WEBVTT

00:00:00.000 --> 00:00:33.990
So we're looking at right now is something that I practically use every single day to run my business. And this is one small element that's called the hive mind, which is essentially a shared memory state of my ever growing team of agents. Agents. Each set of agents correspond to different parts of my digital brain and each one of these little nodes here represent tasks that they've completed. So if I want an overview of the overall activity of all my agents and all the knowledge that they know about each other, this is one of the many ways I can represent that. Now if I want something more on the two d side, something very similar to Obsidian's

00:00:33.990 --> 00:01:03.880
graph view, then we have this portion where we can filter on specific agents, and then we can even search specific tasks. So if I search something related to Gmail, you'll see every single node that remains that represents a task where Gmail was executed. And if I wanted a list view, I could go through this entire table and see each and every action of every single agent in the same place. Let's say I was feeling particularly introverted today and I wanted to have the equivalent of an MSN group chat with all of my agents.

00:01:04.200 --> 00:01:23.285
I can go to this specific section called my war room and instead of using my voice, I could put on my headphones and go straight to the chat room. And when I click on text meeting right here and we click through, this will open up a brand new chat room where I can use all of my specific commands to have stand ups and discussions with all of my agents.

00:01:23.445 --> 00:01:31.110
So all I have to do is I can go into maybe small mode or large mode if I wanna be able to see every single agent at my left hand sidebar

00:01:31.110 --> 00:01:48.885
as well as a status that shows their last completed task. And I can go to the very bottom here, and I can do slash stand up. And I can either tag specific agents to give me the status report or I can have them all tell me what they've done in tandem. So if I just send this specific command right here,

00:01:49.285 --> 00:01:54.485
each one of my agents will be invoked. It will go through its associated database

00:01:53.680 --> 00:02:10.045
and set of memories to tell me exactly what has completed in the last twenty four hours. And you can see each one of them goes through and gives me a very succinct status report ending with our meta agent. So we have the research agent chime in and tell me that this part of the YouTube space might be a little bit saturated.

00:02:10.125 --> 00:02:26.110
Then we have comms who is my designated content agent, the one I probably wanna listen to the most. But each one will chime in. The main agent will kind of look at the other responses and give me the cohesive response on behalf of the rest. So with just a few prompts and slash commands,

00:02:26.190 --> 00:02:45.085
you can have your own LLM council at your fingertips. Now big picture, I wanna be very clear about what this video is. It's not meant to be a step by step walkthrough on exactly how you can go from absolutely zero to this. And the reason is this takes hundreds of hours to start, iterate, and refine. It's meant to show you what's possible,

00:02:45.245 --> 00:02:56.170
how you can get there, and most importantly, how to break down this very opaque concept of this AI operating system. Whatever the term of the day is, this is purely a data organization

00:02:56.170 --> 00:03:06.170
exercise with some layers on top. So in the next twenty ish minutes, my goal is to show you what I use this for day in and day out, how you can set it up for yourself, and most importantly,

00:03:06.515 --> 00:03:41.775
breaking down this very opaque concept of the AI operating system into the simplest terms so you can finally understand it and implement it on your own. Whether you want to use Claude code, codex, or even both, you'll be able to apply all the principles I'm about to show you to whatever LM you want. Let's get into it. And before we deep dive into every bell and whistle that this system has to offer, it's important to level set for anyone that's new here or hasn't watched my prior videos on this. A few months ago, I was quickly jaded with what OpenClaw could and couldn't do, and all I wanted was an easy way to connect my existing Cloud Code subscription

00:03:41.855 --> 00:03:50.815
to my existing Cloud Code ecosystem and connect them together. And I went from wanting to creating a way where you could use a bridge called the Anthropic SDK

00:03:51.040 --> 00:03:54.320
and connecting it to your ClaudeCode system so any skill,

00:03:54.480 --> 00:03:58.960
any project, any plug in was accessible through my Telegram interface.

