March 13, 2023

How does the Memri app work?

When you use the Memri app it might feel as if the magic  is happening right there and then, while in reality that is not the case.  A front-end app, like the one you’re using, is very important and allows you to interact with the system we’ve created; but without the other parts, it would be useless. In this blog you will  learn more about what those parts are and how they work together. 

What is the Personal Online Datastore and why do you need one? 

For you to be able to use our app a lot of different elements need to work together in harmony. One of the most vital elements is the Personal Online Datastore or POD. 

Let’s say you’re opening up the app and want to spend 10 minutes only to browse through tweets related to Machine Learning. To do so those tweets (or any other social-media post for that matter) need to be stored somewhere. That somewhere is the POD. 

The POD is your own online vault that only you can access. The information stored in there is encrypted and can only be used with the key you have. Meaning that if someone unplugs the server, takes it home and tries to access it, they won’t be able to access or understand any of the information stored i n there. 

As you can see in the image above, the POD is the central part of our entire system. It stores your data in a safe and organized way so that nobody can access it and so that the Machine-Learning models that we build can do their magic. More on those later. 

For the POD to be of any use it’s vital that the data that is stored in there is constantly imported from the external sources. There’s not much use if you’re only seeing tweets from 2 years ago and miss out on all the new things, right? 

For the POD to import and interact with external services, we created two types of plugins: 

  1. Importer-plugins: those, you guessed it, import your data from external parties. E.g. getting in and storing all tweets from your timeline. 
  2. Action-plugins: which action things. E.g. sending a message using Whatsapp without having to leave the Memri-app. 

Creating those plugins can be really complicated. External parties store their data in different ways which can make it hard to pull information and put it in the right context and do something with it. Something as simple as someone’s name can be very complicated to understand from the data that has been pulled: , is it their twitter handle or is it the one the email address they created when they were 12? 

Keeping your data scattered across different service vendors is the equivalent of “I will throw this thing in an attic in a random house and when I need it again, I will just knock some doors to see if it’s there.”

Since we not only want you to be able to store data on the POD but also enable you to use it in a meaningful way, the data that’s imported needs to first be organized. Instead of throwing it in the attic of a random neighbor, you put it safely in your own attic, in a specific location, labeled and easy to find, and with nobody being able to move it around or misplace it for you. (If only that would be possible for your Christmas decorations!)

Machine Learning Magic Enabled by Indexing Your Data

By organizing the data from all those different sources in the same way, Machine Learning (ML) models can be trained and used to make your life easier. Before they can do so a process called “indexing” needs to happen. This indexing is done by a mixture of importing information from the source (“date” “Username” “likes”), but also by Machine Learning models that are trained to provide specific context (“Topic” “Bot or Human” “Interesting for you”)

So when a tweet is imported to the POD, the indexers add labels such as: “twitter” “username” “Topic” “date” “Likes” “Friend” “Bot or Human” or any other label you’d find interesting. 

By combining the labels and information from other sources it becomes possible to build tools that can help you in your daily life. 

How Machine Learning can be used to make your life easier

Those Machine Learning tools can make your life easier is probably no surprise, the question is how!? The options are endless, but below you find some examples that hopefully also spark your creativity. 

Sticking with the tweet example for now; Let’s say you import a new piece of data: a tweet about cats. An indexer will then label it as a tweet and another adds a label with the topic: “cats”. Now that you have that it would allow you to only see cat-related tweets and nothing else if you chose to do so. Not good enough? Add another filter and only see red cats! More of a dog-person? Do the exact opposite and see no cat-related tweets ever! (Or filter out the Elon Musk Twitter drama when you had enough of that for the week) 

This way you take control of what you see and don’t get the distractions you have when browsing Twitter normally. You just see things that you really want to see at that moment in time, no more time wasted on scrolling until you find the next interesting post. 

A more complex use case: You’re receiving messages from a friend about an upcoming birthday party. Those messages go in the POD and labels are added. The indexers collect the most important information such as the date, person and location of the party. The tool creates a calendar event and places it in your calendar directly (Action-plugin). It will remind you to buy a gift for that person and since the app recognizes who the birthday-girl is, it can even do a suggestion or remind you of the present you gave her last year.  No more giving the same gift twice!

All Components Working Together 

In this blog we introduced the different components of our system in the most basic way possible and have given some potential use cases for how our tool could make your life better. The POD, the importer-plugins, action-plugins, indexing-plugins and ML-models work together and all have an essential role in making our app work well, and besides that, they provide the infrastructure we need to keep expanding our product over time and allowing others to build their own tools on it as well. Want to know more about that?  Have a look at some of our other blogs! .

