Virtual agents / Chatbots
in United States

The PeTE, a truly helpful Virtual Assistant for the newly developed AT&T corporation.

The PTE at AT&T provides business customers exclusive access to sample code, APIs, SDKs and technical documentation for building mobile productivity solutions for enterprises of all sizes.

PeTE from InteliWISE.com is helping customers with intent - recognition search and customer - engagement triggers. It has like a cool avatar too - The Parrot.

Pandorabots is pleased to announce the release of our new CallMom app for Android. CallMom is a mobile, voice-activated personal assistant that can have a conversation, dial a number, send an email or SMS message, learn contacts, provide help with the app, search the web, open a URL in a browser, read data from web services, check battery status, give directions and find a location on the map -- all through natural langauge, voice commands.

Que is a 3-D chat bot and is the Destination Guide #1 Editors Pick from over 100,000 locations in Second Life.

A chatbot emphasizing useability. You can add her to your website in 5 minutes or less, FREE! She will start chatting with your website visitors immediately. No programming. No scripting. Even no setup required.

Ask Neat is a Virtual Assistant that provides support for Neat products.

Bella giving custom weather reports

Ramona 4.1 is an audiovisual chatbot avatar. This version adds new knowledge sources, including one with Wikipedia-like knowledge and another that enhances Ramona’s whimsicality, along with an improved interface, forming Ramona’s updated unique personality.

Ramona is capable of synthesized speech and changeable accents. Her personality can also be adjusted to make her less or more nerdy or whimsical by typing “Nerdiness” or “Whimsicality” plus a level between 0 and 99 (e.g., “Nerdiness 87″).

Users can hear her speak in 14 international accents, ranging from Baltimore to Bangalore. Users can also converse with previous versions of Ramona.

Zoe was a contestant in the 2011 Loebner Contest. She is an AIML-only bot hosted by Pandorabots.

Harumi is a programmable chatbot working in pair with open office, ready to use in english and french. It is available for the public since summer 2010. You have to edit some part of its memory in order to use it in english or any other language. It was programmed in Delphi and is able to learn from the user.
Harumi brain is very light at the beginning, almost empty in fact. When you write a sentence, Harumi ask you what you mean. The second sentence is then linked to the first one, except if the second sentence reminds her something else, in which case Harumi will link the first sentence to it. With time, this simple algorithm produces good results. Harumi will tend to have your personnality.

Nevertheless, Harumi was not only built as a chat experiment for turing test. From the beginning of the development, Harumi is a usefull program :
You can ask her for your appointments, phone numbers, adress, internet url, files repertory.... all of those informations are stocked in its mind, a file called memory.ods
You can ask her to translate words from english to french, or to seach for a file on a drive. It is possible for her to remind you things you have to do, or to record your feelings and randomly remind you sentences linked to your bad or good mood.
She's able to execute a program, to give you your ip and emac adress or to calculate an operation. As you can see, many windows functions can be replaced by Harumi.

Voice Actions is an advanced virtual assistant for Androids and iPhones. It is comparable to Apples Siri but also lets you make phone calls, write e-mails, send sms, access information and do many more tasks on Android and iPhone devices. Information retrieval is done in a hierarchic fashion, so when people ask for the definition of abstinence the result comes directly from Wikipedia without bothering the APIs of Yahoo Answers, ChaCha, answers.com, pandorabot, cleverbot or other services.

This robot is deeply integrated into the android system, so that settings can be queried and changed via voice as well.