00:03:58.960 --> 00:04:14.255
And I went from interacting with one singular agent to a team of agents to creating a war room where I had an experimental feature to go back and forth using my voice. And now I've evolved this hive mind to allow me to interact with all of these specialized knowledge,

00:04:14.335 --> 00:04:15.775
the subject matter expertise

00:04:16.040 --> 00:04:24.920
of every single employee in my workforce. And the best part of this system is because my Cloud Code is already connected to all of these services through various CLIs,

00:04:24.920 --> 00:04:26.520
integrations, and skills,

00:04:26.760 --> 00:04:29.800
all of my agents inherit this existing infrastructure.

00:04:30.155 --> 00:04:51.070
Now let's make this practical by walking you through one actual business case. So let's say I have a Meta agent, and this is something that I've been experimenting with recently. I'm a novice when it comes to Meta ads, so I wanted the power of Cloud Code to connect to services like the Meta command line interface, which is a brand new way to look at, track, and understand ad performance.

00:04:51.150 --> 00:05:14.620
Behind the scenes, it has a set of instructions walking you through exactly what its role is and how to interact with all of these services, And underneath the hood, this is how it works. When I ask it a question, it will go and proactively search the Meta Ads command line interface. This is a fancy way for Claude Code to go and investigate the entire API and see every single part of a campaign,

00:05:14.860 --> 00:05:31.905
ad spend, ROAS, and a bunch of other words that up until a week or two ago, I had no idea how to actually apply. And then because I want the information distilled and portrayed in a very specific way to be displayed on my mobile device, I create a meta ad skill and this basically creates a custom report.

00:05:32.145 --> 00:05:34.145
Once the skill exists globally,

00:05:34.385 --> 00:05:44.260
every single one of my agents automatically inherits it. And because of this, I can now create a scheduled task that will send me a ping every morning at 07:30AM

00:05:44.260 --> 00:05:46.500
of a full summary of ad performance.

00:05:46.580 --> 00:06:08.025
And if I wanted to go back and forth with my agent and get to the bottom of which ad is working, are any working? Do I have to create some brand new creative? I could also task it with creating that creative using the Gemini skill to use something like Nano Banana to create the creative, add the creative, add some money, put some spend on it, and see how it performs. And this is one small microcosm

00:06:08.025 --> 00:06:18.600
of every single task that I give my set of agents so I can focus on the things that matter. And this is what it actually looks like. So today, I got this report. It breaks down the spend,

00:06:18.760 --> 00:06:19.640
the actions,

00:06:19.720 --> 00:06:47.120
a couple blind spots that I might have, and each one of these hyperlinks right here linked to the direct ad that it's referring to. And again because this is more than just a reporting tool, it can give me a quick take at the bottom here, tell me if I have a winner, a loser, what I'm doing wrong, and how x is affecting y in a way that I might not know out of the box. Now in a similar fashion, I'm gonna go through the relevant tabs that you might wanna adapt to your own system and show you one, how it works tactically,

00:06:47.200 --> 00:06:52.975
and underneath the hood, what's involved to make that happen. So this mission control dashboard is meant to be a glorified

00:06:52.975 --> 00:07:19.945
Kanban where you have all of your agents in one place. You can spy and see if any tasks are happening in parallel real time, and you can switch the layout as you wish, and you can always create a new task and drag and drop it to the agent of your choice. And if you don't want the cognitive load of deciding which agent should take this specific task, you can always do an auto assign. So in this case, if we take this task, which is purely sending Mark a message saying hi,

00:07:20.185 --> 00:07:22.025
you can click on auto assign,

00:07:22.345 --> 00:07:28.345
and then this will use Gemini underneath the hood using the cheapest model from Gemini, which is inconsequential

00:07:28.345 --> 00:07:50.065
from a cost perspective to tell you which agent is best geared for this. And naturally, it chooses the comms agent. So this will now be queued and then sent over and within seconds to a minute depending on the size of the task and the length of the task, it will be executed and you can follow-up on Telegram. And by the way, if you wanted to swap Telegram for Slack or Discord,

