I love the idea of a personal server option. I like to run my own servers, for privacy and control.
I love the idea of home automation but I want it to be made of NoT devices. Network of Things. NOT the Internet of Things. I do not want any of my things on the Internet. Heh.
As for the GPU I can upgrade it, but I am hoping that the RX 460 my home server already has will be enough.
Something like this should be a Virtual Machine application image or a Docker container. But how to provide access to the GPU for OpenCL or CUDA? That might be a challenge.
I backed a company on Wefunder.com called Daplie that is making a personal server called the Connect which is scheduled to be delivered in March. They had a successful Wefunder.
Their website is
and their successfully completed Indiegogo campaign is at
The Connect has no voice component. It does have stackable storage up to 8 Terabytes or you can plug up other storage in the back that Daplie says can be virtually unlimited. Daplie touts the benefits of ownership, ease of use, security and privacy.
Later on Daplie announced a plan to create a digital asset, electronic money thingy called Dapcoin.
Dapcoin is supposed to bring the advantages of blockchain to buying apps for server, getting third party verification that the apps and whole system are legit, and even allow others to put their data on your server for payment in Dapcoin for “sustainable farming.”
One of the two original founders disagreed with this new DapCoin direction, withdrew, and Daplie bought out his interest.
In their Sept Indiegogo update they announced their partnership with a company called NextCloud and that
“NextCloud has a rich app ecosystem with apps like Talk, Calendars, Reminders App, Calendar App, Email App, Notes App, Contacts App, Tasks App (like Trello), News (like Apple or Google News), Document Editing Collaboration App (like Google Drive), Video/Voice Calling App (like Hangouts), Chat App (like Slack).”
Their DapCoin whitepaper
Is a good synopsis of all this and more. It also mentions their partnership with a company called DeNet (decentralized net) which will bring their “exclusive decentralized web hosting service”. DeNet is located in Hong Kong, but all their R & D is done in Russia. Yay.
Love their plans for a personal server and apps, neutral (and ignorant) on DapCoin, and excited about the decentralized web hosting, but bummed and a little paranoid about the R&D being done in Russia.
Just thought I would share this and ask some questions.
Could Mycroft be designed to work with the Connect personal server as well as/instead of working with/being on a Mycroft personal server?
Is my paranoia over one of their partners having R & D located in Russia warranted? I understand if you want to sidestep diagnosing paranoia over the internet. That would be healthy paranoia.
I wouldn’t take windows as a constrain.
People actually interested in installing their own Mycroft Personal Server will have technical skills to make it work on either OS.
In case we are aiming at having this running 24/7, we are not talking about gaming PCs, but about some sort of home server, where people have Windows Pro anyway, because of other reasons (user management, RDP, etc.).
Having docker image as main distribution channel will cover 90%+ of target audience, regardless of the host OS, they are using on the machine, they plan to use it for.
For example I have a farm of RPi’s running docker and then also Media Server running Windows Pro. So depending on the performance requirements (GPU?), docker will enable me to choose where to deploy this.
It would be beautiful to be able to use farm of low-power devices (like RPis), for computing this in distributed manner, which would be also easier to implement using docker image distribution and then running it in Kubernetes or Docker swarm. But that is probably dreaming with open eyes
I was also looking at this, but as soon as they came with the idea of DapCoin, I immediately stopped looking at it. That is not a good behavior in my eyes.
But even from technical point of view, I don’t think this will have enough power for Mycroft. Seems like it will be in the same realm as RPi…
Yes - sign me up! I had actually turned my attention away from my Mycroft for a few months now because I considered that I needed to set up a robust speak to text service locally in order for it to really make sense for me here (my makeshift local basic STT install on an underpowered machine was technically working, but really not cutting it for performance and accuracy). And I just wasn’t getting around to doing that the right way.
I will be watching closely, and I’m looking forward to using something like this for my “production” system that will include my Mark 2 units when they arrive.
I am very much interested in a personal server from both a personal as well as corporate standpoint. I am a researcher for a large company and see value in the potential to integrate this technology into some of our projects. However, for both personal as well as corporate, privacy (as well as the perception of privacy) is critical. In my opinion, a private server would radically improve your offering and value to both the personal as well as the business marketplace.
After reading a good bit of your posts I feel I can trust you. However, that is not enough. Things change, accidents happen, and if the audio is allowed to leave my protected area (home or work) then I must assume it may be compromised. For me personally, I am ok with that. I can review your code and documentation and calculate the odds of sensitive audio getting out. However, I would not be able to convince my family or my company to take such risks as they can not fully understand them. This service is not yet a necessity in our culture (like cell phones or facebook) and as such the level of acceptable risk is much lower. I expect that to change someday soon. Meanwhile, a private server for TTS would make the digital assistant service available to all. Please offer it and offer it soon. I am happy to help in any way I can.
Ron
Id be interested to know what the performace would be on something like UDOO Bolt
that has a Radeon Vega 8 in it, claims “a mobile GPU on par with GTX 950M”
Could you build a “Mycroft Plus” based on one of them and slave others to it?
Another plus for using Docker to distribute the platform is that some NAS vendors (primarily QNAP) are now offering NAS models that both have the CPU & GPU capabilities to run AI type workloads (TensorFlow,etc) in box.
