These are web resources that we believe are reasonably current (or of significant historical value) for software agent technology. I apologize for the fact that this list is in simple reverse chronological order (the order that I added to the list), but that's less work for me and does make it easier to find what's new. Ultimately the list should be a relational database that can be sorted by selected categories. Or maybe I should say that ultimately it should be embodied in a semantic web/grid that can be traversed by software agents to locate resources of interest.
[ Home | Blog | Books | Glossary | Links | Manifesto | Search | Contact | Pre-2001 | 2001 | 2002 | 2003 | 2004 | 2005 ]
| Please let us know if you wish to add (or change) a link. Click here. |
- Agent Academy - a data mining framework for training intelligent agents. Agent Academy is an innovative Research and Development project launched under the Information Society Technologies (IST) EU Programme. The main goal is to develop an integrated environment for embedding intelligence in newly created agents through the use of Data Mining techniques. Agent Academy aims to a) develop the tools for assembling and maintaining a large repository of data on agent use and behavior, b) provide an integrated environment for the systematic study of agent intelligence, and c) develop a well-defined, well-specified model for an agent-training facility. Agent Academy will adhere to a common set of primitive specifications, which are compliant with widely accepted efforts for standardization, such as the ones undertaken by FIPA, OMG and others. The successful outcome of this effort is expected to propagate the use of agent-related technologies into business practices and personal use.
- Xplore - a negotiation-oriented lightweight platform from Xerox Research Centre Europe aimed at coordinating distributed autonomous software components. A negotiation in Xplore is modeled as a collaborative process among autonomous decision-makers, possibly distributed and with different goals and resources, towards the definition of an agreement as to a set of actions to be executed by each of them.
- Agents Victoria - a group of industry, government, and university groups, involved in agent research and applications, that meets regularly in Melbourne, Australia and was formed in 1998 to foster R&D collaboration between industry and research groups using intelligent software agents.
- Software Agents in Distributed Knowledge Management Systems - a briefing paper by Joe Firestone that discusses the use of software agents for process control services in active knowledge management.
- Living Systems Technology Suite (LS/TS) from Whitestein Technologies - an industry-grade, Java-based foundation for the professional development and operation of products and solutions based on software agent technology and autonomic computing. LS/TS is compatible with your existing IT infrastructure. It seamlessly blends in, and adds the features and functionality required to design, build, and operate robust and well-performing business solutions that make use of the advanced properties of software agents and Multi Agent Systems (MAS). The Technology Suite is based on practice-proven object technologies, methodologies, and products. This approach brings about the protection of your investments in infrastructure, know-how, and experience. And it ensures full compatibility with the offerings of major IT vendors, e.g., in the field of business process and data integration. LS/TS was conceived with the know-how, experience, and practical needs of today’s IT departments in mind. The tools build on Eclipse, the run-time environments extend the existing J2SE run-time environment and J2EE application servers. To achieve clean, well-engineered system designs, and to allow for flexible deployment (run-time environment) options, the Core Agent Layer (CAL) was designed. As a unifying layer, CAL defines the necessary abstractions and components to build agent systems, and which is implemented in all LS/TS run-time environments to provide the core platform services. The abstractions and components provided by the CAL were carefully chosen to balance the expressiveness and power of the agent paradigm against the practical needs of software engineering and maintenance. By its open design, the CAL can be extended to meet future agent software engineering requirements.
- MAGE (Multi-AGent Environment) - a Java-based software framework that provides an agent-oriented environment for software design, integration, and execution. It provides a new computing and problem-solving paradigm in terms of agent technology. MAGE has facilities to support agent mental state representation, reasoning, negotiation, planning, cooperation and communication. It provides system design support, description and assembly of knowledge and capability, negotiation and cooperation design for agent-based computing on the Internet. It simplifies the implementation of multi-agent systems through middleware that complies with the FIPA specifications and through a set of tools that support the debugging and deployment phases. It simplifies integration of applications through multiple schemes of software reuse and an agent-oriented software design with a graphic user interface, and also it simplifies execution management through a powerful GUI with extensive run-time support. The agent platform can be distributed across machines (which may be running different operating systems) and the configuration can be controlled via a remote GUI. The configuration can be even changed at run-time by moving agents from one machine to another when required.
- OWL-S version 1.1 - latest release of OWL-S, an OWL-based Web service ontology, which supplies Web service providers with a core set of markup language constructs for describing the properties and capabilities of their Web services in unambiguous, computer-interpretable form. OWL-S markup of Web services facilitates the automation of Web service tasks, including automated Web service discovery, execution, composition and interoperation. OWL-S builds on the OWL Web Ontology Language Recommendation produced by the Web-Ontology Working Group at the World Wide Web Consortium. Previous releases of this language were known as DAML-S, and were built upon DAML+OIL (the predecessor of OWL).
- Craig Ugoretz' Wisdom Seeker Initiative - describes a conceptualization for how software agents can be given the ability to assimilate wisdom.
- Imagination Engines, Inc.: Multi-Agent Systems - Computer users, application providers, and systems integrators are finding multi-agent systems essential in meeting their mission-critical needs. These highly advanced applications offer the ability to assign tasks to "virtual" assistants (intelligent software agents) that in turn act collectively in carrying out a variety of data discovery and processing tasks on behalf of their users. A synergistic community of intelligent software agents can replace much of the human activity and interaction required in monitoring systems, as well as for tracking, finding, gathering, analyzing, managing, presenting, and acting on information. This prevents redundant effort while increasing productivity and maintaining business focus.
- WONDERMAR / EPI-SPARK / LISA - EPI-SPARK (Enhanced Protection of IPR by Streamlined Provision of Access to Regulatory Knowledge) is part of the WONDERMAR II project (Wide Open Network for Development and Research in Maritime Industries) and has as its main objective the development of LISA (Legal Information Software Agent) an intelligent software agent for supplying legal information about IPR (Intellectual Property Rights). An increasing proportion of modern economic activity consists of trade in Intellectual Property. For EU industry to succeed, even in traditional industries its IPR must be protected, to give it the competitive edge, which depends on exclusive use of a patented invention. EPI-SPARK, to achieve this, will create an e-commerce site for the provision of faster, cheaper and more comprehensive IPR services, principally for European SMEs. This will enable them to compete more effectively in the global marketplace. LISA will, by the end of the project, be able to handle 100% of queries, for all EU countries, from a set of 50 standard query types selected by the Patent Agency partner from its customer files and handle 95% of other legal IPR queries.
- WoGLI - the Working Group on Law and Intelligent Information Agents (IIAs) - aims at studying the legal side of the usage of IIAs and the legal implications of human-agent and agent-agent interactions. The WoGLi is part a working group part of the AgentLink Special Interest Group on Intelligent Information Agents.