00:07:50.145 --> 00:09:12.315
you can do that. You just have to set up the connection and make sure it's stable. And within seconds, the system gets pinged that there's a queued task, it starts running, and then it should execute until it's completed. And by the way, as usual, I'm gonna give you a series of resources to help you reverse engineer as much as I'm showing here as possible. But if you want my carbon copy system that I keep on updating every single week with brand new features, adjustments, and everything needed to make this awesome, then you'll wanna check out the first link in the description below. Not only do you get access to this current version of Clawd Claw, but we're working on multiple versions. One for enterprise and eventually for local, and on top of that, you get access to myself, my team of coaches, as well as the Claude code magic course, which is our living course for anything related to Claude code. If that sounds interesting to you, then check out the first link in the description below, and let's get back to video. And because my comms agent is a subject matter expert at anything related to communication including my email, my Outlook, my LinkedIn, etcetera, it knows that for Gmail to use the Google workspace command line interface, which is already a part of my Cloud Code system and leverage it to draft this email. Now if we take a peek behind the curtain, all that's happening is that we have a series of tasks here and I'm using the Gemini skill using the absolute cheapest model Gemini three flash to take all the tasks and auto assign it with a very basic system prompt. And the system prompt is dynamic.

00:09:12.555 --> 00:09:33.880
Based on all the agents that we have, go and decide what is the best geared agent and here's a description of all of the agents. So then Gemini classifies it, it adds it to the queue, and then the system gets pinged like you saw. It starts running, and once it's done, we have completion. And the hardest part of the mission control is making sure to remember that the front end should always have a perfect symbiosis

00:09:33.880 --> 00:10:14.905
with the back end so that when you have a task on screen that propagates to something like your telegram API, your different APIs are being used, and making sure that this whole system is cohesive. Now the schedule tab is very straightforward. It purely creates what are called cron jobs and these are scheduled jobs that run on your computer locally. And even if you host it on a VPS or a cloud provider, you can schedule it from there as well. And if we click on something like this schedule task for our meta ad CLI, you could see we could just add a time from here really easily. We could say every weekday, every weekend, custom, and anything like an nnn or a make.com experience, this is the exact same thing. The trick with this one is if you want the front end to be very straightforward,

00:10:15.240 --> 00:10:21.720
this is what cron looks like underneath the hood. It's a series of numbers and characters that denote things like cadence,

00:10:21.880 --> 00:10:24.040
frequency, day, year, etcetera.

00:10:24.280 --> 00:10:48.430
You don't want to see that as a front end user. So the only thing you would want to tell Claude code is instead of showing me this raw input, show me the equivalent raw input as English or French or whatever language that it is that you speak. Now the agents tab acts as the command center for all of your existing and brand new agents. For your existing ones, you can switch the model right here Assuming you're using Claude Code and you're using your existing Claude Code subscription,

00:10:48.590 --> 00:11:05.175
you can switch the model and this will propagate, fancy word for automatically update anywhere else that this is used. If you wanna change the personality, if you wanna change the task list, if you want to tell it to focus on this skill versus that, one, you could just tell it through telegram

00:11:05.255 --> 00:11:15.860
or you could just write it directly through here. And you can always stop your agents, delete them, restart them, and I even added a feature that you might want to steal from me which is having suggestions

00:11:16.020 --> 00:11:18.900
on agents that deserve to exist that don't.

00:11:19.060 --> 00:11:32.775
And a good way of doing this is you would have some language model. In my case, I don't want to sacrifice my precious Claude code tokens so I will put my Gemini three flash API on the front lines to look through all of my conversations,

00:11:32.935 --> 00:11:36.455
scan through and see what agents am I overburdening.

