Gaia, A Decentralized Ecosystem to Support AI Applications

GM GM! Welcome to what's going to be another great episode of DevNTell. So if you didn't know, DevNTell is a 30-minute podcast held every week, allowing founders, hackers and anyone in between to come on the show and tell us about their product. And today, I'm ecstatic to welcome Sushmita and Toby, who are DevRels from Gaia. So if you didn't know, Gaia is building a decentralized ecosystem to support AI applications that learn, improve, and grow over time. So if you stick around for today's episode, you'll see Sushmita and Toby give us an overview of Gaia, what features it packs, and how you can get started using it today. All right, let's get into it, but first, a word from our sponsor. GM GM, welcome to the show Sushmita and Toby. Pleasure to have both of you on today.

GM. Super excited to be back here. And yeah, this is one of the OG shows from Developer DAO that is the longest and still running till this day. Indeed it is, indeed it is. And yeah, as long as people keep building really cool products, there's always going to be a stage here for them to showcase it. And yeah, Gaia is certainly an interesting one at the intersection of AI and crypto. So really excited for this one to hear basically learn about it. But before we get into all the great content you have packed for us, why don't you give the crowd an introduction for yourselves in case folks aren't familiar. Okay, I can go first. GM GM, this is Sushmita. I started my web3 journey from Developer DAO, then I joined ConsenSys and I was on the rapid application development team or DevRel team later. And now I'm at Gaia. So Gaia is a decentralized AI infrastructure. So yeah, we're going to talk about that, but as this is I love building and talking to people and how I can help things easier as a DevRel. So yeah, I'll give the popcorn to Toby.

All right, hi everyone. I'm Tobiloba and I'm from Nigeria, Lagos, Nigeria and I'm first time here on DevNTell. Excited to be here. Sushmita has told me a lot about this podcast and this show, so it's actually an honor to be here. My journey started my journey in tech started like in 2022. Learned to code, learned to build on the front end mostly, because that was what I used to like learn how to like actually write software. And then from then on, it progressed into open source. In open source I did a lot more things, made a lot of friends. Sushmita is one of the great friends that I made from contributing to open source. And from there it sort of like sprung into me now building an AI agent, you know, building on the blockchain and you know, building in web3 because with open source you never stop learning. So as you build you learn. So that was essentially the process of how I you know, was able to delve into these tech spaces and me now working in web3. So yeah, excited to be here.

Yeah, amazing, amazing. and yeah, thank you for the kind words. I was telling telling you both before we went on, as long as people keep building cool products, we'll keep having this show. and I suppose from all your contributions from open source, Toby, as well as yourself, Sushmita, I know you're a big open source contributor too, like what made what made both of you kind of stick to web3, like what what keeps what keeps you both in this industry?

I think I can go first. It's like when we first joined Developer DAO, it was all about learning and building with friends. So it was like we joined here for a movement, like web3, we want to build with friends. And I think we stayed for me, I stayed for the community. All the friends that I met along the way, like and having to wake up every day and build something exciting is really fun. And if it's with your friends, it's it's more fun. So yeah.

Yeah, great answer. Yeah, for real. sorry, the question was why could you repeat it? I'm trying to like rephrase my response. So yeah, you do a lot of open source contribution. You can choose to do open source contribution for a regular web2 project or web2 projects, but you specifically stuck with web3 and found yourself at at a company that does web3 and AI. Like what what made you come to this industry and made you stay?

Oh yeah, as with most of the ethos of like open source, you realize that open source sort of like prioritizes you know, collaboration, it prioritizes community and it also prioritizes you know, perspectives. If you think about open source it's just a gathering of people with several different perspectives that are you know, coming together to then build something beautiful. Or maybe not beautiful in some other cases, but at least as long as it works, you know, you use it. Um so yeah, that sort of like perspective just like you know, drew me a lot more to web3 because with web3, it seemed like super niche. It was you know, it was very complicated. A lot of people didn't know how most things worked there, me included back then. But then I was like um yeah, why why would any technology be complicated? So my goal in web3 since joining has always been like you know, tend to like always you know, with every day, to like lower that barrier and be like, okay, this is just another software stack that you should learn. It's not something that you should you know, break your brain over. It's just something you can still use it like every day life and um you don't even have to know like the blockchain is powering this piece of software. You just have to know that, okay, you make a call, you get a response, you send your regular you know, HTTP request and you get a response back, maybe you are calling a protocol. So yeah, you know, those things just sort of like, yeah, I mean the fact that it's niche and um the onboarding um is something that I think needs a lot of work was one of the things that sort of drew me to it. and then you know, AI agents just sort of like came along the way because I was like I mean the Eliza boom sort of just drew everybody to AI engineering, I guess. So yeah, indeed, indeed.

