SAFE Network & AI case study : SpaceGPT app

I followed the recent discussions about AI and SN potential symbiosis. It’s super interesting but a bit too abstract IMO, and I’m not sure where we’re heading!

So I have a concrete case-study for you guys.

Here is a little early demo / MVP I have been working on lately, fully GPT-based : (name not definitive)

Small preview if it doesn’t work properly for you :

For now I call it a “knowledge exploration” tool. It’s the first time I show it publicly, so if you like the concept and want to help my team and I make it a really useful product, then feedbacks are more than welcome ! Shoot me a DM here on the forum, or even join this discord I just created :smiley:


I want this work-in-progress product to give highest quality content possible AND be super accessible to everyone, no need for an API key or to know how to set up a local LLM.

At the moment I think for it to succeed, it has to be quite centralized because of some technical constraints or “business” needs to achieve the goal :

  • We need very high quality GPT / LLM content. Possibly several fine-tuned models for each purpose instead of relying on shaky prompt engineering. Today these models couldn’t be run locally on everyone’s machines. I’m confident that will change fast but for now and for at least a year I don’t see a viable business model without a monthly subscription, or at least a freemium model, to cover both the high quality LLMs API costs and a fast-paced development cost.
  • We will need people to share their exploratory data & feedbacks as much as possible to know what topics / concepts and questions people are interested in, what answers are deemed satisfying etc. so that everyone can benefit from it, by eliminating noise and provide exploration recommendations for instance. We can’t just rely on the base LLM models for that. Foundation models LLMs are of course not trained to show you what you could be interested in. So we would need to train & use centralized & opinionated machine learning models for that, at least in the beginning.

But now let’s say it’s 2024 and people like the product, it has all the essential features, great UX, we have good enough models that could run on (some) people’s machines and I want to make it 100% decentralized as soon as possible, because I believe this kind of tools should be as decentralized as possible. Like wikipedia or the internet archive or any frequently useful tool benefiting everyone (looking at you Google search).

And let’s say I just discovered the SAFE Network and I want to give it a go! (Actually I’ve been lurking here since 2014 xD). I’ve laid out the key questions / doubts I have around SAFE Network’s ability to help me achieve full decentralization on this specific SpaceGPT tool:

  • Data Decentralization: How can the SAFE Network help manage user data, so privacy is maintained while also allowing users to share their exploration data in a granular way if they’re okay with it, to improve the LLM’s ability to provide relevant Q&As for everyone ? That’s probably the easy part but it’s not so clear in my head yet. And would data retrieval be fast enough ? Would people have to pay for each little update to their exploratory data ? (Yes as far as I know. Is it a problem for adoption then ?)
  • Compute Layer Capabilities: With SpaceGPT demanding significant computational resources for LLM operations, can the SAFE Network’s compute layer provide the necessary support? Will people have to pay for it ? Would it all be working automagically without having to set up anything?
  • Name Resolution System (NRS): Can the SAFE Network’s NRS system facilitate efficient, user-friendly access to SpaceGPT? Even having to download a specific browser would severely hinder adoption I think. But I understand this could be inevitable to achieve 100% data safety. And as a side note, decentralized DNS-like system doesn’t look very important to me, at least for now, and I’m afraid it would inevitably end up almost as centralized as current DNS system. It’s just a DNS market reboot after all, but managed by SN (much better, but still…)
  • New Business Model: How can we transition from a subscription-based model to a decentralized one, without compromising the ongoing development and maintenance of the app? Of course I could just open-source the code and let the project live. Why not. But that wouldn’t necessarily help this specific product be more useful and accessible to everyone in the long run. Is “Pay The Developer” SAFE Network feature still planned ?

And there are probably many other needs and considerations I didn’t think of.

So will the SAFE Network help developers / entrepreneurs achieve all that easily at some stage ? At least that was my hope when I first discovered the SAFE Network project.

And the other question is when will each stage arrive after base data layer MVP release (maxwell?), but we all know from experience that we shoudn’t try to answer that! :zipper_mouth_face:

My feeling is that if we don’t have all these pieces ready, then fully developing a data and compute heavy app on the SAFE network will not appear obvious to devs.

Maybe partial decentralization – data-layer first – would be easy with SN and would already bring some great benefits for this type of use case ? Could we easily combine SN full data handling with centralized API / server based computing waiting for the SN compute layer to be operational ?

I guess for most questions it’s just a bit too early to tell with 100% confidence ¯_(ツ)_/¯

But we’ll soon figure out! Bravo for the fantastic work team MaidSafe !


