00:00Welcome to Archon, your command center for AI coding

00:02It is your tool to manage all of your knowledge and tasks for your AI coding assistant

00:08The big goal of Archon is to be the one tool that enables AI and human collaboration at a very deep level

00:16It's something that is very much missing in the AI coding space right now

00:20So, Archon is the tool to fill in that gap for you, for you as the user

00:25It is a beautiful user interface to manage all of your projects and tasks and all of the knowledge that you're curating for your code bases, the libraries that you are using

00:33And then for the AI coding assistant, it is an MCP server to manage all of the same things, so super easy to connect this to literally any AI coding assistant

00:43And then you instantly give it access through the MCP to search all of the documentation that you've curated and manage the same projects and tasks in this Kanban board

00:54And so for this video right now, I've got three things for you

00:58First of all, I want to cover why we actually care about using Archon in the first place

01:02Then a quick start

01:06I just want to help you in a couple of minutes get Archon fully set up and connected to your AI coding assistant

01:10And then the last thing that I want to go through with you is a practical guide on how to use Archon in your AI coding workflows, so that you can significantly improve the code quality output of your coding assistants, and how easy it is for you to manage your AI coding assistance, so putting yourself in the driver's seat, while also still enabling your AI coding assistance to go very far

01:32Now, first of all, why do we care about using Archon in the first place? I mean, that's the big question you have whenever you're looking at a new tool, especially when it's one related to AI, and there's millions of tools out there

01:43Well, the big problem that we have With AI coding assistants right now is they take care of too many things under the hood

01:49Here's what I mean by that

01:55In our tools that we have, like Kirao or Cloud Code or Codeex, all these coding assistants, they have the ability to search the web

02:01That's their way to retrieve external documentation

02:04Right now, searching the web for LangChain or Pydantic AI, all these libraries that we're using, and they also have the ability to create their own internal task lists, so they can organize their own work and knock things out task by task, and that's all fine, and these capabilities are quite powerful, but the The problem is, there's not really a way for us to collaborate with the AI coding assistant on these things

02:27We can't really pick the knowledge that it searches through, because it's just going to search the entire internet

02:31We can't really interact with this task list

02:38It's more of an internal tool

02:46You see the problem here? It takes care of a lot of things for us, which kind of kicks us out of the driver's seat in some ways that we'd really want to be a part of the process, actually defining the tasks and choosing the different sources that our AI coding assistant is going to look for to understand the libraries

02:53That we're building with, and that is exactly what Archon helps us with

02:57So, I have a little demo going on the left-hand side here

02:59This is more just mock calls to show you how Archon works at a high level

03:02We'll really get into the AI coding workflow in a little bit here

03:06And so, first of all, it's searching my documentation, everything that I've already curated for it in the Archon user interface

03:12So, I get to point it to where to search, and so it pulls certain pages from the documentation

03:18It's performing RAG under the hood for both keyword and semantic searching, very, very powerful RAG strategies

03:25That we have for this, and then I also have it set up to manage the tasks here

03:28So, we'll see in a little bit that it's going to start moving around these tasks, and it's going to be real-time updates for us

03:33So, when it uses the Archon MCP to move these tasks around, we don't even have to refresh our UI, and we can watch it work in real time

03:42And we can even create our own tasks here without even having to interrupt Cloud Code

03:47We can collaborate with it because the next time it looks at the tasks that it has to do, it'll find those new tasks that we have created for it

03:54So, take a look at this in just a second here

03:56We'll see it move the first task to doing

03:58Boom

03:59There we go, live updates

04:00And it's just going to keep going through, moving all these tasks around

04:04It's kind of simulating what we do in a real AI development workflow

04:06So there we go

04:09It moved it to review, and then it's going to keep going on and on and on

04:11Very, very cool

04:13And there are so many other things that we have in store for Archon as well, being able to actually kick off our AI coding assistants as background tasks in Archon for our planning or validating, like reviewing our pull requests

04:27There's so many different things that we have in store for

04:29Archon, this is just the beginning that we have for the knowledge and task management, but still very, very powerful

04:35And so with that, now that you got a good understanding of how Archon works at a high level, allow me to help you get it set up, now connected to your AI coding assistant in just a few minutes