And and yeah, I was going to also say like um web3 has its own um complicated rabbit holes to go down. Um and AI is like a whole another a whole another rabbit hole in itself. Yeah. So what in particular made both of you gravitate towards Gaia, as we mentioned a project that is both at the intersection of of web3 and AI.

I think I can maybe take a lead on this. then I know Toby also might have something to add. I think what drew me in about Gaia is that okay, let's let's talk about what Gaia is first. Gaia is decentralized AI infrastructure. So what do I mean by that? So think about this in a centralized our centralized AI is like ChatGPT. If you don't pay for a month, do you have access to all the premium features? You kind of don't. That's that's not something you own. And what drew us towards this web3 is the ownership of it. And that's how we I for me, I also drew towards like Gaia. Okay, this is this is my AI, this is my data and this is all I could own. And I could train it however I want. It's not going to be biased towards anything. It's not going to be like have these own sets of data that just comes within or even take my own thing. So with this it's it's my own AI that I could have as long as I want and no one can access it. It's it's the privacy, it's it's the decentralization, it's it's all the parts of it that drew me in for me. I would give popcorn to Toby. I know he has something to add.

Yeah, so with Gaia it was actually a very like fun story, to be honest because I actually found out about Gaia in this you know, small community of ours that we call Acuru. So the idea behind Acuru was that we wanted to actually build you know, actual open source AI. you know, like not not not as a brand name. So um so then we sort of just started the idea and then you know, decentralization came in because I mean most of the folks there were like were web3 folks. So um put web3, then put AI together and then you start thinking how can AI run on decentral decentralized infrastructure, how can AI guarantee data ownership, and how can AI guarantee you um you know actual earning um would I how would I put it, actual earning you know, incentives such that you are able to use your own knowledge to be in a sort of network of or a system that you are able to use information to exchange or something like that. So um Gaia just sort of ticked all those boxes for me because finding out about it and then I found out you can actually still then use Gaia like every other regular um how would I call it, every other regular like um inference provider, but now it's actually on decentralized infrastructure, which means that you have some access to like parts of the blockchain and then you can also still like you know use it for a lot of on-chain things. Um so it was just like um yeah, like honestly this is like the this is the the perfect combination of of tech. So I was like yeah, this is dope something I want to be a part of and then the Gaia sort of would I put it, the Gaia sort of weaved then moved along and now I collaborated on Gaia with a few you know, sort of side projects and here we are today. Amazing, yeah. a wonderful answer and certainly open source AI is um is pretty wild. Like once you start actually like working in the working in the space and like exploring all the different tooling and um open source versions of closed source software that folks are making. Um it's it's really really awesome. Basically you can you can run a lot of the AI um like a core set of AI um either locally if you got the hardware or um if you don't have the budget for the hardware, you have these decentralized um AI networks like like Gaia and all the other ones um to to kind of help you out. And um I think this is a good segue um to getting into the content you have prepared and and basically give us a a rundown of what um all the all the neat features that Gaia packs in. So Toby should I bring up your screen?

Okay, so why don't we go to our network map first. because we recently hit like 600K nodes. Uh yeah, for sure. Network map. Yeah. It's coming up. Yep. There we go. Yeah, we recently hit like 600K nodes and like throughput over yeah. We're going to hit maybe 700K soon in this 600K 600K nodes I mean it was like 611K yesterday. 611K yeah, now it's 659. So I'm guessing 700K is going to be super soon. So everybody is actually like you know putting more knowledge to the to the network, people deploying nodes just makes us sort of see um you know that momentum just gives us the uh the energy to know and and it gives us that assurance to let us know that okay, people actually value um what they see in you know what they gotten to experience using decentralized AI. So definitely a motivator there. Awesome. Now let's dive into our docs and let's talk about what we can do builders can do with Gaia and yeah.