To me this is key, get that right and solid and we are on a great path with a working product (everything changes). Add in messaging and I do hope to speak more with simpleX on that front. It makes a ton of sense if messaging is secure and anonymous in parallel to a data network of the same vision and goals. With 2 separate networks it just adds to functionality and security. I.e. Spend DBCs on SAFE (so essentially create the DBC to give your pal etc.), Send them in simpleX on another disinct channel (and protocol).

The planets of decentralisation are aligning and hopefully staying very simple and secure.

Then …


A copy or export button would be great.

Is there a way I could quickly add results from a search or exploration to my own knowledge nodes?

Have you looked at ? It’s been around a long time but is primitive in many ways. It could have much better integration with other tools. It should be able to parse wikipedia. With the addition of SpaceGPT it would allow one to build out their own knowledge database quickly. Find what they are looking for and connect it with what they currently know.


I didn’t understand at first but I searched on the forum and saw you posted this 4 days ago about SimpleX : Messaging layer for SAFE and beyond?
So messaging / instant communication wouldn’t necessarily be handled on the main data layer of the Safe Network. Ok I’ll look into that !


I found out about thebrain just a few days ago :smile: Yeah I think it’s too complex for most people. But I saw they added a GPT based “thoughts” generation tool recently.

And yes exactly, the end goal would be to have a super easy and complete personal knowledge management tool. But the best path to achieve that is not perfectly clear yet.


There are many sample configuration on that might give you some ideas as to how you can

many of the examples are built by people who are trying to make their software more useful.

I’m looking forward to see what you come up with. Thank you for the effort.


I’ll definitely have a closer look at that, thank you. Another great inspiration is Obsidian, very powerful as well. But both these tools have a create-first then expand / explore approach to second brain building, I’m leaning more towards an exploration-first and then refine / edit approach, if that makes sense. Not the same audience probably.

Great I’ll keep you updated then :smiley: !


Obsidian. Obsidain? Ah, did have a look at it once …

Did not get it at first but SpaceGPT is in fact a “notetaker”-inspired idea?

For the record, there is a plugin available for this other, say conventional Joplin-notetaker, called ‘Jarvis’:

Edit, followed one of his links later on, maybe of interest too:

Well what I really like and find powerful on obsidian is the nodes graph, that you can use to connect all your notes together. But overall it requires a lot of work and maintenance to keep it useful. I think LLMs could allow to do something similar but with ease. But there would be some drawbacks of course. For the note taking use case I feel you can’t get any better than Obsidian or Notion.

But for knowledge exploration (and hopefully organization + memorization) I feel like there’s tremendous potential with these new models :slight_smile:

For now I’ll focus on the exploration use case and then we’ll see !

Super interesting thank you! In the same vein I would love to have a browser plugin that would convert any web article or youtube video to a knowledge graph automagically. Shouldn’t be that difficult to develop :thinking:


I have been thinking about graphs for my Avatar personal memory store for a while - haven’t made any progress though . .

1 Like

If anyone’s bored (already waiting for next testnet after RewardNet!) I just released a first beta version of my app :grinning:
Would love to get some of your feedbacks → (


Well its not wrong, as such - but the advice contains the phrase feared by all home mechanics
assembly is the reverse of disassembly” which is , as always, a damned lie

1 Like

That’s an interesting use-case :laughing: Yeah for super precise & practical stuff like this GPT is not super useful (except for code!!). Or maybe combined with some docs found on the internet!

I’d have the answers automatically expanded rather than making the user expand each one. Maybe collapse them if there is not enough space to display the results.

1 Like

I’ll be honest, I just tried to think it might struggle with…
God knows I struggle myself with rebuilding these carbs. I have two in bits right now with all the fiddly bits in the ultrasonic cleaner and the one on the car that kinda runs needs serious work if it will ever pass an emissions test again.


Really cool! Will launch on SN when ready?

One request for mobile, and it’s silly really but I have ADHD sometimes but when the chat bot is generating text after you expand from basic/medium/advanced, I’d like to be able to scroll the screen right away.

Partly to keep the new text towards the middle of the screen rather than the bottom and also because having a screen you can’t interact with touch seems oddly paralyzing. :crazy_face: might just be me.

I also wonder, is there better verbiage for beginner/medium/advanced?

Might I suggest, easy / moderate / advanced

Keep up the great work, I’m really enjoying it and I’ve learned something from it already!


Thanks so much for the feedbacks guys!
@Nigel Awesome!! Didn’t put much thought into mobile version yet so your feedbacks are gold really. I’ll rework that and come back to you when it’s done if that’s okay :smiley:

Oh and yeah of course I will definitely try to launch a SN version as soon as possible! Not sure what the right path will be on the LLM side for that yet but I’ll figure out in due time.


Solid user experience. I’m rooting for you! :clap: