I spent the last couple of weeks rewriting MegaHAL, and it's finally online again after a brief absence.<p>You can talk with MegaHAL here: <a href="http://megahal.kranzky.com/" rel="nofollow">http://megahal.kranzky.com/</a><p>All source is freely available on GitHub, unencumbered by a license.<p>The main MegaHAL repository is <a href="https://github.com/jasonhutchens/megahal/" rel="nofollow">https://github.com/jasonhutchens/megahal/</a> It includes a console application and eight built-in personalities, including Sherlock Holmes. And it's easy to hook into its API if you want to build something else with it.<p>MegaHAL uses Sooth, which is a simple stochastic predictor, written in C but wrapped in a Ruby gem. It's available at <a href="https://github.com/jasonhutchens/sooth/" rel="nofollow">https://github.com/jasonhutchens/sooth/</a> MegaHAL uses five separate Sooth predictors to do its thing. You could build other things with it.<p>Finally, the code for the server itself is available at <a href="https://github.com/jasonhutchens/megahal-server/" rel="nofollow">https://github.com/jasonhutchens/megahal-server/</a> It's a Rails 4.2 app with a crappy Bootstrap theme. A basic REST api hooks things up, and a daemonized version of MegaHAL processes the queue of jobs coming in from the world.<p>Have fun, I'm looking forward to seeing how warped the online personality becomes, and how big the brain file grows.<p>Share and Enjoy!