you get access to it? So, you can actually get access on Openrouter. So, if you type in North Mini, you'll see North Mini code is ready to go. It's 256K context window and it's free to use and you can plug it into Hermes agent directly. Pretty awesome. Now, how do you actually set this up with Hermes? All you do is you go to your terminal like so and then you go to Hermes model, select Openrouter from the list and then you would select North Mini code as the model for uh your Hermes agent. That's how easy it is. So, you just type in Hermes model, set up Openrouter.

[00:01:34]So, what is the API? It's this free one.

[00:01:37]How do you get access to it inside terminal? Now, you can also run it with Ollama. So, if you prefer to use Ollama and run it locally, this is not a cloud model from what I've seen. So, you can install Ollama in one single click using this terminal command and then from here, you just go to this section and you can see again it's a local model, it's not cloud-based which means it's free for anyone to use and run locally.

[00:01:58]Um then to pull the model, you would click this, paste it into your terminal with a llama running. To run it inside Hermes agent, you can use this terminal command. You can also run it with open claw, clawed code, code X app, code X and open code as well. Pretty awesome.

[00:02:13]And so, if you are out of tokens or if you've run out of usage on your existing limits, you can just use a free model like this and plug it into Hermes for it nothing can stop you. That's pretty cool. And so, this is how you can use system, how it works, etc. And this is something I call the free API command engine. So, you can wire it into Hermes and you get an agent that can write files, run tools, build real things for you for free. And you know, we just for fun we built this out with Hermes, but you can use it agentically and it can call tools. It's actually a very small model.

[00:02:46]So, this is a really small model if you're running it locally, which means it's really fast and it outperforms Gemma 4 uh on some of the benchmarks. It's 30 billion parameters with 3 billion active. It's one command to run it, 256K context window, and free whether you use it on the API or if you use it directly with um a llama as well. So, you got two different options right there.

[00:03:09]And you can see that it's working. It's scheduled the task, pretty simple and easy, and you can see that it's currently scheduled that Japanese practice that we just talked about right there. Pretty nice. So, here's the announcement of North Mini and its setup. And you can see how it performs on benchmarks. So again, you would compare it against models like claim 3.6, Gemma 4. These are the comparable models if you want to understand how it works, etc. And you can see the quote from Cohere here who built it. So, North Mini Code is Cohere's first agentic coding model, a 30 billion parameter mixture of experts model with 3 billion active, optimized for code generation, agentic software engineering, and internal tasks. That is perfect for the Hermes agent. It's also available on Hugging Face and Openrouter for free as well. So, you can see the details on Hugging Face right here in terms of the architecture, how it works, everything else. So, how can you wire into Hermes? You just grab a free Openrouter key, create a Hermes profile for it.

[00:04:10]So, we actually created North Mini as a profile and you can use this terminal command to create a separate agent profile for North Mini. Why would you do that? I think it's good to separate agent profiles by API because then if one goes down, you can use another one.

[00:04:24]You don't need to switch the models manually. And also, you can test them side by side and give them the same tasks. So, if you look at our agent operating system for Hermes, you can see that we can select between all these different models and we have the conversation history for each one and we can just use them based on the skills.

[00:04:38]So, we have Communicator 7, Claude 3.7, and also North Mini ready to go. We can see the full conversation history over here. We can also talk to our AI agents.

[00:04:46]We can voice activate them. We can generate images, video, and voice with them as well. But if you just want to chat with North Mini or build out teams with them, you could also use the Kanban board here. So, you can actually set up a Kanban board just for North Mini and then give it tasks. It will automatically triage inside the Kanban board and build it step by step. So, now at this point, you understand how to set up an agent profile for this, how to run it with free API or with local models.

[00:05:13]You've seen it work in action. You've seen how powerful the model is.

[00:05:18]Like, it is a big, big update. I mean, it's it's pretty useful. A lot of people run out of tokens quickly. This is an option to to fix that.

[00:05:25]Now, let's talk about the old way versus the new way as well.

