Fork me on GitHub

What is the Mission behind ConnectorDB?

Jun 6, 2016. | By: Daniel

For thousands of years, human beings have improved their lives through observation, experiment, and logical thinking. From noticing which foods make us feel good to searching for the ideal sleep pattern, we are always striving to be healthier, happier, and more productive.

Sometimes we do a pretty good job at this task, but there are limits to what we can observe and analyze. Traditional experiments may take years to collect data only to run basic analyses and find the simplest of patterns.

Recent advances in data analysis and machine learning pave the way forward. Using powerful computers, these programs are sometimes able to find patterns and insights in datasets that defy traditional patterns of thinking.

The question at the heart of ConnectorDB is simple: what if we collected data about our lives and subjected it to the meticulous eye of our most powerful ML algorithms? With that in mind, there are two parts to our project - a question and a goal.


We honestly don’t know if analysis of the mudane details of our lives will lead to deep insight. We might easily find simple patterns that tell us things we already know - that getting enough sleep helps our performance, or that exercise makes us feel better. What we want to know is whether machine learning applied to more detailed, minute-by-minute data can help us optimize our lives in ways that make a significant impact.

Self-improvement, as everybody knows, is no easy task. And anybody who owns a FitBit or productivity app can tell you that changing our negative habits and building positive behaviors is hard whether we have a computer accompanying us or not.

ConnectorDB is an attempt to answer this question. We hope that by looking at personal data, machine learning can show us the best, and most effective way to follow through on our goals. We hope that through active research into personal optimization, we can make a machine which will tune itself to our personalities, and actively nudge us towards our goals.


Gaining actionable insight by analyzing our personal data would be a huge milestone. But that might only be the beginning. If we can find useful patterns by looking at what happens in an individual life, the possibilities that arise from analyzing millions of lives are endless. This is the next step in our project: creating a human dataset.

For one thing, having more data might lead to more accurate insights and predictions. Our individual quirks fade away when seen with the details of others, leaving the core driving forces in our lives.

More importantly, with detailed data on the entire lives of many people, it might be possible to help with truly difficult decisions that can have unforseen effects reverbrating throughout our lives. We’d know what habits and lifestyles led to long and fulfilling lives in the past, and by matching the circumstances of our lives with the lives of those who came before us, we’d truly learn from history.


In order to spur work towards these goals, we created a special database for gathering and viewing detailed quantified-self data. We also created special apps that sync with this database, which gather data from your devices. All of our work is open-source, so if you are technically inclined, you can download the database and apps right now, and gather data while contributors to the ConnectorDB project try to figure out how to use this data to improve our lives.

If you are not a techie, we will try to set up a ConnectorDB server at in the coming months. We first need to make sure ConnectorDB is stable, and that the insights gained from gathering private data outweigh the risks associated with holding it online. We also need to figure out how to fund the necessary servers while remaining open and free.

Recent Posts


Mission 2

Releases 3

Updates 1

This Site


ConnectorDB is a very new open-source project. If you are a designer/developer or ML enthusiast, head on over to the connectordb github, where you can choose which part of ConnectorDB you want to contribute towards! Pull requests or bug reports are welcome!