00:11:36.455 --> 00:11:59.045
And in this case, you can see that comms is doing way more than it should. It's handling WhatsApp. It's handling school. It's handling mail. It's handling every single thing you can imagine. So maybe it makes sense to have another agent that's called email manager. And the best part is if you want to create a new agent, you should design it. So when you click on new agent, it lets you just write the name, the display name, the description,

00:11:59.205 --> 00:12:23.890
and it gives you the link to the bot token. So all you have to do is go to Telegram, create a brand new bot, you take the existing token, you copy and paste it into your front end, and then you should be able to activate and ping it from here. And underneath the hood, you can add way more sophistication than I do, but every single agent is purely a CloudMD file and what's called a YAML file. This is a breakdown of its configuration. You could add its own specific rules and skills

00:12:24.315 --> 00:12:26.315
completely specific to this agent,

00:12:26.475 --> 00:12:41.060
or you can keep it nice and minimalistic and just layer on top of your existing global skills in your system. And when it comes to the suggestions feature, like I said, all it's doing is looking at your usage over time, looking for really used and abused agents,

00:12:41.140 --> 00:12:42.660
looking through your conversations,

00:12:42.660 --> 00:12:54.075
and looking for patterns, using pure natural language. Because when you use things like the Gemini models, you have enormous context windows, very cheap inference, so you can afford to take entire

00:12:54.155 --> 00:12:56.315
JSON files of your conversations

00:12:56.315 --> 00:13:03.995
and automatically have that sift through and decide what makes the most sense. When it comes to the chat tab, this is just designed to have all of your communication

00:13:04.380 --> 00:13:32.045
centralized in one place. So if you wanna keep tabs literally on all of your agents and see all of your conversation history with them and continue the conversation at the very bottom of here, like you can write status update, what's next, you can type whatever message you want, you could just say hi, and behind the scenes, it will still use your existing harness, your existing subscription just from this online portal. And assuming you use this with multiple platforms, this can help distill all of those conversations

00:13:32.125 --> 00:13:55.455
into one unified view. Now when it comes to memory systems, everyone has an opinion as to what is the best. And I even dropped a video a few weeks ago walking through the different levels of memory so you can decide for yourself what makes the most sense for yourself, your business, and your day to day. In my memory world, I have five to six different layers and these layers really roll up to these three categories which are importance,

00:13:55.535 --> 00:13:57.375
salience, and recency.

00:13:57.455 --> 00:14:02.975
And the one thing that I can do in this blurred memories tab is I can write something like let's say Gmail

00:14:03.130 --> 00:14:26.545
and this will show any memory related to that. So you can make your memory palace searchable, which when it comes to memory, it's beyond just throwing a vector database and throwing everything in there and just expecting it to work because memory is not just about the setup, but it's also about maintenance. And one additional thing that you can do is you can create insights on your memory. So you can have, again, a language model, a cheap workhorse,

00:14:26.625 --> 00:15:21.785
take a look and scan through your memories and derive insights about you, Things that you don't know about yourself. And this would be the equivalent of doing slash insights in Claude code to get the full breakdown of all the pros and cons of how you've been using it over the last thirty days. Now, I've covered the entire deep dive of how I've structured memory in a prior version of this video, but the TLDR is this. You want Claude Coe to interview you on how you wanna deal with fresh memories and how you wanna deal with fading memories and important memories. Do Do you want important memories to be pinned forever? Do you want memories that fade to fade into non existence, or do you want them to be stored somewhere? And when it comes to the semantics of this system, pun intended, you have different factors that you'd wanna consider. One of them like I said is salience, is a fancy word for the importance of a memory and whether you want to create your own embeddings. Now the beauty of a system like this is that you can have it run on an online database, something like a Supabase,