04:44So getting started with Archon is fairly straightforward, and most of the setup you're actually walked through in the user interface once you have the application up and running

04:53I'll show you that in a little bit, and there are only a couple of prerequisites that we have in this readme, which of course I'll have this linked in the description

05:00You'll want Docker or Docker Desktop, preferably, because Archon runs as a few different containers

05:06You'll want Superbase because it's the database that powers all of Archon

05:10There is a free tier for the cloud Superbase

05:12You don't even have to pay anything

05:14That's what I'm using for this demonstration

05:15And then also local Superbase works

05:18If you want to host it yourself, you can do that as well

05:21And then you'll obviously need an API key for an LLM provider, OpenAI

05:23And then we also support Gemini and Olama

05:30So if you want to run things 100% locally to have your Own private knowledge base, you can do that with Olama, and so that's another really awesome benefit to Archon

05:37And then to get started, all we have to do is start by cloning the Archon repository, and we're using the stable branch because that's where we have the official releases

05:48And so you can use the main branch if you want something a bit more experimental, but I'd recommend starting with the staple branch

05:54Then we just change our directory into Archon, and now you can open up this folder in your favorite code editor, like you can do Visual Studio Code or Windsurf or Cursor, whatever you want to

06:03Go ahead and open this up, and then we can set up our environment variables

06:06The only two values we have to set right now is our Superbase URL and service RO key

06:14Everything else, like our OpenAI API key for example, we actually set in the Archon user interface in the settings page, we'll see in a little bit

06:21And so, going to my Superbase dashboard, the way that you get these two values for cloud Superbase is you go into your project, once you have it created, go to the project settings on the left-hand side, and then when you go to data API, this is where you can get your project URL, so go ahead and copy that and insert

06:38That's for the Supabase URL, and then to get your service role key, you go to API keys, and then you want to reveal and copy the service role secret, and we want to be in the legacy API keys tab, so go ahead and fill out both of those things right here

06:53If you are running local Supabase, then usually your Supabase URL is going to be this right here, so host.docker.internal, pointing outside of the Archon container, then with the port for your Supabase Kong container, and then this service role key, you set that yourself in the environment variables when you are self-hosting a Supabase

07:12That is all you have to do now

07:14Our environment variables are set up

07:16Make sure you actually do that in an .env file

07:17So you'll copy, rename it to .env, set up those values, and now we can start the Archon containers

07:25And actually, one last thing before we spin up Archon, we need to set up our database

07:29And so going back to the instructions in the readme, we just finished our environment configuration

07:35Now we need to run our database setup

07:37And so I call up the specific file right here that has all of the SQL you need to run

07:41So you just need to go to migrations/complete_setup.sql, copy the content here, and then we'll go into our SQL editor in

07:46Superbase

07:50And so, going back over to Superbase, it's this tab right here in the top left for the SQL editor

07:54Create a new snippet, paste it in, and run it

07:57This is going to create all of our Archon tables, and you don't have to know every single table that we need to create here, but I'd recommend just going to the table editor and making sure that you see a lot of Archon tables here after you run that SQL

08:08So, awesome

08:11And this is all going to be empty now, but we're going to populate this in a little bit when I show you practically how to actually use Archon

08:18So, going back to the guide here after we have our Database set up, now we can move on to actually spinning up the containers, and it's just a single command

08:26You got to make sure you have Docker installed

08:28Once you do, it's just a single command to spin up everything

08:32And so I'll go to my terminal here back in our Archon folder, paste this in: docker compose up build-d

08:36This is going to build all of our Archon containers at the same time

08:41We got one for our user interface, one for the MCP server, and one for all of the API endpoints, and it's going to take a little bit to build, so be patient

08:49Come back in 10 to 15 minutes, and then we'll be good to move on

08:51All right

08:53Our containers are built

08:55This is what your logs should look like if everything is working well

08:58You can also verify that the three containers are up and running in Docker Desktop

09:02Then with that, we can go straight to the Archon user interface, local host port 3737 by default

09:06Those ports are configurable as well

09:09So you want to bounce right to the settings page here because you want to set up the credentials for the LLM providers that you want to use

09:17And so all these are blank by default

09:18I'll just start by using OpenAI right now

09:20So I'll save all my changes, and then I can select the provider I want to use