- Nature Inspired Computing: A New Set of Tools for Management - a new book (in progress) dedicated to the application of computing techniques inherited from nature to management and economy. Nature Inspired Computing advances the state of the art of coping with increasing complexity in two ways: emergent (bottom-up) simulations and optimization. Emergent simulations lead to a better understanding of complex interactions and to original theoretical approaches. Nature inspired algorithms for optimization lead to efficient, supple, and adaptable tools. The universality of the computing techniques inherited from nature, i.e. their applications as well in biology, physics, engineering as in economy or management, clearly demonstrates their depth. The book will cover both theoretical interpretations and innovative computing tools and will be useful to both academics and practitioners.
- FleshFactor Forum - vintage 1997 discussion about the interaction between users and intelligent software (e.g., software agents). Includes contributions by Pattie Maes of the MIT Media Lab.
- NEW TIES - New and Emergent World models Through Individual, Evolutionary, and Social Learning - a research project funded by the European Commission via the 6th Framework's Future and Emerging Technologies open scheme whose goal is to realize an evolving artificial society capable of exploring its virtual world and developing its own view of that world. The long-term target is to learn how to design agents that are able to adapt autonomously to, and then operate effectively in, environments whose features are not known in advance. The main pillars of the envisioned research are world models and the learning mechanisms generating these. The project will not implement specific training facilities or feedback systems rewarding the learning of world models for its own sake. Instead, it is interested in emerging world models powered by a basic survival game. In order to obtain the expected emergent features, the project will work on a very large scale compared to that of today’s common practice with respect to the size of the agent population and agent complexity. The project defines culture as knowledge structures shared among agents that reflect aspects of the environment, including the other agents.
- EPSRC Novel Computation initiative - an initiative aimed at developing new computational approaches to deal with complex systems by supporting adventurous, non-conventional, and multi-disciplinary research. The ability to deal with complexity is becoming a major goal in many areas of research, from the understanding of cell division to the management of computer networks. Complex systems appear everywhere in 'real-world' observations, such as flocks of birds or schools of fish behaving as a single super-organism, and colonies of insects working cooperatively for their overall benefit. Current projects include non-Linear media based computers chemical and neuronal networks through machine learning, function of distributed plasticity in a biologically-inspired adaptive control algorithm - from electrophysiology to robotics, eXtended Particle Swarm (XPS), market based control of complex computational systems, and novel approaches to networks of interacting autonomes.
- Distributed Agents (part of IEEE Distributed Systems Online) - focuses on support for the development of large-scale, secure, heterogeneous, agent systems. Research in this area includes scalable and secure agent platforms, location services, directory services, and systems management. Support systems are not only expected to support heterogeneous agents (both architecture and programming language), but also different operating systems and hardware. This area of research connects with Distributed Systems, Artificial Intelligence, Computer Systems, Mobile Code, Parallel Computing, Semantic Web, Large-Scale Systems, Cognitive Science, Security, Agent Technology, Software Engineering, and other areas of computing.
- Intelligent Software Agents (by David Wallace Croft) - some historic references from the late 1990's.
- Swarm Development Group (SDG) - supports the development of the Swarm Simulation System (Swarm) to advance the state-of-the-art in multi agent based simulation and promote the free interchange of multi agent based simulations among computing specialists and the public and to develop and maintain the integrity and competence of individuals engaged in the practice of agent based simulation.
- QL2 SOftware, WebQL - a Web mining and unstructured data management software tool for quickly and easily developing and deploying software agents to extract information from the World Wide Web and other unstructured data sources and to reformat it into structured formats such as spreadsheets, databases, and XML.
- Agent Factory - "A Rapid Application Development Framework for Agents" - ongoing research at University College Dublin that is concerned with the creation of "a cohesive framework that supports a structured approach to the development and deployment of agent-oriented applications." Key features are: an interpreted Agent Programming Language that is derived from a formal logical model, an Agent Platform that supports the deployment of agents written in this language, Lightweight Agent Implementation that can be deployed on PDAs, Prefabricated System Agents including FIPA Agent Management System and Directory Facilitator agents, well-defined methodological support for the fabrication of agents, and an integrated toolset that aids the fabrication process.
- OWL-S version 1.1B - latest beta release of the OWL-based Web service ontology, which supplies Web service providers with a core set of markup language constructs for describing the properties and capabilities of their Web services in unambiguous, computer-intepretable form. OWL-S markup of Web services facilitates the automation of Web service tasks, including automated Web service discovery, execution, composition and interoperation. OWL-S builds on the OWL Web Ontology Language Recommendation produced by the Web-Ontology Working Group at the World Wide Web Consortium. Previous releases of this language were known as DAML-S, and were built upon DAML+OIL (the predecessor of OWL).
- AgentcitiesUK.net - a government-funded UK project designed to assist academic researchers and business and industry in the development, use, and exploration of agent-based technology and agent-based approaches. The project supports activities designed to examine significant problems from an agent perspective. Portal development is supported to offer a place to locate software agent tools and components for teaching and research. The project supports development of agent services that provide geographical or location-independent functions. The project supports the development of infrastructure and frameworks for a distributed laboratory for agent experiments And finally, the project supports community building to bring together academic and industrial research interests.
- Journal of Artificial Societies and Social Simulation (JASSS) - an electronic, refereed journal devoted to the exploration and understanding of social processes by means of computer simulation. It is freely available, with no subscription.
- Third Americas' School on Agents and Multiagent Systems - four days of tutorials on the field of agents and multiagent systems at Columbia University, New York, NY, July 17 - 20, 2004, primarily intended for graduate students from around the world, but with a particular focus on students in North and South America. Undergraduate students may be allowed, provided they submit a letter from an advisor recommending them as qualified for this school, and non-student attendees are also welcome to apply.
- Yahoo Mobile-Agents Discussion Group - intended to discuss and exchange information about the use of mobile agent technology. Both problems and ideas about different platforms (Voyager, Grasshopper, Tryllian, Aglets, ...) and also about their applications (mobile computing, distributed processing, etc) are welcome.
- World Federation on Lateral-Computing(WFLC) - Lateral-Computing.org - a non profit virtual professional organization founded to promote the emerging field of Lateral computing. It organizes seminars, workshops, conferences and publishes newsletters, conference proceedings. Lateral-Computing is the term coined to capture unconventional computing techniques. The Lateral Thinking approach to computing has led to numerous interesting and smart solutions for problems whose mathematical models are not available. One of the components of Lateral-computing is Soft Computing which approaches problems with a human information processing model. Soft Computing includes Fuzzy logic, neuro-computing, evolutionary-computing, machine learning and probabilistic-chaotic computing. Lateral-Computing is for building a new generation of artificial intelligence based on unconventional processing.