00:15:22.060 --> 00:15:24.220
a Neon, or like myself,

00:15:24.460 --> 00:16:59.710
all of this is contained in a local SQLite database. So each and every part from who the agents are to all the conversations, to all the scheduled tasks, to all of my memories, to everything in the hive mind is all stored for free on my local database. So the sky's the limit, and you can make this work irrespective of the platform of your choice. Then to help you build and design your own memory system, I'm gonna give you my memory skill on top of a series of other things that you can use to interview yourself and have Claude Code build that system for you. Now when it comes to the holy grail of the hive mind, this three d version and the two d version really are based on the foundation of the list view. If the list view is actually working and the list view is operational and all the agents are logging in real time and all of the database is set up, everything else is just additive. So once you set up the boring stuff and you make sure that this table is always populated and it's populated with the latest and greatest summaries of what that agent is doing, you can always layer on the two d version or the three d version, whatever makes the most sense for you. And when it comes to implementing these more fancy features that are easy on the eye, but tricky on the back end, this is my mental model of how I create them. So in this case, I was inspired to create for myself the very thing that I really like about Obsidian, which is this graph view where if you're not familiar, each one of these bullets denotes a project, a task, or something similar. So all I did was actually screen record using Loom. You could use things like Tele, whatever screen recording of your choice, and I went through and I told it. I basically spoke

00:16:59.525 --> 00:17:00.405
freestyle.

00:17:00.485 --> 00:17:07.445
This is what I love about the Obsidian Graph View. I just wish that I could create it in a way that really synchronizes

00:17:07.445 --> 00:17:14.120
in real time to what my agents are doing. And then all I did was I hooked up to my Claude code system,

00:17:14.360 --> 00:17:16.600
this skill, which is the Gemini skill,

00:17:16.760 --> 00:17:23.160
and as a part of this skill, if you zoom in here, one of them is processing video through their video understanding API.

00:17:23.320 --> 00:17:52.040
So all I did is take the Loom, download it, drag and drop the file path and I said, hey, want to build this, but I wanted to integrate into my mission control in this way. And one added thing is depending on your system, this three d version again looks beautiful, but it uses a lot of resources. So if you don't have the best of computers, then the two d version is the most efficient. Now ending off with the beloved War Room, in my last video, I walked through at length on how I designed this voice and live meetings capability.

00:17:52.395 --> 00:18:16.230
The voice being the part where I can launch this specific room, it plays a beautiful tune behind the scenes, and it allows me to interact with all my agents synchronously. And I went from just having the ability to speak to my agents in this way to now having the ability to go back to the war room, go to the picker, and then I can select who should always be in our stand ups when we do our daily meetings. And the way I designed this theoretically is very simple.

00:18:16.470 --> 00:18:25.165
I wanted to not only always have a synchronized list of my latest and greatest agents, and I also wanted to have a list of their latest and greatest tasks

00:18:25.245 --> 00:18:55.705
according to the hive mind, but I also wanted to create a special set of slash commands specific to this room. And a couple of them you already saw, one of them is slash stand up, and one of them is slash discuss, but it can also pin an agent so that they lead every single reply. So if you wanna have your council meeting, but you wanna designate one specific agent as the core leader of this meeting, then you can do so. And then everything else is just clearing the agent history, and the hardest part of this is making sure that when you have this conversation,

00:18:56.105 --> 00:19:07.490
each agent is aware of the last response and the overall context. And luckily, I'm not a rocket scientist. I just asked Claude Code, can you find a way that in this specific ecosystem

00:19:07.490 --> 00:19:10.210
of the War Room that we can have this conversation

00:19:10.290 --> 00:19:24.285
and it all has context on all the other replies as well as their underlying Claude MDs, YAML files, etcetera. And on top of that, if you played around with things like custom GPTs back in the day, then you'd remember you could tag specific GPTs

00:19:24.365 --> 00:19:30.925
in the exact same manner. If I want to talk to my content agent and ask it, give me advice for creating

00:19:31.550 --> 00:19:32.750
a good video

00:19:33.070 --> 00:19:35.710
on a Claude Claw system

00:19:35.870 --> 00:19:37.310
for YouTube,

00:19:37.390 --> 00:20:13.605
this will automatically tag that specific agent. And again, these are small things, but everything is iterative and everything is additive. So the core question to ask yourself is what is the eighty twenty for you in terms of features that actually drive business value and drive ROI versus something that's purely a novelty? And behind the scenes, the stand up and discuss slash commands are purely pinging this non visible prompt to you and I that's basically telling them, give me a status report on what you've done according to your entries in the hive mind as of the last twenty four hours. So this is really where you see the entire system coming together and acting cohesively.