09:25For both my large language model and my embedding model, Archon uses both under the hood for crawling for all the documentation that we store in our knowledge base

09:33And so we have quite a few different chat providers that are available

09:36I'm just using OpenAI

09:38You can select your model and then click on save settings

09:40Don't forget to do that

09:42And then after we save the settings for the LLM, then we can go to our embedding provider

09:47There's less options here because some providers like Open Router don't actually have embedding models, but we can set each one separately

09:51I can use OpenAI for chat and then

09:54I could use Ollama for embeddings, for example

09:56So select your provider here again, set the model, and then save your settings, and then boom, we are good to go

10:02That's everything that we have to set up in the settings here

10:06And then going to the MCP tab, we have instructions for how to connect Archon to pretty much any AI coding assistant

10:12I mean, we don't have explicit instructions for every coding assistant here, but we have a lot covered, and any MCP compatible AI coding assistant can connect to Archon

10:24So, you can kind of just copy the instructions we have for one of the other coding assistants

10:27So, for Cloud code, for example, I'll go here

10:29I'll copy the single line

10:30That's literally all I have to do

10:32Then, I'll go back to my editor here

10:34All I have to do is paste this command in my terminal, and boom, I am now connected to Archon

10:37It is that easy

10:39I just get this error because I already am connected, but then I can do `claude mcp list` and this is going to actually verify my connection to Archon, looking really, really good

10:49So you just have to follow whatever process we have here based on your AI coding assistant, and then you're good to go

10:54The last thing that I'd recommend doing is go back to the settings and Copy the recommended global rules that we have for your coding assistant, so you got one for cloud code, and then one that applies to any other AI coding assistant

11:06So copy this, and then for cloud code, for example, you just go to your cloud.md

11:10I've already got this pasted in here, and then for another AI coding assistant like Codeex, it'd be something like your agents.mmd

11:16So just follow the instructions to set up global rules for your coding assistant and paste this in, and this is all you need

11:24Your coding assistant now understands how to use Archon for the knowledge and task management, and then

11:29Upgrading Archon is also very easy

11:31When there are new changes you want to bring in for new releases that we have, you just have to pull the latest changes with Git, run the exact same Docker Compose command that you ran to start things for the first time, and then the last thing is, there's a section in the settings page that will alert you of any migrations that you need to run

11:48So you can click on a button right here, copy the SQL to run those migrations, and then you go into the SQL editor, just like we did earlier, running that to get your database up to speed as well

11:57That is it, very easy to upgrade

11:59So with That, you have Archon fully set up

12:01Now, a quick word from our sponsor, which is very thematic for Archon, by the way

12:05Then we'll get on to how you can practically use Archon in an AI coding workflow

12:11I'll show you how I approach a brand new project, how I incorporate Archon into it

12:16The sponsor of today's video is none other than Superbase themselves, which I am pumped for because, for the longest time, they've been a core part of my tech stack and the database that powers all of Archon, very thematic

12:26They recently had their first ever conference, Superbase Select

12:30That's the video you're looking at

12:31Right here, it's the full recap, which I'll link to in the description, and their CEO, Paul Copplestone

12:37He kicked things off by introducing a lot of incredible new additions to the platform, starting with a remote MCP server

12:43I've been waiting for this one, so our agents can manage our Superbase projects without us having to install anything

12:49And then a lot of new things for scalability, enterprise level in particular, incorporating S3 buckets, Oreo, which is a platform they just acquired, and a new open source initiative for database orchestration called Multi-gress, which is probably the biggest

13:04thing for making Superbase that much more scalable

13:06I really do think that Superbase is the future of Postgres

13:11When they say scale to the millions, they really mean it

13:12And the biggest takeaway that I got out of this event is that they understand the limitations of Postgres as the underlying database, and they're addressing that by building things on top of the Postgres engine, while still making it just as easy for us as the end users to leverage Superbase

13:28And with that, they've got their series E for a $100 million raise and a $5 billion valuation, which is extremely impressive

13:37And last thing I'll Say, if you really want to dive into multi-gress and see how that makes Superbase so scalable, Sugamarine did a talk right after Paul Coppstone where he covers more of the core architecture, so if you want to get more technical and see how Superbase can really scale, definitely check that out