- Adaptable Java Agents (AJA) - a tool for multi-agent system programming by Mihal Badjonski. AJA consists of two programming languages: A higher-level language used for the description of the main agent parts, called HADL (Higher Agent Definition Language), and a lower-level language used for the programming of the agent parts defined in HADL, called Java+, which is actually Java enriched with the constructs for accessing higher-level agent parts defined in HADL. AJA agents have the following features: agents are static (not mobile), agents communicate with other agents using a construct called negotiation where messages sent can be encrypted or digitally signed in order to ensure the security of the system, agents possess adaptable parameters and neural nets that adapt themselves when the environment changes, agents have reflexes which are the reactive component of the agent architecture, agents can perform their actions in parallel and action executions are synchronized, agents are accessible via the Internet since they act as simple HTTP servers that people can use to communicate with an agent, agents have Java Swing-based graphical user interfaces for communicating with the owners of the agents, and all useful Java features can be used in the implementation of AJA agents (e.g. JDBC for the database access) since Java+ extends Java.
- New Release of Teaching Material for "An Introduction to Multiagent Systems" by Michael Wooldridge - teaching materials for this introductory textbook include PowerPoint versions of slides for the entire course, revised & extended coverage of topics, PostScript/PDF slides & handouts, sample course/module descriptions, sample exam papers, and extensive online links to other resources. All teaching materials are available for free download.
- International Foundation for Multiagent Systems (IFMAS) - a non-profit corporation whose purpose is to promote science and technology in the area of artificial intelligence and multiagent systems. In pursuit of its purposes, IFMAS will engage in activities including, but not limited to: 1) Coordinating and arranging seminars on artificial intelligence and multiagent systems, 2) Becoming a representative forum for experts within the field of artificial intelligence and multiagent systems, 3) Distributing, and making available, knowledge about multiagent system technology through publications, organizational seminars, courses, and conferences, and 4) Collaborating with scientific and other institutions, organizations and other societies, including industrial companies, governments, and international bodies with similar or related purposes.
- Agent-Oriented Software Engineering IV: 4th International Workshop, Aose 2003, Melbourne, Australia, July 15, 2003: Revised Papers (Lecture Notes in Computer Science, 2935) (click here for Amazon) - this book edited by Paolo Giorgini, Jörg P. Müller, and James Odell assesses the state of the art of agent-based approaches as a software engineering paradigm. The 15 revised full papers presented together with an invited article were carefully selected from 43 submissions during two rounds of reviewing and improvement for the 4th International Workshop on Agent-Oriented Software Engineering, AOSE 2003, held in Melbourne, Australia, in July during AAMAS 2003. The papers address all current issues in the field of software agents and multi-agent systems relevant for software engineering; they are organized in the topical sections modeling agents and multi-agent systems, methodologies and tools, patterns, architectures, and reuse, and roles and organizations.
- ISO/IEC 13250 Topic Maps - an International Standard that provides a standardized notation for interchangeably representing information about the structure of information resources used to define topics, and the relationships between topics. A set of one or more interrelated documents that employs the notation defined by this International Standard is called a topic map. In general, the structural information conveyed by topic maps includes groupings of addressable information objects around topics (‘occurrences’), and relationships between topics (‘associations’). A topic map defines a multidimensional topic space -- a space in which the locations are topics, and in which the distances between topics are measurable in terms of the number of intervening topics which must be visited in order to get from one topic to another, and the kinds of relationships that define the path from one topic to another, if any, through the intervening topics, if any. In addition, information objects can have properties, as well as values for those properties, assigned to them externally. These properties are called facet types. Several topic maps can provide topical structure information about the same information resources. The Topic Maps architecture is designed to facilitate merging topic maps without requiring the merged topic maps to be copied or modified. Because of their extrinsic character, topic maps can be thought of as overlays on, or extensions to, sets of information objects. The base notation of Topic Maps is SGML; an interchangeable topic map always consists of at least one SGML document, and it may include and/or refer to other kinds information resources. A set of information resources that comprise a complete interchangeable topic map can be specified using the ‘bounded object set (BOS)’ facility defined by the HyTime architecture in ISO/IEC 10744:1997. As the Extensible Markup Language (XML), a World Wide Web Consortium recommendation, is a subset of SGML, as explained in Annex K of SGML (1997), also known as WebSGML, XML can be also used as a base notation for Topic Maps.
- Ontopia - a business created to bring knowledge, information, and process management solutions to the market through the development of outstanding quality topic map software. They provide customers with effective, integrated knowledge management solutions that will enable them to make relevant information quickly accessible and so expose the full value of corporate knowledge. They achieve this goal by providing the right combination of robust, scalable software products, customized applications, expert consultancy, project management, and support. Their solutions are be based on open standard technologies, in particular XML Topic Maps (XTM) and ISO 13250 Topics Maps, that permit the representation of knowledge in an interchangeable form and provide a unifying framework for knowledge and information management.
- Topicmaps.Org - an independent consortium of parties interested in developing the applicability of the Topic Maps Paradigm to the World Wide Web, by leveraging the XML family of specifications as required. This work includes the development of version 1.0 of an XML grammar for interchanging Web-based Topic Maps, called XML Topic Maps (XTM) Version 1.0, written by the Topicmaps.Org Authoring Group.
- SemanticWeb.org - The Semantic Web Community Portal. A facility to demonstrate ideas and concepts leading to the Semantic Web.
- Engenia Software, Inc. - provides innovative enterprise solutions that use intelligent "software agents" to integrate the planning, execution and reporting functions of complex organizational processes. With Engenia's non-invasive, end-to-end process management solution, projects are streamlined and productivity is optimized, resulting in increased innovation, customer satisfaction, and profitability.
- BotBox.com - provides a new generation of tools to users of the Internet and intranets that help them stay efficient and focused, and to use the net to its fullest potential. BotBox AB is a spin-off company from SICS, Swedish Institute of Computer Science. Their flagship product, BotBox Personal Assistant ("Your Personal News Agent") gives you a set of information monitoring agents that automate the tedious task of retrieving and filtering relevant information. You specify the sources and your agents bring in the news - as soon as they arrive. No more browsing around just to see if something has happened. Using BotBox You can: 1) efficiently stay updated on the latest news by monitoring RSS news feeds, blogs, etc., 2) know the latest trends and findings by monitoring technology pages, research publications, etc., and 3) keep ahead of your competition by monitoring their press releases, etc.
- Agent-Based Systems at the SICS (Swedish Institute of Computer Science) Intelligent Systems Laboratory - aims to provide a technical and conceptual foundation for the automation of electronic markets. The markets studied are on one hand more specialized, e.g., bandwidth for IP telephony, railway transportation, and electric power, on the other hand more general markets for goods, services, and information. In the first case, supply and demand are for (more or less) standardized commodities, and the main problem is to achieve an efficient allocation under different circumstances while allowing participants to act in their own best interests. In the second case, supply and demand are more vague, and the main problem is to match interests of and build trust between market participants.
- AgentBase.com - survey of Agent-Based Systems by Sverker Janson of the Swedish Institute of Computer Science.
- Intelligent Software Agents on the Internet - thesis by Björn Hermans is an inventory of currently offered functionality in the information society & a prediction of (near-)future developments. Dated 1996, but useful historical perspective. Abstract: Software agents are a rapidly developing area of research. However, to many it is unclear what agents are and what they can (and maybe cannot) do. In the first part, this thesis will provide an overview of these, and many other agent-related theoretical and practical aspects. Besides that, a model is presented which will enhance and extend agents' abilities, but will also improve the way the Internet can be used to obtain or offer information and services on it. The second part is all about trends and developments. On the basis of past and present developments of the most important, relevant and involved parties and factors, future trends and developments are extrapolated and predicted.
- James Odell - Consultant specializing in applying object-oriented and agent-based techniques to build process-aware business systems. His commercial work involves understanding, communicating, and developing business systems - especially those involving UML, business process management (BPM), OO, multiagent, and complex adaptive systems (CAS). These systems can and do include software, machines, and people as agents and objects.
- JSR 87: Java Agent Services - defines a set of objects and service interfaces to support the deployment and operation of autonomous communicative agents. It is based upon the Abstract Architecture developed by FIPA, the Foundation for Intelligent Physical Agents. This Abstract Architecture defines how agents may register and discover each other, and how agents interact by exchanging intentional messages which are grounded in speech-act theory and first-order predicate logic. The specification defines two kinds of entities: 1) Java classes for objects corresponding to the various elements of ACL (agent communication language) and SL (content language), as well as FIPA agent names and descriptions, and 2)
Java interfaces corresponding to the agent services for agent registration, discovery, and communication. It is intended that the service interfaces may be implemented in terms of a number of different technologies, including both existing Java standards and proprietary systems.
- Ajanta - a mobile agent programming system being developed at the University of Minnesota. It allows agents written in Java to securely migrate from machine to machine on the Internet. The Ajanta project is aimed at building an infrastructure for mobile agent execution that incorporates security and robustness features as an integral part of the design.
- Ontology by John Sowa - a reasonably detailed introduction to the subject of ontology. He tells us that... The subject of ontology is the study of the categories of things that exist or may exist in some domain. The product of such a study, called an ontology, is a catalog of the types of things that are assumed to exist in a domain of interest D from the perspective of a person who uses a language L for the purpose of talking about D. The types in the ontology represent the predicates, word senses, or concept and relation types of the language L when used to discuss topics in the domain D.
- What is an Ontology? by Tom Gruber - brief explanation of ontology. His short answer... An ontology is a specification of a conceptualization. That is, an ontology is a description (like a formal specification of a program) of the concepts and relationships that can exist for an agent or a community of agents.
- Ontology and Policy Management at IHMC - a project at the Institute of Human and Machine Cognition at the University of West Florida to create methodology and infrastructure, to be incorporated in the KAoS Services Framework, to enable defining and managing policy and semantically rich services in software agents and human-robotic environments.
- Research in Agent-Based and Complex Systems at the Altarum Institute - agent-based modeling, focuses on the entities that make up systems, rather than on variables and equations that describe interactions. For instance, think of a factory floor. Rather than equations describing the interaction among shop floor tools, we would construct a separate "autonomous agent" representing each tool, and then provide each agent with "self knowledge." Thus, an agent representing a machine tool would "know" its location, capabilities, operating constraints, and input/output requirements. So, too, would the other tools "know" about themselves. The simulation would then let these agents loose to interact with each other. As they interacted, the behavior of the shop floor would emerge and be observed. Our experience in developing agent-based models over the last fifteen years has shown that these models offer a number of advantages over the more traditional equation-based methods.
- Amorphous Computing at MIT Project MAC ("Switzerland") - The objective of this research is to create the system-architectural, algorithmic, and technological foundations for exploiting programmable materials. These are materials that incorporate vast numbers of programmable elements that react to each other and to their environment. Such materials can be fabricated economically, provided that the computing elements are amassed in bulk without arranging for precision interconnect and testing. In order to exploit programmable materials we must identify engineering principles for organizing and instructing myriad programmable entities to cooperate to achieve pre-established goals, even though the individual entities are unreliable and interconnected in unknown, irregular, and time-varying ways.
- Agent-Mediated Knowledge Management - AMKM 2003 - This book edited by Ludger van Elst, Andreas Abecker, and Virginia Dignum is a collection of papers focusing on agent-mediated knowledge management. Most of the papers are extended and improved versions of work presented at the Symposium on Agent-Mediated Knowledge Management, AMKM 2003, held during the AAAI Spring Symposium in Stanford, CA, USA in March 2003; also included are 3 special articles, including a detailed introduction to the topic by the volume editors. The 28 papers are organized in topical sections on collaboration and peer-to-peer support, agent-based community support, agent models for knowledge and organizations, context and personalization, ontologies and semantic Web, and agents and knowledge engineering.
- SchemaWeb.info - a repository for RDF schemas expressed in the RDFS, OWL and DAML+OIL schema languages. SchemaWeb is a place for developers and designers working with RDF. It provides a comprehensive directory of RDF schemas to be browsed and searched by human agents and also an extensive set of web services to be used by RDF agents and reasoning software applications that wish to obtain real-time schema information whilst processing RDF data. RDF Schemas are the critical layer of the Semantic Web. They provide the semantic linkage that 'intelligent' software needs to extract value giving information from the raw data defined by RDF triples.
- Agent Semantic Communication Service (ASCS) - the search system for the semantic web. It allows a user to make precise queries for information encoded in DAML/OWL. ASCS also supports several kinds of simple inference to support query broadening or relaxation. ASCS can also be used directly by web based agents to support semantic search and ontology translation.
- Standard Upper Ontology Working Group (SUO WG) - an IEEE working group that is developing a Standard that will specify an upper ontology to support computer applications such as data interoperability, information search and retrieval, automated inferencing, and natural language processing. An ontology is similar to a dictionary or glossary, but with greater detail and structure that enables computers to process its content. An ontology consists of a set of concepts, axioms, and relationships that describe a domain of interest. An upper ontology is limited to concepts that are meta, generic, abstract and philosophical, and therefore are general enough to address (at a high level) a broad range of domain areas. Concepts specific to given domains will not be included; however, this standard will provide a structure and a set of general concepts upon which domain ontologies (e.g. medical, financial, engineering, etc.) could be constructed.