Okay, so as I mentioned earlier Gaia is decentralized computing infrastructure that lets everyone to create, deploy, scale your own LLMs and you can use that for AI agents or for anything. So for me, what can I do with Gaia? I can go ahead run my own LLM node and I can train it with my data but for example, if I'm running a really smart LLM, it doesn't it's not going to have some context unless I give this LLM some knowledge base, some RAG models and then it has all this context and it can go through it. So if you click on for devs, Toby. Yes, and then setting up your own node is the way to go, where we have some system requirement. We kind of ask for like 16 16 gigs RAM at or if you don't have any GPU or like it's just CPU um I think like can we pull out our node config repo first and I just want to show all the LLM that we have.

Yeah. So this is like all the LLMs that we have so far. So now there are all the time we get questions from devs like which node we we should start running. So let's say if you have like a computer that has no CPU or no GPU but only CPU, we suggest you to run like maybe smaller models like really small like three billion parameters or something. But if you have 16 gigs RAM or like any Mac M1, M2 or anything, just go ahead and run something like eight billion parameter models. So before we jumped onto this call today, we were helping a dev to building his like own smart wallet application and he was facing some problems with tool calling with one of his application. And our main suggest was to run this Llama 8 Groq tool, that one. Tool call. Yeah, in so this so also like there are some times there are some devs who go who doesn't know this system requirement and jump straight into 70 billion parameter model. And that sometimes starts down that whole system. So yeah, be careful like I I never run any any LLM that is over 8B yet. I've only run like eight billion parameter models. So that is where like if you have like 16 gigs RAM and a MacBook I would suggest running. But yeah, like Llama is really good, one of the best LLM that I have been running a lot. There's also like Qwen, there's also like Mistral that is good for tool calling and of course there are DeepSeek and bunch of others. We will share all this node config link with Narb so that anyone can take a look at that. So yeah, this is one thing. And now let's go back to our docs as we have already talked about all the LLMs. Let's see docs.

Awesome. So as you know, as we already have these options, now you can go ahead there are three ways there are only three step for you to run your own node, this just you just install the GaiaNet CLI, you pick the model and go gaianet init and then it's just gaianet start. That's it and to stop it it's just gaianet stop. It's just only three step and um if you want to update your like knowledge base, there's option for customizing your Gaia node. That's how uh you go from there. It's over here, yeah exactly. Customizing your Gaia node. So but let's say that you want to give your node we we kind of give it like some pre knowledge base just to get started with, but let's say you're like no hell no I want my node to be clean, I want my node to be a super smart freaking intern about web3 and DeFi, I want to do my own thing. You can go to knowledge base Toby, can we click on that? On the left. Knowledge base section. Yeah. Then you go to knowledge base and create your own knowledge base and you config your model with that. But let's say that um yeah, you can uh to create a knowledge base there are like multiple things to consider, you can start your you can like update the RAG prompt with TXT file, maybe a Markdown file, maybe PDF, maybe CSV, whatever works best. So it's right up to you. So and we already have videos and like we kind of try to keep all the clear docs for this. We also have a section for all the examples and like what is it called, templates. So we kind of keep we kind of keep building these agents and templates. So to showcase like our Gaia's capabilities. and um yeah, we also have this live stream every week or something where we build agents live to showcase like how Gaia could work. And all that. So yeah, this is like all the minimum way to explain what we could do.

But also let's say you are a dev, you don't want to run your own node, you want to try out Gaia, for that case we have our public domains. You can get Gaia API key, which is if you have uh you have to connect your wallet and like you will just connect your verify that with your email. We will give you 10,000 credits for that. I think Toby is kind of showing that like how that would work. So we will give you over 10K credits, which you could use and for application. So when you run a Gaia node, it comes with this uh link. Uh let's see yeah, there is your API key, you can apply for developer free trial and we'll give you 10K credits right over there. And you could use that. So you might be thinking, okay, Gaia is difficult might be difficult to you know, like configure into your application. This is the fun part. When you are using Gaia, you don't need to have some different sets of code or anything. You just swap out your just like how you are going to use OpenAI config. Like instead of the URL, you just put Gaia's URL and then for the API if you're running your own node, you don't need any API key. If you're using one of our public domain, you need some API key just just so that no one like abuses that. So yeah. So this is like one stop all the explanation. so I'm open to questions. So if we go back to the nodes section for people who want to run nodes, are they only able is the node only capable of running one model at a time?

So it depends on I think is it one I think there's option to run multiple node, but uh it's there's a problem with hardware requirement. Most people do not meet the criteria for that. So we all always love to work with the multi agent models and all this, but it's the hardware that kind of stops us. Yeah, it's always it's always the hardware and like and when you were saying oh people want to jump straight into the 70B models, like they don't realize you need like quite a bit of RAM and/or VRAM um to run that. Um even even on a local machine. Um yeah decentralized compute networks like this are really um really helpful for for folks who don't have the money to spend on um like three or four 5090 4090 cards um just to be able to run a 70 billion model.