13:54And really the whole recap is worth checking out, so link in the description

13:58I am always behind Superbase and I love it as a platform

14:02So, this is probably the most important part of the video, showing you how to use Archon in an AI development workflow

14:09And the main point that I want to drive across here in the Next, like five minutes that I've got with you, is that it's up to you to define your own AI coding workflow and how you want to incorporate Archon

14:20There's a lot of flexibility here

14:21I'm going to recommend a couple of commands that I have for reusable workflows, but you get to decide when Archon looks in the knowledge base, when it manages tasks, does it create the projects? Do you create the projects for the coding assistant first? That is all up to you entirely

14:37And so when I am starting a new project or a new feature in an existing project, the first thing I'll do is set up my knowledge

14:44What are the files? That I want my coding assistant to reference, or the documentation that I want it to search through? For example, maybe I'm building an AI agent with Pantic AI, or I'm working on some backend that's using Superbase for the database, and I want my AI coding assistant to be able to search through this documentation to understand how to code with Pantic AI or with the Superbase SDK

15:06So find those resources, and what you want to do is you want to go to the documentation

15:13So for example, I can go to Google here, and I can go Superbase documentation

15:15There we go

15:18I got the Superbase docs, and I can actually start by just

15:22Crawling this if I want to

15:25So I can go to Archon, click on add new knowledge, paste in this URL, and start the crawl for any old website

15:29This works

15:32However, there are a couple of formats that are actually more optimal for crawling

15:36So going to Supabase to the documentation here, if I go to llms.ext, text, take a look at this

15:44Most documentation websites, if you just append llm.ext to it, I can do the exact same thing for Pantic AI

15:50It has this curated list of files that are ready to be ingested as markdown for your AI coding assistant

15:58So, I'd highly recommend looking to see if your documentation has That, and then if it does, copy this, go into Archon, and then crawl this instead of just the raw web page

16:10I'll actually start the crawl here so we can see this in action

16:14Another format that's really great is sitemaps

16:15And so Mem Zero, for example, which is a tool for agentic memory, they have a sitemap

16:21And so I can do just /sitemap.xml

16:25This is typically how you check for a sitemap

16:27This is also a very good format

16:29So I can copy this, go into Archon, add this knowledge, start crawling

16:31Boom

16:33There we go

16:34And you can crawl in parallel if you want to

16:36So now we're crawling both the MEZO and Pantic AI

16:41Documentation at the same time

16:46And once this crawling is complete, our coding assistant, through MCP, will immediately be able to search through everything that we brought into our own private knowledge base

16:51All right, I have both of my documentations crawled now, and I can also click in to view the different chunks and the code examples that we're able to search through with the Archon MCP

17:00And again, these can be any URLs that you want to crawl

17:03I would recommend generally sticking to library documentation, especially with the sitemaps and the LLM.ext, but it is quite flexible

17:07There's a lot

17:12That you can bring into your Archon knowledge base

17:16So, we've got that set up now, and we already have Archon connected through MCP

17:20Now, we can dive right into coding something

17:23Now, when I am creating code with an AI coding assistant, I always split things up between planning and implementation

17:30I even have a full video that I'll link to right here where I go through my general process, and there's this really nifty Excal diagram that I have going through how I plan things out and then how I implement it

17:40And I don't do all of this from scratch every single time

17:47I take my general process for planning

17:50I Package that up into a markdown document that I have as a reusable workflow

17:54You can take this as a starting point if you want

17:57I'll have this linked in the description as well, but I encourage you to take my general ideas around planning and executing and actually build your own workflows

18:06And that's the thing with Archon, is you get to customize how you leverage it in your workflows

18:13Like for example, I have step one, read and analyze a requirements

18:15So there's a specific file that I pass in, which is just what I want to build

18:19And I have a really simple request for this demonstration purpose

18:24I just want To build a panenti agent that uses mem, so obviously it has to leverage both of the pieces of documentation I have in Archon

18:31So I have it understand the requirements first, and then I have this little research phase where it lists the different sources that we have crawled in Archon, and then it performs RAG to look through the different chunks and code examples that we have there