- MIT Project Oxygen - "Pervasive, Human-Centered Computing" - enables pervasive, human-centered computing through a combination of specific user and system technologies. Oxygen's user technologies directly address human needs. Speech and vision technologies enable us to communicate with Oxygen as if we're interacting with another person, saving much time and effort. Automaton, individualized knowledge access, and collaboration technologies help us perform a wide variety of tasks what we want to do in the ways we like to do them. Oxygen's device, network, and software technologies dramatically extend our range by delivering user technologies to us at home, at work or on the go. Computational devices, called Enviro21s (E21s), embedded in our homes, offices, and cars sense and affect our immediate environment. Handheld devices, called Handy21s (H21s), empower us to communicate and compute no matter where we are. Dynamic, self-configuring networks (N21s) help our machines locate each other as well as the people, services, and resources we want to reach. Software that adapts to changes in the environment or in user requirements (O2S) help us do what we want when we want to do it.
- MetaGlue - part of the MIT Project Oxygen software infrastructure that provides computational glue for large groups of software agents, such as those used in the Intelligent Room. MetaGlue clearly separates software that acts on behalf of users from software controlling spaces, provides wide-scale communication and discovery services, enables users to interact (subject to access control) with software and data from any space, and arbitrates among applications competing for resources. MetaGlue is implemented in Java, replacing the remote method invocation (RMI) mechanism with one that allows dynamic reconnection so that agents can invisibly resume previously established, but broken connections.
- Atom - an XML-based file format intended to allow lists of information, known as "feeds", to be synchronised between publishers and consumers. Feeds are composed of a number of items, known as "entries", each with an extensible set of attached metadata. For example, each entry has a title. The primary use case that Atom addresses is for syndicating Web content such as Weblogs and news headlines to other Web sites and directly to consumers. However, nothing precludes it from being used for other purposes and types of content. Atom appears to be a competitor of the RSS format.
- AtomEnabled.org - web resources for users of Atom, a universal personal content publishing standard created by leading service providers, tool vendors and independent developers.
- Open Source Agent Systems Written In Java - a descriptive list of the various research projects that have produced open source tools for developing software agents using Java.
- MultiAgent.com - a portal for information about research and developments in multiagent systems maintained by José M. Vidal. Includes recent conference announcements.
- Event Share Framework - an XML-based protocol for sharing event information between entities. Individuals desire to aggregate, publish and distribute event information in many locations, and by various means. Doing this has been made difficult because of a lack of a formal format by which to distribute this event information. The ESF is designed to provide that standard formant, allowing entities to communicate event information in a standard format and manner, by using an XML-grammar, which facilitates the aggregation of information, and provides a well-defined pattern of usage for instances of this grammar. The major goal of the ESF is simplicity and extensibility. To that end, the ESF is built as an extension of the already popular and widely used RSS (Really Simple Syndication) 2.0 format.
- RSS 2.0 (Really Simple Syndication) - a Web content syndication format that allows a web site to publish an information feed that can easily be consumed by a "reader" application. Many web logs (blogs) are available as RSS "feeds". RSS is a dialect of XML. All RSS files must conform to the XML 1.0 specification, as published on the World Wide Web Consortium (W3C) website. At the top level, a RSS document is a <rss> element with a single subordinate <channel> element, which contains information about the channel (metadata) and its contents.
- Agent Technology Pty Ltd - an Australian start-up company incorporated to take advantage of the power of networks based on intelligent software agents. The company's technology particularly takes advantage of the rapid growth in "always-on" data networks provided by telecommunications products such as various forms of broadband; ADSL, cable, mega-link, Frame Relay, ISDN etc. Agent Technology has developed an intelligent software agent network approach with underlying technology that can be adapted to many industry sectors. The technology can generate numerous product candidates over time. The strategic direction and essence of Agent Technology is to develop disruptive technologies that displace old and inefficient business processes or technical solutions. The company's strategic approach includes global as well as localised markets. At the DEMO2004 conference they demonstrated Sweet-Tooth, a decentralized software agent network for supply chains. It is a highly scalable technology, offering a low-cost product that satisfies price-sensitive customers. A secure P2P network, Sweet Tooth can grow organically and even scale up to solve a domestic or international trade requirement. The product allows small companies that sell to or buy from large organizations to inexpensively implement supply chain communication.
- Capturing Business Complexity with Agent-Based Modeling and Simulation - a course sponsored by Argonne National Laboratory, University of Chicago and Santa Fe Institute to provide an intensive introduction to agent-based modeling and simulation (ABMS) with a focus on business applications. The first half of the course focuses on ABMS concepts from the perspective of company managers and analysts. The second half of the course focuses on ABMS implementation from the perspective of company software developers and includes extensive hands-on exercises.
- OWL-S - an OWL-based Web service ontology, which supplies Web service providers with a core set of markup language constructs for describing the properties and capabilities of their Web services in unambiguous, computer-interpretable form. OWL-S markup of Web services will facilitate the automation of Web service tasks, including automated Web service discovery, execution, composition and interoperation. Following the layered approach to markup language development, the current version of OWL-S builds on the Ontology Web Language (OWL) Candidate Recommendation produced by the Web-Ontology Working Group at the World Wide Web Consortium.
- The Semantic Web - On February 10, 2004 the World Wide Web Consortium released the Resource Description Framework (RDF) and the OWL Web Ontology Language (OWL) as W3C Recommendations. RDF is used to represent information and to exchange knowledge in the Web. OWL is used to publish and share sets of terms called ontologies, supporting advanced Web search, software agents and knowledge management.
- Agent Business Force Corporation - Agents were designed at universities as a tool to develop systems capable of providing such flexibility and adaptability, while keeping the productivity and efficiency of the past. Agent Business Force converts this research to tangible benefits for real-life business applications. Their RIDL product is a language designed specifically to support multi-agent systems.
- RIDL - a programming language from Agent Business Force which is for multi-agent systems what C++ was for object-oriented systems. RIDL is a computer language that supports agents with the right keywords, concepts and language constructs. With RIDL, you no longer need to reduce your agents to objects. What's more, RIDL doesn't throw away the old. It is not because you have agents, that you no longer need objects. RIDL is unique in the way it blends agents and objects. When it comes to agent-oriented software engineering (AOSE), RIDL is to Java what C++ was to C.
- Axeda Agents - a family of products that provide intelligence at the device level within the distributed architecture of the Axeda Device Relationship Management System™ (DRM). Axeda Agents are available in two forms, a library of portable C-code that can be embedded in small footprint systems, and as a server that provides local intelligence on larger systems. Both provide two-way, Firewall-Friendly™ monitoring, communications and control of device data and events in real time. Axeda Agents are what enable hundreds to millions of remote devices to communicate, via the Internet, to the Axeda Enterprise™ server. Axeda Agent Embedded provides the base set of communication services used to establish and maintain secure communication between Axeda Enterprise and the device. Axeda Agent adds rule-based embedded intelligence to eliminate the need to send all of the available information across the Internet for processing, reducing the amount of communication bandwidth required and allowing the Axeda DRM™ system to operate even if the connection is temporarily unavailable. Business rules that define how the Axeda Agent operates are created using the graphical Axeda Builder™ tool, which enables creation, deployment, and remote administration of Axeda Agent projects.
