GLM 5.2 + Claude Code is INSANE!

So today I'm going to show you how I've plugged GLAM 5.2 into Claude Code and also Obsidian. And it's a really powerful setup that means we can build and automate anything we want with GLAM 5.2, which is really powerful in itself, but we can actually do it inside our harness for Claude Code, which is pretty cool. And also the cool thing about this is obviously it's a lot cheaper than using Claude Code on a subscription. So you can get the power of Claude Code's agent harness and you can plug GLAM 5.2 into it.

And on top of that, what you can actually do is you can build with it, save everything inside your workspace and use this inside your agent operating system, like you can see right here. So we have Claude Code, but it's running on GLAM 5.2. So you get the same agentic power that can build whole apps, websites, whatever you want, but it's a different brain underneath, which is GLAM 5.2, which is a lot cheaper. Now, at this point, you might be saying, OK, that's great.

But how does GLAM 5.2 compare to something like Opus 4.8? So if we take a look at the benchmarks over here, on a lot of tasks, when I tested it out personally, GLAM 5.2 could actually build better things and create better outputs than Opus 4.5. So for example, here's something we actually built out. It's kind of like a full open world game.

And also, bear in mind that with this system, if you ever get, for example, rate limited or you run out of tokens inside Claude Code, well, you can easily switch to something like GLAM 5.2 and build out some awesome stuff as well. So how does this work? So it's pretty simple and easy. What you can do is you can download OLAMA for free.

And then once you've got OLAMA, make sure you're on the cloud subscription, go to models, and you can set up GLAM 5.2 with Claude Code here. You can also set it up in one click with OpenClaude or Hermes Agent, Codex, etc. So it's pretty easy to plug into all of these. And then what I actually did is I got Claude to set up for us directly and create a little workspace where we can save everything that we've created.

So we have GLAM 5.2 with the workspace over here, but then we've also got GLAM Code, which is GLAM 5.2 Cloud, plugged into Claude Code here. And the other cool thing about this is it links to our memory. So this is actually synced to our memory galaxy with Obsidian, which means that every time I create outputs with GLAM and Claude Code, it's personalized and it's linked to all of my memories. And also, anytime we use GLAM 5.2, that is actually logged directly into our Obsidian memory too, so that we can categorize and also we can pull more context in there.

And I don't need to organize it myself. So if we go back into GLAM Code here, if we want to just use it, we can just tell Claude Code what we want to build. So we can say, for example, OK, build out a Pomodoro timer app just as a quick demo here. And you can see it working directly.

And we've got this plugged in on High Effort with OLAMA, and it's pretty simple and easy to get it working. Now, you might say, OK, what is GLAM Code? Well, we've got Claude Code, which is the coding agent that can actually do stuff. And then you can basically point Claude Code's brain somewhere else, like, for example, GLAM 5.2.

Now, as another example of this, we've actually got free Claude Code plugged into the system, which means that when we're creating stuff, we can also use free local models with the same harness. We can even direct that with voice chat, and then we can see what it builds live over here. And we've got the workspace with everything we've created over here too, which is pretty cool. And then every time we create something, it's all saved in one place.

And then you can see our creation right here, pretty simple and easy. So we can build apps with this, tools, games, landing pages. Also, the other thing that I've seen recently is like sometimes, especially if you're using Claude Code in desktop, like, it will just fail at doing stuff. So this way instead, if it ever fails or breaks on you, you can just switch to GLAM 5.2 with Claude Code instead.

And it works in three simple steps. So Olama runs GLAM 5.2 for you, you point Claude Code at it, and then AgentOS can just make it a simple button where you can switch between all your agents and you're ready to go whenever you want. So for example, we can switch to Paperclip here or the AI Agent Mastermind. We've actually got GLAM 5.2 plugged into the Agent Mastermind.

This is basically like a group chat as well, where our agents can talk together. And then if we need to, we've just got in one single click Claude Code with GLAM 5.2 plugged in right here. And we're going to see like our recent builds, we can see what's new with this. It looks and feels like Claude Code, plus we've got a full workspace one right here.

And you could do this with anything on Olama actually, that would be pretty interesting. So any model that you like the look of on Olama, you can plug it into GLAM Firepoint. Sorry, you can plug it into Claude Code. So we've got Claude Code for, for example, KimmyK217Code.

You can even use free local models with this as well. One thing I will say is like local models are great, they're free. They're not going to be as powerful as Claude Opus. But GLAM 5.2 comes pretty close to it, like pretty much there.

And it's a million token context window as well. And so you can use it, you can type what you want whenever you want to. We built a few apps with it as well, it looks pretty good. Also, you might say like, doesn't this cost a lot of tokens, etc.

So you've got two options for this. Like you could use Olama, or you could actually plug in your existing CLI with GLAM 5.2 if you've got the coding planned. And then plug that into Claude Code or just use a CLI directly instead. The reason that you wouldn't use like the normal CLI here is like, it's just not going to be quite as good for coding as something like Claude Code.

And also it's kind of fun to switch between them. We've also got, for example, Olama GLAM 5.2 plugged into Hermes here. It's a separate profile. So we can manage all of our agents in one place.

And the cool thing about this is however you want to use GLAM 5.2 is very, very flexible. So if you want to use it inside Claude Code, you've got it ready to go over here. If you want to orchestrate it inside Paperclip, well, you could do that over here with your teams of agents. If you wanted to plug it into Hermes, you could create a separate profile and have that running right here.

I mean, one thing we actually did as well with Hermes is we have GLAM 5.2 and we turned it into a video creation team and also a blogging team, as you can see right here, where they can all coordinate together and build out whatever we want as a team of Hermes agents as well. So whether you're using it in Claude Code or Hermes agent, it's a pretty powerful system. So that's basically it. Now, if you want the full system, we've got GLAM Code in one tab.

We have the Agent Operating System, which is a whole workshop. And basically what you can do with this is have all of your agents in one place, Hermes, Claude, GLAM Code, et cetera, all running together inside one system, which is the Agent Operating System. If you want to get our full system for using this and a community of people learning, sharing, and growing together. We actually had a member who messaged me about this today, and that's why I actually tested it out today.

You can get that inside the AI Profitable Boarding. Link in the comments description or go to theaiprofitableboarding.com. People are sharing really awesome stuff, as you can see right here. And every single question that goes inside here, I personally answer along with video tutorials.

Plus, there's always people online 24-7, which means you can get help and support whenever you want to. Now, inside the classroom, you get access to all of our best trainings. Inside the new daily update section, you can actually get access to the Agent OS. We update it daily.

You get the video tutorial, full guide, and the resources to install it. And then we add new guides based on what's actually useful that comes out. We test out with a video tutorial and give you a full guide on how to use it. Plus, you get a four-weekly coaching course.

You can ask questions, share your screen, meet other community members. You can also use the map to meet people locally near you who are building with AI agents just like you. And that's all available inside the AI Profitable Boarding. Plus, you can DM me personally if you have any questions.

Thanks for watching.