And as you mentioned, you also make it accessible through an inference API. You mentioned that people get 10,000 credits to use against that. is there also a paid tier if people go over that or or how can people basically pay for more um more use? So we are not uh currently there's no way to pay for any, so we're not it's we're not monetizing that. So we are mostly focusing on running the node. So there's some fun part that uh Toby do you have any node running currently? I can stop my local node, but just give me one second. Okay. But you can continue while I stop my node. Yeah, so there's fun part is that when you run your own node, it gives you a link which even I can interact. For example, if Toby is running a node, he can give me the like link and I can interact with it. It's it's not only local it's it's not totally local. Even you can interact with it, anyone can.

So but this node address kind of comes with uh I think there he goes, kind of comes with this string of address just like wallet address. And that's that's the fun part is that we have Gaia domains which lets you uh just like for wallets, we cannot identify whose wallet this is unless we have some ENS or something. That's what Gaia domains are, but for our AI nodes. Gotcha, gotcha. And we have we have multiple domains listed on our website that anyone can go and try it out. A lot of people are running. But yeah.

I want to bring up the um the chess the chess domain Sushmita and I worked on for our stream that we did on Saturday. So like she was saying um you can actually totally run any of these nodes um on your own, you can even deploy them as domains and um the fun part about domains is that you can have a domain that um you know sort of acts at an interface for your node or acts as an interface for a bunch of or a cluster of nodes. Meaning that with that with a specific domain, you can create like a sort of knowledge expert or a sort of um you know super contextualized LLM embedding for any model or that we have currently running on Gaia. and what I mean by that is that say you are somebody that is trying to you know, you have your company's products currently running. Maybe you need like a sort of AI agentic um sort of layout to your product. You can come to Gaia, make your own domain deploy your own Gaia domain, give it a ton of give it a maybe a bit of context here and there, have a bunch of nodes running there, and you can sort of have this domain serve as the you know soft of truth you know, for your product. You can integrate that domain in any product you want because it has an LLM that runs with it and it also has your embeddings that you've created. Like Sushmita mentioned earlier to um you know sort of grant you that ease of access. You don't have to always train every model every time whenever you are trying to use it in a product. It's just you know one API call um because you already have that sort of backend service that is powered by Gaia. Like like she was saying exactly she was saying. So um you can share my screen again. I don't think you're sharing. Okay. let me share this let me just share this window first. So um Sushmita you want to continue?

Okay. Yeah. So yeah, so yeah, this is like where okay. Give us the link so that we can interact with it. Okay, awesome. Uh that's the link or you can click on that and show us. So this is like we kind of customized one of our LLMs to be a chess expert. So this was for one of our like chess agent that we built live the other day. And if he gives us the link, we all can interact with it. It's it started. I think the demo gods are trying to get that to me. We happen to here. It's it's almost a tradition that has to break. Uh this is uh what can I what can I change here? Same URL, let me stop and start it again. could be something um so yeah you can just stop and you can your nodes. You can continue Sushmita I'll just stop sharing.

Yeah, so I think like the way you see when he started the node it it comes with all the strings and then gaianet.com gaianet.com. So when you have a domain, it can be, okay, DevNTell.gaia.domain. It can be just one source of truth with this and like anyone can identify that. You can have things private in like living on your place with data safety and all of that. So yeah. I think that's the whole point we were getting at. But yeah, if you have any other questions.

Awesome. Yeah, it looks like um there's a lot of great um content you both um have prepared for a lot of devs that might be watching today who want to get started with um Gaia. I guess from all that you've seen are there any particular AI agents or any applications that have been built with Gaia that have kind of caught your eye and you're like oh that's cool or um maybe something you wish people would build with it.

Yeah awesome Gaia. Yeah, we have this repo for all the cool projects that comes within. Let me share the link with you, which is called Awesome Gaia. So all the cool projects that people are building in the community or us building we add into it. And I think one of the greatest cool project that I have seen when I before I joined Gaia was this search agent that searches and like gets all the answers. And then you kind of like get all this so it was kind of before like the deep research came into the picture. So this was kind of fun to see from that point. And then there we had these what are the other other agents that we have? Bunch of agents we worked on. So Toby do you have any other favorite?