- EXceed SNx - Uses intelligent software agents to monitor a company's supply networks providing them with C3i or Command, Control, Communications and Intelligence over the network. Automating the handling of 80 percent of a company's supply chain exceptions will enable them to reduce cost and focus energies and resources on eliminating the 20 percent of exceptions that can't be automated.
- Software Agents In Business: Still An Experiment by Navi Radjou of Forrester Research dated March 27, 2003 - first brief in the Software Agents In Business series. Although limited today, the commercial adoption of applied software agents is poised to grow as firms look to make their business processes flexible and manage them by exception.
- Software Agents In Business: Steady Adoption Curve by Navi Radjou of Forrester Research, dated May 13, 2003 - second brief in the Software Agents In Business series. Firms' adoption of applied software agents will evolve in stages over the next decade, supported by standards and technologies like Web services and the Semantic Web.
- Adaptive Agents Boost Supply Network Flexibility by Navi Radjou of Forrester Research, dated March 11, 2002 - this brief discusses how manufacturers migrating to adaptive supply networks will exploit intelligent-agent technology to detect and resolve operational glitches proactively. Decentralized organizations with a partner-friendly mindset will benefit most.
- Agents As Catalysts for Economic Change and Beyond, By Sally J Cusack, Stephen D Hendrick - article from the January 2001 issue of Application Development Trends magazine that lays out the case for software agent technology to create a more efficient means of conducting e-business and posits that the implications of agent technology go far beyond mere buying and selling. As researchers at leading technology companies and world-class universities continue to explore the potential uses and limitations of software agents in today's society, the possibility that they could serve as a catalyst for new economic models in a global economy becomes clearer. Although somewhat dated, the rationale from the article is still worth reading. The authors are/were with market researcher IDC.
- XAT Solutions, Inc. (eXchange Agent Technology) - focuses on Business Execution Management, which is the optimization of business processes in real-time when actual events deviate from planned events. XAT has developed a unique multi-agent architecture to manage large, complex, dynamic businesses. Some of the distinguishing attributes that set XAT software apart from competition are automated intelligent decision making, real-time performance and the use of smart heuristics. XAT’s technology enables enterprises to automate and optimize the execution of their business processes in real-time under the dynamic “non-linear” conditions that prevail in real world business environments. XAT uses a highly Distributed form of Artificial Intelligence (DAI) implemented with a hierarchical multi-agent architecture. Complex intractable problems are decomposed into small, simple problems that are much easier to solve, and allowing intelligent decisions to be made locally and concurrently overcomes the limitations inherent in any system with centralized monolithic architecture. The extensible nature of the hierarchical architecture allows systems to evolve and scale over time by starting with low-level agents initially and gradually adding higher-level agents as needed. Allowing “thin” agents to make quick decisions locally instead of depending on a central engine with long latency ensures real-time performance. XAT agents can be distributed over multiple servers in order to maintain real-time performance as the system scales up.
- UltraLog - a Defense Advanced Research Projects Agency (DARPA) sponsored research project focused on creating survivable large-scale distributed agent systems capable of operating effectively in very chaotic environments. The project is pursuing the development of technologies to enhance the security, robustness, and scalability of large-scale, distributed agent-based systems operating in chaotic wartime environments. The objective of the UltraLog project is to create a comprehensive capability which will enable a massive scale, trusted, distributed agent infrastructure for operational logistics to be survivable under the most extreme circumstances. The grand challenge of the UltraLog project is to extend the Cougaar cognitive agent architecture using a layered, integrated approach with technologies in robustness, security, stability and scalability. The program will focus on research, development, evaluation, and demonstration of a prototype, distributed society of over 1000 medium complexity agents operating under directed adversary kinetic and Information Warfare attack. UltraLog's goal is to operate with up to 45% information infrastructure loss in a very chaotic environment with not more than 20% capabilities degradation and not more than 30% performance degradation for a period representing 180 days of sustained military operations in a major regional contingency.
- ABLE (Agent Building and Learning Environment) - a Java framework, component library, and productivity tool kit for building intelligent agents using machine learning and reasoning. The ABLE research project is made available by the IBM T. J. Watson Research Center. The ABLE framework consists of a set of core JavaBeans called AbleBeans and a set of function-specific JavaBeans called AbleAgents. Application-level agents (JavaBeans) can be constructed out of these components using the Able Editor or any standard bean builder environment. The core AbleBeans include beans for reading and writing data from text files, for data transformation and scaling using templates, for rule-based inferencing using boolean and fuzzy logic, and for neural network learning including back propagation and self-organizing maps. The function-specific AbleBeans include agents for classification, clustering, prediction, and genetic search.
- Business Rules for E-Commerce (BREC) - a research project at at IBM T. J. Watson Research Center investigating rule-based business processes for e-commerce: both business-to-business (B2B), e.g., to integrate supply chains; and business-to-consumer (B2C). The overall mission is to develop technology that is highly reusable and easy to integrate with a broad spectrum of networked applications. The project prototypes applications in tandem with developing reusable componentry and also contributes to company-wide efforts in strategy and in common architecture, e.g., for inter-agent knowledge-level communication and inter-operability. The reusable technology for business rules and rule-based intelligent agents is embodied as an extensible structured Java library, called CommonRules (formerly called DIPLOMAT; follow-on to RAISE and Agent Building Environment implemented in C++). An alpha prototype of CommonRules has been released (free with trial license) on the Web, at AlphaWorks. You can see the overview of the CommonRules 1.0 release of July 30, 1999. [Note: the project web page does not appear to have been updated since August 9, 1999, but may still be of some interest.]
- Intelligent Agents project (1994-97) at IBM T.J. Watson Research Center - the IBM Agent Building Environment (ABE) developer's toolkit product alpha, available 1996-1998 on IBM's AlphaWorks, is no longer being distributed, because it is no longer being supported and maintained actively as a code base. It has a follow-on, however: CommonRules, a Java library from the Business Rules for E-Commerce project (BREC).
- Information Economies - research effort at IBM focused on the evolution of the Internet towards an open, free-market information economy of software agents buying and selling a rich variety of information goods and services. They envision the Internet some years hence as a seething milieu in which billions of economically-motivated software agents find and process information and disseminate it to humans and, increasingly, to other agents. Agents will naturally evolve from facilitators into decision-makers, and their degree of autonomy and responsibility will continue to increase with time. Ultimately, transactions among economic software agents will constitute an essential and perhaps even dominant portion of the world economy.