18:43And then I do codebase analysis if it's a feature in an existing codebase, and then I have a plan and design

18:49I don't need to cover this whole markdown because the point I'm trying to drive home here is I just fit Archon into some

18:57Part of my planning process, and you can customize this to however you want your AI coding assistant to use Archon

19:01And then I'm going to do the exact same thing for the implementation phase

19:05I'm going to take my general process, package it up into a command that I can execute as a reusable workflow

19:12And this one specifically speaks to how to leverage the projects and tasks within Archon

19:19So, I tell it to look in my global rules because this is where I'll specify any existing projects in Archon that I'm working on

19:25If it doesn't find one there, then I tell it to make a new project and then manage all the

19:30Tasks

19:32So, create new tasks for each of the things that it's doing to knock out my implementation for me

19:36These are the kinds of things, again, that you can customize to however you want to use Archon

19:41And I'm going to keep saying that over and over again because that's the main point that I want to drive home here

19:44And so, I'll show you

19:48I actually ran the create plan already on my simple request for the Pantic AI agent

19:51And here we go

19:54It's using RAG, uh, in Archon to search through the chunks and the code examples

19:58It's doing quite a bit of analysis here

20:00This is looking really good

20:03And then finally, after it

20:06Reads through all of my documentation that it thinks it needs, it builds the plan for me

20:09So, I go into the PRPS folder

20:13This is a very simple version of PRP, by the way, if you followed my other content in the past

20:16But yeah, take a look at this

20:18We have this full implementation plan with all my research findings from Archon

20:21It's got the different tasks that I wanted to knock out one by one

20:25So now when I go and actually execute this plan, we're going to have all of these tasks created and managed in Archon

20:29It is a beautiful thing

20:32So I'm going to come back once I have everything executed

20:36I'll show you how

20:38That worked as well

20:40All right

20:41I just wanted to come back mid-execution really quick to show you that I executed my workflow

20:43It's starting a new project and adding a bunch of new tasks, and so we can see that here

20:47It created a brand new project in Archon

20:50The nine tasks that I had in the plan that I created, it converted into Archon tasks, and it moved the first one into doing to set up the initial project structure, very, very nice

20:59So, not only is it easier for us to manage the tasks for our coding assistant in Archon, it also gives us a lot of observability into what's happening

21:06We can even click in to see

21:08The description to kind of see a little bit of extra details of what the coding assistant wants to do for this specific task, and again, we can always edit this to change the instructions live

21:16We can add new tasks if we think it's missing something

21:20We have that flexibility to edit things live and again determine the workflow in the markdown document

21:25So I'll come back again once we have the final implementation

21:30Okay, our implementation is complete

21:32I just cut it short of the validation here because it's not the point to have a fully complete solution in this video here, but yeah, it's got all the

21:39Tasks in review

21:41It was just about to create the tests and then move everything into done

21:44So the Archon integration for the project management is working perfectly

21:48And if we look at the code just really quickly here, I can see, and I, I checked this off camera already, it's looking really good

21:54Like it clearly understands how to build Padantic agents, how to work with the memories with MemZero

21:58This is the kind of thing it would not have been able to figure out without being able to look at the MemZero and Podantic documentation because LLMs have the notorious training cutoff

22:08They don't understand

22:10These libraries, and that's why we need RAG with Archon for it to write accurate code, and it definitely looks like it did

22:17So yeah, at a high level, that's how I use Archon with my planning and my executing

22:22Build these workflows yourself, take inspiration from this if you want, because again, I will have these linked in the description if you want to use these slash commands, and slash commands are just prompts

22:32And so no matter your AI coding assistant, you can tell it to look at this markdown document and execute this operation

22:38You don't have to use cloud code like I'm using in this demo, it is just my

22:42Preferred AI coding assistant right now, so that is everything that I have for you, my friend, on using Archon, a full guide with the setup and how to incorporate it in your AI coding workflows

22:52I definitely want to be putting out a lot more content on my channel in the near future as well, diving even deeper into incorporating Archon into building full projects end to end, so definitely stay tuned for that if you're interested

23:05If you appreciated this video and Archon, and you're looking forward to more content on AI coding and using Archon, I would really appreciate a like and a subscribe, and with that, I'll See you in the next.