[00:05:28]So, if you're using an API currently, well, every agent uses up tokens. You have to kind of ration those tokens and you're scared of doing stuff because you don't want to use up too many tokens whilst you're building and that is a big problem, my friends, right? And then also, you might want to let it run overnight It's a 24 AI agent, but if you're running if you're scared of running out of tokens, well, that's a nightmare, right? Whereas if you have a free API, you can run it all day, 24/7, there's no meter, especially if it's local. You have a free agentic model wired into Hermes, you can throw it every small job without thinking twice. You can spin up several agents in parallel for free, and you can save the the premium models for the jobs that actually need them, right?

[00:06:08]So, you can use your frontier models for the really powerful jobs, and tools like North Code Mini for the small jobs.

[00:06:16]Now, if you want every system and setup that I've shown you today inside the AI Profit OS, you can get that inside the AI Profit Bot Room.

[00:06:23]Link in the comments and description, or just go to the AI Profit Bot Room.com to get access. And you also get four coaching calls a week, plus daily tutorials as new models drop, a 30-day roadmap, every prompt in the Obsidian memory setup for all the agents, and 3,600 members inside the AI Profit Bot Room who are building systems like this as well. So, you can get that all inside there. Now, some people say, "Well, free models can't really build anything."

[00:06:46]But, you've seen how it worked today.

[00:06:47]Like, it can actually be used agentically. Other people say, "Well, setting up a new model, that's a lot of work." But, as you've seen, it's just like one quick copy and paste terminal command. And other people say, "Well, I'll just keep using my paid model for everything." But, then you keep paying for the cheap jobs, too. Whereas, you could route the grind to free models, save the premium for what it's worth, um and that's the whole game right now, right? And you might say, "Well, this sounds technical or difficult to set up, etc." We've got 184 pages of testimonials and wins from people setting this sort of stuff up inside the AI Profit Bot Room, right? So, if they're non-technical and they can do it, and if I'm non-technical and I can do it, then we can all build with this, right? You don't need to be a coder or developer or technical to build with AI agents anymore. That's totally changed.

[00:07:33]So, what you just gained? A free coder, Cohere, North Mini Code, completely free on the API. A real agent, cuz you've wired it into Hermes. It can write files, it can run tools, he can build it, can schedule tasks for you. It's a 2-minute setup. You just set up a profile. I've shown you the terminal commands for that already.

[00:07:49]It can build. So, you have one command, and then you get a finished artifact in its workspace. So, for example, everything that we build with whatever agent we're using, we get the full setup inside here, right? So, we can see what we've built, we can preview it, and we can come back to it later. So, everything that we build with our Hermes agents is saved inside our workspace, which is just awesome and easy to use whenever you want to get it, right? And then you can run it all day, especially if you're running it local. So, you can have this running 24/7 and doing tasks for you, and you actually have the output because this is an Apache 2.0 weights license, um so you can keep everything it makes. And I would say, you know, honestly, the best agents to experiment with are the free ones because it doesn't matter. Like, if you you're not going to worry have to worry about tokens or limits or resources, you can just, you know, build cool stuff and see what it does. So, if you want to make the free model part of your system, we uh you know, there's new free models dropping every few weeks now. The agent operating system inside the AI Profit Bot lets you wire each one in and root work to whatever's best and the cheapest without rebuilding anything. So, if you want the full agent operating zip file with Hermes and every model inside one dashboard, the setup walkthrough, four weekly coaching calls, 3,600 members, and 155 uh sorry, 184 pages of member wins, you can get that inside the AI Profit Bot.

[00:09:10]Link in the comments and description, or go to the AI Profit Bot dot com. Inside the community, you can ask questions, get help and support in real time. I answer these questions personally.

[00:09:18]Inside the classroom, you can get access to all my best trainings, including the new daily updates, and we have it the agent OS system over here. We update it daily, so we're going to add a new version later today. You get the video tutorials, the zip file, and new tutorials added as they drop. You can also jump on weekly coaching calls, get help and support in real time. Inside the map, you can meet people locally who are building with AI agents like Hermes and North Mini in your local area. And this is all available inside the app for boredom. Link in the comments description or just go to the app for boredom.com to get access. Thanks for watching.