- Agent-Based Software Development - acts as an extension of the Agent-Based Software Development book. It provides information about the book as well as links to the various web resources referred to by the book. The links are divided according to the chapters in the book and can be accessed by going to the contents page. Of particular interest is the resources section, which provides links to the most relevant agent-related events, publications and websites.
- "AgentSpeak(L): BDI Agents speak out in a logical computable language" - a classic paper that discusses an abstract language for reactive planning systems.
- Moise+ - an organizational model for multiagent systems based on notions like roles, groups, and missions. It enables a MAS to have an explicit description of its organization.
- SACI (Simple Agent Communication Infrastructure) - enables distributed agents to communicate in a easy way. It is a Java API and a set of tools that can be used in order to help the development of societies of distributed agents. Agents are identified by a name and grouped in societies according to an organizational model (Moise+) and communicate through KQML messages. They can send messages to others agents just using receiver's name. The location in the network is made transparent to the sender by a Facilitator (white pages service). Agents might know others by a yellow pages service. Agents can register their services with facilitator and query this facilitator to find out what services are offered by which agents. Agents can be implemented as applets and can run on web browsers.
- Jason (Java-based agentSpeak interpreter used with saci for multi-agent distribution over the net) - the first fully-fledged interpreter for an extended version of AgentSpeak, including also speech-act based inter-agent communication. Using Saci, a Jason multi-agent system can be distributed over a network effortlessly. Various ad hoc implementations of BDI systems exist, but one important characteristic of AgentSpeak is its theoretical foundation; work on formal verification of AgentSpeak systems is also underway. Jason is implemented in Java (thus multi-platform); various customisation of agent features can be done in Java. Another important characteristic of Jason in comparison with other BDI agent systems is that it is available as Open Source under GNU LGPL.
- RealDialog Agent (from LiveWire Logic) - an engaging automated agent, enabling any customer or employee-facing Web site to automatically respond to end user questions with immediate and relevant answers. A RealDialog Agent can correctly answer the vast majority of user questions, reducing stress on all support touch points and greatly lowering the cost structure of customer support and call centers, while significantly improving customer satisfaction. A RealDialog Agent answers customer queries or problems through friendly and interactive text-based conversations as opposed to static FAQs and cumbersome searches - the result of keyword or pattern-matching approaches - resulting in much higher customer satisfaction ratings.
- JASA (Java Auction Simulator API) - a high-performance auction simulator that allows researchers in agent-based computational economics (ACE) to run trading simulations using a number of different auction mechanisms. Development thus far has concentrated on variants of the double-auction -- a type of auction in which we allow multiple sellers as well as multiple buyers. This type of auction is used to run a variety of real-world marketplaces, such as stock markets and futures markets, and the fact that it allows both supply-side and demand-side to be modeled means that it is an effective tool for studying the microeconomics of marketplaces with small numbers of traders where strategic interaction means that neoclassical equilibrium theory breaks down. The software is designed to be highly extensible, so that new auction rules can easily be implemented. The software also provides base classes for implementing simple adaptive trading agents. It was developed for research carried out at the Agent Applications, Research and Technology group of Liverpool University.
- The Prometheus Methodology - a detailed process for specifying, designing, and implementing intelligent agent systems. The goal is to have a process with defined deliverables which can be taught to industry practitioners and undergraduate students who do not have a background in agents and which they can use to develop intelligent agent systems. Prometheus distinguishes itself from other methodologies by supporting the development of intelligent agents, providing "start-to-end" support, having evolved out of practical industrial and pedagogical experience, having been used in both industry and academia, and, above all, in being detailed and complete. Prometheus is also amenable to tool support and provides scope for cross checking between designs. The methodology consists of three phases: system specification, architectural design, and detailed design.
- TROPOS (and TROPOS) - An Agent-Oriented Software Development Methodology for building agent oriented software systems. Tropos is based on two key ideas. First, the notion of agent and all the related mentalistic notions (for instance: goals and plans) are used in all phases of software development, from the early analysis down to the actual implementation. Second, Tropos covers also the very early phases of requirements analysis, thus allowing for a deeper understanding of the environment where the software must operate, and of the kind of interactions that should occur between software and human agents.
- RedfishGroup - a loosely-coupled organization of complexity researchers, software developers and business professionals applying the emerging science of Complex Adaptive Systems to difficult problems in business and government. RedfishGroup was founded in 1991 by Stephen Guerin and is currently based in Santa Fe, New Mexico. Some of their interests include self-organizing systems design, 3d interactive visualization, agent-based modeling, and peer2peer network design.
- Agent-Based Systems and Agent-Based Modeling at NuTech Solutions, Inc. - Agent-based simulations can provide valuable information about the dynamics of the real-world system that they emulate. As widely varied individual agents interact in the model, the simulation shows how their collective behaviors govern the performance of the entire system - for instance, the emergence of a successful product or an optimal schedule. These simulations are powerful strategic tools for "what-if" scenario analysis: as managers change agent characteristics or "rules," the impact of the change can be easily seen in the model output. Perhaps most important, the computer can generate strategies that the user might never have considered.
- XML.org - an industry web portal formed and introduced in June 1999 by OASIS, the XML interoperability consortium, to minimize overlap and duplication in XML languages and standard initiatives by providing public access to XML information and schemas in a centralized repository. Today, XML.org has expanded its reach and has emerged as a centralized XML portal that serves as a valuable resource and meeting place for technologists, developers and businesspeople designing and implementing purpose-built XML languages.
- Business Process Execution Language for Web Services (BPEL4WS) - a notation for specifying business process behavior based on Web Services. Processes in BPEL4WS export and import functionality by using Web Service interfaces exclusively. Business processes can be described in two ways. Executable business processes model actual behavior of a participant in a business interaction. Business protocols, in contrast, use process descriptions that specify the mutually visible message exchange behavior of each of the parties involved in the protocol, without revealing their internal behavior. The process descriptions for business protocols are called abstract processes. BPEL4WS is meant to be used to model the behavior of both executable and abstract processes. BPEL4WS provides a language for the formal specification of business processes and business interaction protocols. By doing so, it extends the Web Services interaction model and enables it to support business transactions. BPEL4WS defines an interoperable integration model that should facilitate the expansion of automated process integration in both the intra-corporate and the business-to-business spaces.
- BPMI.org (the Business Process Management Initiative) - a non-profit corporation that empowers companies of all sizes, across all industries, to develop and operate business processes that span multiple applications and business partners, behind the firewall and over the Internet. The Initiative's mission is to promote and develop the use of Business Process Management (BPM) through the establishment of standards for process design, deployment, execution, maintenance, and optimization. BPMI.org develops open specifications, assists IT vendors for marketing their implementations, and supports businesses for using Business Process Management technologies.
