Ultra Hal is an AI platform from the company Zabaware in development since 1997. It is a learning bot that statistically analyzes past conversations to determine a response. It has a plug-in architecture and is fully scriptable and customizable for various uses. It supports many speech and graphics rendering engines for character representation and runs on many platforms including Windows, WWW, iPhone, Second Life, Twitter, and Facebook.
Additional comments by developer Zabaware:
Ultra Hal is like an inquisitive child and is capable of learning new things from conversations based on complex natural language processing technology capable of statistically analyzing past conversations. The algorithms behind Ultra Hal have been in development for over 16 years and the recent explosion of social networking has given the system a huge conversational pool to base its knowledge on. The system analyzes hundreds of thousands of conversations publicly available on Twitter each and every day. These conversations, along with conversations the system has with web visitors and users of its Facebook app, get assimilated into a large conversational database that becomes the base of knowledge for the artificial intelligence. Having a conversation with Ultra Hal is, in effect, like having a conversation with the “collective consciousness” of Twitter, Facebook, and user’s of Ultra Hal. Hal’s personality is a reflection of all of these people.
Ultra Hal Assistant is available as a $30 for Windows PC and has 3d character animation, speech recognition, and speech synthesis capabilities. It is able to server as a personal information manager remembering appointments and contacts. Web-connected versions of Ultra Hal (including the iPhone version, Second Life, Facebook, and Twitter versions) are also connected to Wikipedia and Bing and are able to utilize these sources to answer various fact-based questions (e.g. What is the tallest building in the world?)