If  you want to learn more, try it yourself, share cool ideas, or simply receive updates when we have them: Sign-up to our newsletter, join the waitlist for early access or share your ideas and thoughts in our Discord!

recent posts
“Data is the new oil!” In the last couple of years you’ve probably heard this phrase more than once. The metaphor, originally coined by Clive Humby in 2006 to explain that just like oil, data is of low value without it being refined into something useful, has formed the mental model around data.
Read more
AI is changing the world as we know it, and is doing that at an unprecedented speed. Now that Large Language Models (LLM) such as OpenAI’s GPT are made available to the general public, the impact AI can have on our lives becomes more and more visible. With over 1 billion visitors to its website in the first 4 months, it’s safe to say that ChatGPT is already having an impact on the lives of many, but what kind of impact?
Read more
Last week our team went to Paris to for the first time in our history present our company on stage and participate in a start-up competition. We were one of the 48 participants that made it to the final eight and were invited to come to the main event in Paris and present our pitch live on stage.
Read more
This April our remote start-up got together during a retreat, or Memritreat as we call it, in Amsterdam to spend time together in person, reflect on the last couple of years, work on our business strategy and brainstorm on the product direction. Even though the time we had available was short, being in the same room brought a lot of energy and will help us now that we’ve moved back to our home-offices again. 
Read more
By using music you create a similar atmosphere for everyone in the call and as a facilitator, I can say this can make quite some difference and really helps people feel more together. Especially if you throw in some classics from the Spice Girls or Backstreet Boys. 
Read more
“During her Reputation tour Taylor Swift hired a security company to set up a kiosk that played her concert and exclusive rehearsal footage. They covertly installed the kiosk with cameras, with facial recognition technology for the purpose of luring any of Swift’s hundreds of known stalkers. That way they could identify and apprehend them. That example raised a lot of questions about ethical use of technology for me.” 
Read more
When you use the Memri app it might feel as if the magic is happening right there and then, while in reality that is not the case. A front-end app, like the one you’re using, is very important and allows you to interact with the system we’ve created; but without the other parts, it would be useless. In this blog you will learn more about what those parts are and how they work together. 
Read more
Recently we posted this picture on our socials with the question: which animal is not generated by AI? The results weren’t as unanimous as you might have thought. People struggled with finding the right one and started having their own theories about which image was correct and which wasn’t. 
Read more
The Monopoly-problem sounds like one of the latest TikTok challenges gone wild: Kids running across town, placing hotels on every street corner, forcing people to pay when they stop in front of their hotel for just a second. It would be mayhem. 
Read more
In today's fast-paced and information-saturated world, it can be overwhelming to keep up with the constant influx of information coming through multiple channels. Platforms such as Facebook, Twitter, Instagram, Whatsapp, news-sites, podcasts, and many more, are constantly fighting for your attention. More often than not, our minds get hijacked by the dopamine dependencies these platforms create purposefully.
Read more
Buzz-buzz: “Your post got a new reply!” “You got 5 new kudos on Strava” “Someone viewed your profile” “@memriapp just retweeted your tweet”. Chances are that simply reading those words triggered some dopamine release for you already, giving you a short sense of pleasure. Feels good right? Well, you might reconsider after reading this blog. Social media is trying to make you addicted to their stuff! Not so dope…
Read more
Want to try out text to image generating yourself but don’t know where to find the latest models? Have a look here! We’ve created a list of free AI Image Generators you can use (at least temporarily) without paying. Now you can Generate Ai images for free.
Read more
Within Memri we do retrospectives at the end of each sprint (every 2 weeks). We know that it helps us find things we can improve on, learn from and identify what is going well. But still, doing the same type of retrospective each sprint can feel boring after some time. The result? People zone out, leading to more superficial insights. In an attempt to make those retrospectives more fun, and therefore more valuable we tried using Machine Learning, and thus far that has worked! Here’s how we did it.
Read more
Memri was founded in 2020. In the following two years we’ve worked hard to get closer to reaching our goal: Create a personal AI optimized for your goals and that gives you control of your data. We knew from the beginning that our vision was very ambitious. At times that has been a blessing, and at other times a nightmare. It binds us and guides us, but it can also be daunting: Where do you even start?!
Read more
Can you remember how you ended up here? Was reading this blog your intention when you picked up your phone? Or were you actually just setting your alarm and accidentally opened up another app and got caught in scrolling for longer than you intended? We’ve been there, and don’t worry it happens to all of us for a reason.
Read more
When you start the Memri app and use it like you normally do it might feel as if everything you see is happening there and then, in reality that isn’t the case. A front-end app, like the one you’re using, is very important and allows you to interact with the system we’ve created, but without the other parts, it would be useless. In this blog you will learn more about what those parts are and how they work together.
Read more
Join us

shaping a future of possibilities

We envision a future where individuals regain control over their digital experiences, where data sovereignty is a birthright, and where privacy and trust are foundational pillars of the online world.

By integrating regenerative AI solutions responsibly, we aim to create an ecosystem that empowers individuals, fosters inclusivity, and cultivates sustainable growth.


Sign up to receive our ad-free newsletter about product updates, data privacy, machine learning and the latest news from Memri.

Thank you for your subscribing. Please check your inbox or spam folder for a confirmation.
Oops! Something went wrong..
Check your email address and try again