- Business Process Modeling Language (BPML) - a meta-language for the modeling of business processes, just as XML is a meta-language for the modeling of business data. BPML provides an abstracted execution model for collaborative & transactional business processes based on the concept of a transactional finite-state machine. BPML considers e-Business processes as made of a common public interface and as many private implementations as process participants. This enables the public interface of BPML processes to be described as ebXML business processes or RosettaNet Partner Interface Processes, independently of their private implementations.
- Business Process Modeling Notation (BPMN) - a specification for a graphical notation for expressing business processes in a Business Process Diagram (BPD). The BPMN specification also provides a binding between the notation's graphical elements and the constructs of block-structured process execution languages, including BPML and BPEL4WS.
- Business Process Query Language (BPQL) - a management interface to a business process management infrastructure that includes a process execution facility (Process Server) and a process deployment facility (Process Repository). The BPQL interface to a Process Server enables business analysts to query the state and control the execution of process instances managed by the Process Server. This interface is based on the Simple Object Access Protocol (SOAP). The BPQL interface to a Process Repository enables business analysts to manage the deployment of process models managed by the Process Repository. This interface is based on the Distributed Authoring and Versioning Protocol (WebDAV). Process models managed by the Process Repository through the BPQL interface can be exposed as UDDI services for process registration, advertising, and discovery purposes.
- Web Service Choreography Interface (WSCI) - an XML-based interface description language that describes the flow of messages exchanged by a Web Service participating in choreographed interactions with other services. WSCI describes the dynamic interface of the Web Service participating in a given message exchange by means of reusing the operations defined for a static interface. WSCI works in conjunction with the Web Service Description Language (WSDL), the basis for the W3C Web Services Description Working Group; it can, also, work with another service definition language that exhibits the same characteristics as WSDL. WSCI describes the observable behavior of a Web Service. This is expressed in terms of temporal and logical dependencies among the exchanged messages, featuring sequencing rules, correlation, exception handling, and transactions. WSCI also describes the collective message exchange among interacting Web Services, thus providing a global, message-oriented view of the interactions. WSCI does not address the definition and the implementation of the internal processes that actually drive the message exchange. Rather, the goal of WSCI is to describe the observable behavior of a Web Service by means of a message-flow oriented interface. This description enables developers, architects and tools to describe and compose a global view of the dynamic of the message exchange by understanding the interactions with the web service.
- Extensible Mobile Agent Architecture (EMAA) - a Lockheed Martin DARPA project to provide a rich component framework to develop or integrate distributed systems using autonomous mobile agents. The central component for EMAA is the agent Dock, which acts as a daemon process within a Java Virtual Machine (JVM) and supplies the hosting infrastructure and foundation for software agents and services. Mechanisms for reliable agent migration and authentication among Docks, as well as service lookup and discovery, are built into the framework.
- Interoperable Intelligent Agent Toolkit (I2AT) - a Lockheed Martin DARPA project to reduce by an order of magnitude the effort to create and maintain CoABS Grid-aware agent applications and thus to further the transition of DARPA agent technology and the CoABS Grid in particular. Beyond prototype applications, which are typically developed by the research community, successful CoABS agent and Grid technology transition must address how non-researchers may use the technology without having to be an expert in the particular field. The project calls for a tool that makes creating agents as simple as defining calculations in a spreadsheet. This simplification will lead to the ability to develop complex agent-based system measurably faster and the ability to configure and modify existing agent-based applications to reflect changing operational needs and added requirements.
- Affective Computing at the MIT Media Lab - Affective computing is computing that relates to, arises from, or deliberately influences emotions. Research focuses on creating personal computational systems endowed with the ability to sense, recognize and understand human emotions, together with the skills to respond in an intelligent, sensitive, and respectful manner toward the user and his/her emotions. We are also interested in the development of computers that aid in communicating human emotions, computers that assist and support people in development of their skills of social-emotional intelligence, and computers that "have" emotional mechanisms, as well as the intelligence and ethics to appropriately manage, express, and otherwise utilize these "emotions." Mechanisms of emotion will be needed to build "human-centered" machines, which are able to respond intelligently and sensitively to the complex and unpredictable situations common to human-computer interaction. Affective computing research aims to make fundamental improvements in the ability of computers to serve human users, including reducing the frustration that is prevalent in human-computer interaction.
- Telescript - a programming language and platform produced by General Magic (vintage 1995, now defunct) for mobile agents which can move themselves around in computer networks to "do their job". This paper describes how Telescript agents can be created and controlled via ordinary web browsers and how they can interact with Java applets. [Please let me know if you have a better link.]
- MECCA (Multi-agent Environment for Constructing Cooperative Applications) - a Java-based platform for software agents developed by Siemens researchers. [Please let me know if you have a better link.]
- Firefly - a pioneering commercial effort (acquired by Microsoft and later shutdown) by Professor Pattie Maes of the MIT Media Lab to exploit collaborative filtering based on the earlier HOMR (Helpful Online Music Recommendations) project. [Please let me know if you have better links.]
- BotTechnology.com - a portal site for the development of Bot Technology, Intelligent Agent protocols and algorithms as well as the language and code necessary to make all this happen. The mission is to bring together all the necessary resources on the Internet to create Bots and Intelligent Agents that will be relevant to all aspects of our daily lives. The purpose of the site will be to be the ombudsman between the bot and intelligent agent developer and the ultimate end users. Their intent is to become the Internet's infomediary for the creation, design, research and implementation of bots and intelligent agents on the Internet as well as on Intranets and Extranets. They also offer consultative services in the design, research and evaluation of bots and intelligent agents. Their goal is to listen to what you want in the technology arena of bots, intelligent agents, data mining and knowledge discovery on the Internet.
- Magenta Technology - a commercial firm dedicated to the development of Multi-Agent Systems for enterprise computing, was established in 1999 in order to build commercially viable technology based upon the concepts of Multi-Agent Systems. Magenta develops next generation solutions and services through 3 main activities: 1) Supply Chain Execution and Logistics Components (Network Scheduler and Network Designer), 2) Magenta Technology Platform (engines, toolsets and knowledge engineering resources to extend the existing products or to use as a base for building custom applications), and 3) Licensing Intellectual Property for industrial use. Their platform includes an Ontology Manager, a Negotiation Engine, and support for a Virtual Market.
[ Home | Blog | Books | Glossary | Links | Manifesto | Search | Contact | Pre-2001 | 2001 | 2002 | 2003 | 2004 | 2005 ]
L3xicon.com - a web thesaurus and lexicon listing agtivity.com under software agent, intelligent agent and agent.
Updated: January 29, 2006 07:54:58 PM -0500
Copyright © 2006 John W. Krupansky d/b/a Base Technology