I think um PR review, Acuru Search was definitely very cool. So Acuru Search had this kind of um perplexity kind of um vibe where you can use where like you have an inferencing layer that you know behind that Gaia is powering. Um somebody called um a very great developer worked on this. So he sort of created that sort of Gaia layer that powers this. And then he added some tool calling capabilities to the agent such that with Gaia it can also use Gaia's inference to get that information, you know parse it and digest it and then give the user back a response. And on on this note this is also a very nice segue to mention the integrations that Gaia has. Um there's integrations with Eliza, currently integrations with um LangChain, integrations with um LangGraph, integrations with um Cursor, even your your IDEs you can integrate Gaia there you know instantly and you won't have to do anything too crazy because Gaia has an OpenAI compatible API. Eliza.gg also was built I don't know if you saw it you used Eliza.gg at the time when it was like very live when it was live then a lot of people were using that was Gaia powered. So um yeah there's so many of these projects that are up here on like um the Awesome Gaia repo that people can come to check out and you know test. Agent kit also from CDP and DTK there's several other integrations uh that Gaia currently has at the moment and um and projects that you can you know build and scale using Gaia's infrastructure. Yeah.

Also like this is maybe one of the perfect time to mention Gaia node currently have MCP support now. So you can also have MCP to do bunch of work like because MCP is like super this layer because we don't have bunch of tool calling you just go ahead it's just it's also Open MCP just using that with your node and giving this agentic capabilities to do bunch of stuff with it. So just wanted to mention that. I was going to ask you about it, but that's good. Yeah, that's good you brought it up.

And I guess for people who um might be starting to learn um like AI and Gaia or or what have you um for the first time like what would you recommend them as a good starting point to starting to use Gaia? Um like is there a particular Hello World template or something that you can recommend?

I think I would highly suggest is to go through our doc and trying to understand how you can set up your own node because just like we mentioned Gaia is all about open source decentralized AI or LLM that you can use and like into your application. So try to see how you can set up your own node, have your own perfect intern in your computer and then think about what you can build with it, what you want to automate or agentify with that. So I would suggest that's how to get started with.

Awesome, awesome. and yeah um folks who are watching um this today or whenever, um we will have links um for all of that in the description below. Um so definitely um you'll want to check that out. and um I guess before we we end off, um I'm just always curious to hear um from from the folks who are building in the space like um from both your perspectives, um what do you think is are some of the most interesting and or important trends um that are being built today or will be built um at this intersection of of crypto and AI.

I think we can all agree that MCP is here to stay. So that is one of the thing because when you see this one tool calling for this other tool calling for that and then we have this MCP doing bunch of layer a layer for bunch of things. This is something here to stay. Also I'm a really advocate for Zero Proof Knowledge ZKP and stuff. So I think these are the thing that are here to stay and you know just all general web3 stuff. I'm always advocating for web3. Yeah. also um agentic networks um what do I mean by that? Um think decentralized networks that index AI agent, AI agents executing on tasks, AI agents delegating tasks to one another, AI agents paying each other for tasks that that they've worked on or something. It's sort of like an Internet of Agents. That's something that uh I definitely see um you know part of the community drifting into um in terms of you know web3 and um yeah decentralization. Also like I think we can all agree that web3 UX still kind on a difficult frustrating position. So it's not that we need really cool UX or something maybe the agents could fix those and for the mainstream. Yeah exactly exactly. Just get just type oh I want to get started with Ethereum and the agent makes your wallet, it teaches you exactly funds funds with your credit card, bang, ready to go. Exactly.

Yeah, yeah. Um I'm waiting. I'm waiting for um for that moment because it doesn't look like anybody wants to solve the UX problem in crypto. Um but anyhow that is a show for another another day. um but uh with that, um unfortunately we've come to time. Toby, Sushmita, thank you again so much for taking the time out of your day um to give us that wonderful overview of Gaia and um looking forward to seeing people build um their own projects using that. Thank you so much for having us. Super exciting. Thank you for having us. My pleasure.

And before everybody leaves, um those of you watching us live, I've dropped a link to um in the chat for you to go claim your live attendance badge um through Bit Badges um for watching us live. Um so if you're into digital collectibles, um definitely check that out. You'll have about an hour or so to be able to claim that. and with that, I just want to wish everybody a very happy Friday, happy weekend wherever you may be and we will catch you back here for another great episode of DevNTell next week. All right all, have a good one. Bye!