>> What we figured was the biggest problem with any form of machine learning or data based system is that we require high quality historic data. When a company starts the heavy dependance on free/freemium analytics services it means that all that data is usually lost for good. [...]

At the risk of shamelessly promoting our (also open-source) product: We also didn't like the fact that all commercial event analytics tools were completely proprietary and would effectively be closed data silos, so we recently released the open source EventQL event analytics database [1]. Maybe it would be an interesting target to support in octo.ai?

[1] http://eventql.io/

It does sound like a great target to support! Okay to get in touch with you when we start on this?

Thanks for having a look!

How are Snowplow and Piwik completely proprietary?

I'm not familiar with Snowplow, but why would you put Piwik in the same category as Octo?

Pretty great vision, much of the analytics from 3rd parties is clickstream/web data. For the most part, unless you have a specific use for it, it's too much data to bother saving yourself. Does Octo somehow handle this huge volume without everyone having to host google analytics on their own? (Maybe a dumb question, I didn't dive into it past the homepage :)

Actually, this is a really great question! It is quite a bit of data to bother saving yourself till you actually get to a scale to make use of it. Now that the internet business is fairly mature, the specific use cases for high quality data has exploded.

I would like to argue that its usually a lack of frameworks (and lack of dev resources) to enable this, due to which people do not store all this data. AWS and others are cheap enough machine abstractions which with the right framework (like us) may let you store this data without (too much) work.

Thanks for having a look at us!

Is the machine learning goodness included in this? Also a 'vagrant up' would be very nice... Thanks, anyway!

Hey, first of all thanks for having a look! We are cleaning up the ML goodness for the next update!

Sorting out the installation bits, for easy dev and deployment.

really great, thank you very much for open sourcing, can't wait to dig into this!

Feel free to reach out directly to me, if you need any help!

This looks nice.

To OP, I'm looking forward to the dockerized version. Would be a good subject for a presentation at ContainerizeThis 2016 - http://containerizethis.com.

If you're not too far from Texas, we'd love to have you present.

So you're like an open source version of Segment? Am I understanding it right?