I happen to have a Ryzen based QNAP box at home that also has a Nvidia 1060 6GB GPU in it. Something like this might be an alternative option that is a little more “user friendly”, while still having the horse power to handle the load.
Hey there,
I think its a great idea. I would even say its necessary in order for Mycroft being truely cloudless and private.
So, what about the Software that is running on Home now? Is it open source?
My idea would be to release it as a virtual appliance, this could be run on any desktop computer or notebook that had a dedicated gpu for the home user or on an ESXi instance for the pro users.
I have been using linux for years and have to admit that getting nv and ati gpus to work with the appropriate drivers can be frustrating, so a completely preconfigured vm would be great for the average user as well as for power users who are running vms anyway.
I also like the idea of releasing it as a qnap compatible format, as this would be relatively easy to use for home users as well.
And of course i think distributing it over all the mycrofts in the household is a great idea, this doesnt seem to be the right choice when it comes to optimizing latency and also it seems like a much bigger project than just running it on one server.
I think this is a great idea. Not everyone wants the put their info in the cloud or like you said they have internet/bandwidth issues. I also see this expanding personal assistant use to non traditional places such as cars, boats, off grid locations.
I am personally interested for the non traditional and privacy concerns.
I personally thing this will work better if it can be optimized for lower hardware specs. it will be able to go more places at that point. If you could run the whole thing on 2 Raspberry Pis or on some outdated home server someone built years ago would be awesome.
I have some old crappy PC hardware and a raspberry pi ready for testing if needed!
Great Idea! I’ve been actually thinking of it for a while since I built my own “personal smart assistant” including mycroft and a few other technologies, such as vision and so. Everything was stuffed into a raspberry PI 3 but STT… which had to be outsourced to google. As a consequence I started playing with deepspeech, so according to me you are proposing an… almost perfect solution.
It is almost perfect because, as you stated, it requires a quite expensive and geeky hardware to run the server.
I would rather go for deepspeech and tensorflow lite running on an ARM platform with GPU (sounds familiar, doesn’t it? maybe a smartphone?). The point here would be to build tensorflow lite and Deepspeech and provide the needed info to build them for most “hacker-friendly” smartphone platform such as OnePlus and Google Pixel.
I think this is an amazing idea! I’m a geek who enjoys creating and hosting his (or her, I’ll never tell ) own resources either for fun, or to educate myself. Though mostly, it’s out of concern for my privacy. And while I must commend you, because I haven’t come across any issues with any of you, I’m still a little overly cautious and like to host my own resources (such as mail, web pages, databases and such). I think the idea would be rather neat.
It would be interesting to utilize FPGA’s. For $15-20, I am hoping that quite a boost can be obtained. So running complex voice recognition modules, and thus having better speech recognition for speech control. That is what is so awesome about this project. You are essentially controlling skills. Outside of needing different pricing model, I think that that mycroft personal could absolutely target the commercial market.
Count me in.
This will definitely be the make or break feature for me to use MyCroft to add smart Voice Control to my home automation.
Seeing this happen in combination with a solution for having distributed access devices (sound in/out) throughout the house would definitely come close to my ideal setup for this.
Thanks for your feedback @Martin_Corino - we agree - having a self-hosted solution is important for those who value their privacy, which is a key reason that people come to us instead of say Alexa, Siri or Google Home.
Distributed device access is harder to achieve but definitely something we want to work on.
Thanks for the reply Kathy.
I will be eagerly awaiting test versions
In the meantime I’ll pitch in with the Dutch translation because that’s the third “must have” for me.
Hi,
Just found Mycroft.ai, I am experimenting with a Rock64 running Deb. installed Mycroft for Linux working OK.
Regarding computing power for a local server. I would be very unhappy to see vast power hungary X86 Gpu pcs employed.
I cannot see anyone mentioning using an arm based SBC cluster… Good processing power, a lot less power consumption and cheaper to buy.
Have you quantified how much processing horsepower you need for a domestic server?
Here is a brief article :- https://www.linux.com/blog/2018/7/sbc-clusters-beyond-raspberry-pi
Here is a company building and selling various multi SBC clusters:-https://www.picocluster.com/
It wold be interesting to see what compute power these clusters could deliver!
regards
Patrick
When something can replace the compute TOPS and per watt of a gpu at comparable pricing, I’ll be happy to look at it. At last check, the best ARM GPU’s were a factor or more below what a desktop GPU could. the power draw on a small gpu is minimal when not actively engaged in processing. Clusters tend to be less efficient than a larger single machine, and cheaper in the long run.
This was measured using Linpack TPP v1.4.1 at 60,000 Mflops BUT only 55w total power at full load. The cost was around £545 complete!
Gaming Gpus have many orders of magnitude more horsepower but the total cost is greater, the cost has to include the pc the GPU is installed in.
How many Mflops (approximately) power is necessary to produce a working local compute mycroft server with a reasonable performance?
There is no point specifying a server that will need a second mortgage to purchase it and a power station in the back garden to run it!
After all you are competing with a $25 product from Amazon or Google, (Ignoring the privacy aspect). You have to put a very high value on your privacy to fork out for a PC based GPU server to replace commercial unit.
