ffnet is a fast and easy-to-use feed-forward neural network training solution for Python. You can use it to train, test, save, load, and use an artificial neural network with sigmoid activation functions. Any network connectivity without cycles is allowed (not only layered). Training can be performed with several optimization schemes, including genetic alorithm based optimization. There is access to exact partial derivatives of network outputs versus its inputs. Normalization of data is handled automatically by ffnet.
Card Stories provides a server for a networked guessing game using picture cards. One player (the "author") starts the game by choosing a card, picking a word or a sentence to describe it, and sending out invitations to others to participate. Each of these players receives seven cards and has to pick one that best matches the author's description. Once enough players have chosen a card, the author displays all chosen cards and the players try to figure out which one is the author's. If at least one but not all of them guesses correctly, the author wins, along with the players who guessed correctly. Otherwise, the guessers all win.