00:20:13.605 --> 00:20:19.845
Alright. So now that you have an understanding of how my system works, I wanna walk through this paradigm of the AIOS

00:20:19.845 --> 00:20:32.820
so you can fully understand it and see how it plays into what I've shown you thus far. Now the main thing I'd say about this system is that all of this top layer here, the part where you have the fancy dashboard that I showed you, all the functionality and features,

00:20:32.980 --> 00:20:59.880
all of that is cute. But the part that really matters, the foundational layer is this bottom layer. How is your data organized? If your back of house is organized, then everything else is purely a cherry on top. So if your system looks like this when you open up your desktop and you have files and folders all over the place of different file types and sizes and you expect that even taking my carbon copy system and layering it on top of this will give you something very powerful,

00:20:59.960 --> 00:21:04.920
you'd be wrong. The art of making this work is really the art of just being hygienic

00:21:04.920 --> 00:21:08.520
with your files, your skills, and deciding very proactively

00:21:08.815 --> 00:21:13.375
what deserves to be a global skill and what deserves to be a project level skill.

00:21:13.615 --> 00:21:21.535
And again, skills are universal whether it's Codex, Claude, or Gemini. And beyond that, it really just comes down to the different skills, rules,

00:21:22.000 --> 00:21:24.720
and command line interfaces and integrations

00:21:24.720 --> 00:21:30.160
they make available to existing OS. And when it comes to the agents, the skills in the CloudMDs,

00:21:30.240 --> 00:21:38.935
you again just have to decide what deserves to graduate or be promoted to a global skill that every single agent should have access access to versus

00:21:39.015 --> 00:22:43.705
what should I pigeonhole, make specific to one particular terminal agent or project. And once you have this bottom layer figured out, everything else is easier. You just add on some form of memory. You would decide what kind of database makes the most sense for me. Do I care about scheduling? Do I care about specific agents? Do I want specific skills for these agents? Or do I purely wanna just build on the existing skills in my system? Once you make those decisions, the last part is how would you like to interact with your system on the go? In my case, it's Telegram because the blast radius of my business and my business contacts and my personal life is zero. In your case, it could be signal. It could be discord. It could be whatever. So the deeper you get into this agentic OS or AIOS or whatever the term will be five hours from now, the deeper you understand that this is a data engineering problem. This is not a AI problem. And once you get the hang of one of them and you start playing around and giving it feedback saying, you know what, I hated the way you did this. This is where you don't have self improving, but you have iterative improving, which when it comes down to it,

00:22:44.105 --> 00:22:54.530
for business purposes, the best way to build agents is to have an infinite game mindset where there is no one solution. There's no Hermes agent or OpenClaw agent configuration

00:22:54.530 --> 00:22:57.730
that's gonna be perfect for you. This is an iterative process,

00:22:58.050 --> 00:23:14.235
and basically fixing your back of house and layering this on top allows you to go iteratively and decide is this a data layer problem or is this my operating system problem? And to help you not only understand, but implement a lot of the concepts that I walked you through, I'm gonna make available to you a series of resources.

00:23:14.315 --> 00:23:39.425
This includes a full blueprint of my existing system that you could feed to Claude code, codex, and reverse engineer everything that I showed you here. You could also take the transcript of the video. You could even take the video itself and feed that to Gemini and ask it to create the perfect prompt for you to design it, but also give you as many supporting documents as you need along with the skills to create the memory system of your dreams. And again, this is something that I've been working on nonstop.

00:23:39.425 --> 00:23:46.865
I've been iterating on it for months, and everyone in my exclusive community has had access to each and every version and all the supplementary

00:23:46.950 --> 00:24:12.095
So if you want the carbon copy version of my command center and you wanna keep tabs on everything else we have coming up, which is even an enterprise grade version of this system, then you'll wanna check out the first link in the description below, and I'll see you in my early adopters community. And for the rest of you, if you found this video helpful, inspirational, and hopefully informative, then please let me know by leaving a like on the video and a comment. It really helps the video and the reach, and I'll see you all in the next one.