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 | Links | Glossary | Software Agent Manifesto | Pre-2001 | 2001 | 2002 | 2003 | 2004 | 2005 ]
| Please let us know if you wish to add (or change) a link. Click here. |
- iSOCO (Intelligent Software Components, S.A. - "intelligent software for the networked economy") - a company founded in 1999 by a group of researchers from the Artificial Intelligence Research Institute (IIIA) of the Spanish Scientific Research Council (CSIC), located at the Campus of the Autonomous University of Barcelona (UAB), with the idea of transferring its research to the market, taking advantage of its sound knowledge of Artificial Intelligence (AI) and Component Based Development (CBD).
- Whitestein Technologies ("the Software Agent Company") - a Switzerland-based company that specializes in the design and development of advanced agent-based systems, applications, and technologies, combined and well integrated with other advanced information and communication technologies (eg. mobile wireless computing) and current state-of-the-art technologies (eg. Java J2EE).
- AgentLand ("Get smart, Get an Agent") - offers information, download, and assistance for Intelligent Agents for the internet: Monitoring agents, information research agents, price comparison agents, chatterbots, virtual assistants etc.
- TAC Trading Agent Competition - an international forum designed to promote and encourage high quality research into the trading agent problem. TAC trading agents operate within a travel shopping scenario, buying and selling goods to best serve their given travel clients. TAC scores the results based on the client's preferences for trips assembled, and net expenditures in the travel markets.
- ACE Agent-based Computational Economics (Department of Economics, Iowa State University) - the computational study of economies modeled as evolving systems of autonomous interacting agents.
- KIF Knowledge Interchange Format - a language designed for use in the interchange of knowledge among disparate computer systems (created by different programmers, at different times, in different languages, and so forth).
- OpenCyc - open source version of the Cyc(r) technology, the world's largest and most complete general knowledge base and commonsense reasoning engine. OpenCyc can be used as the basis for a wide variety of intelligent applications.
- Quickstep recommender system (IAM Group at University of Southampton) - a hybrid collaborative/content-based recommender system to recommend on-line research papers. Uses kNN multi-class paper classification and an ontology to enhance the profiling process.
- Foxtrot recommender system (IAM Group at University of Southampton) - evolution of the Quickstep recommender system that uses pearson-r correlation to recommend and kNN classification to profile user interests. An ontological approach is taken to represent user profiles.
- Agent Based Computing at the Intelligence, Agents and Multimedia Group (IAM) (University of Southhampton) - research areas include Models of Interaction, Agent-Oriented Software Engineering, and Applications of Agent Technology.
- Lost Wax - the European leader in the commercial application of agent technology, they develop software solutions using Java/J2EE, .NET and agent technologies.
- Agentis Software - offers a unique real-time agent computing architecture that delivers the best attributes of hard-code (ultra-scalability) and state-based eProcess systems (real-time agility) concurrently. By combining business-level process design, an application transformation system, and an innovative agent server that can retry different processes at runtime and dynamically flag situations where no discrete outcome is available, Agentis solutions also deliver the most comprehensive approach to managing business exceptions.
- LARKS Language for Advertisement and Request for Knowledge Sharing (Software Agents Group at Carnegie Mellon University Robotics Institute) - a common language for use by middle or matchmaking agents to pair service-requesting agents with service-providing agents that meet the requesting agents' requirements.
- Autonomous Agents and Multi-Agent Systems - the first scholarly journal to focus on Agent-based systems. Editor(s)-in-Chief: Nicholas Jennings, University of Southampton, Dept. of Electronics & Computer Science, UK; Katia Sycara, Carnegie Mellon University, Pittsburgh, PA, USA
- Agent ART (Applications, Research, and Technology) Group (Department of Computer Science, The University of Liverpool) - basic and applied research into intelligent autonomous agents and multi-agent systems. Research areas include Agent-Oriented Software Engineering, Argumentation, Negotiation, and Dialogue, Data Mining, Logical Foundations of Computation, and Rational Decision-Making.
- The Dead Agents Society - a reading & coffee group at the University of Liverpool, UK, which meets every two weeks to discuss the literature on autonomous software agents.
- Aglets (IBM site) - Java objects that can move from one host on the Internet to another.
- Aglets Software Development Kit (Open Source) - a framework and environment for researching and developing mobile agents in Java.
- Robust Agent-based Systems Incorporating Teams of Communicating Agents (Center for Human-Computer Communication at the Oregon Health & Science University) - research effort to develop a fault tolerant Grid-compliant multi-agent architecture based on the theory of teamwork expressed in terms of joint intentions, a multi-agent communication language with provably correct conversation protocols, and a joint action interpreter that enables a user to provide specifications for teams of agents in a high-level logical language. Projects include Adaptive Agent Architecture, Agent-Talk, and STAPLE.
- AAA Adaptive Agent Architecture (Center for Human-Computer Communication at the Oregon Health & Science University) - a specification for robust multi-brokered multi-agent systems.
- Agent-Talk (Center for Human-Computer Communication at the Oregon Health & Science University) - a research project investigating the design of an agent communication language with well-founded communicative acts and provably correct dialogue protocols.
- STAPLE Social & Team Agents Programming LanguagE (Center for Human-Computer Communication at the Oregon Health & Science University) - a research project to design, specify and implement an agent oriented programming language by building upon a formal theory of multi-agent systems (Belief, Desire, Intention, Teamwork, Persistent Teams, Maintenance Goals), a formal agent communication language based on speech act theory with provably correct semantics, and agent architectures that use some incarnation of BDI logic as formal specification of their behavior. The syntax and the logical semantics of this language include operators from modal logic, temporal logic, and dynamic logic of actions. The goals are to be able to directly execute the logical specification of an agent in this language, and logically prove the behavior of a system specified in this language.
- Autonomic Computing Systems (IBM) - An approach to self-managed computing systems with a minimum of human interference. The term derives from the body's autonomic nervous system, which controls key functions without conscious awareness or involvement.
- Autonomic Computing - article in Scientific American.
- AGEA agent-based Business Acceleration Suite - a commercial product whose goal is the "zero latency enterprise". Built on Java and XML.
- AIsland - provides a framework to build and distribute agents where mobile agents travel between different AIslands. The framework exposes objects (graphic module, audio module, neural network, fuzzy logic ...) to an agent developer, who can glue these modules together using a scripting language, initally JavaScript. The initial version builds on Java and fat clients, facilitating a Java Swing GUI and a BSF/ Rhino engine, to script against modules sitting on a JMX component bus hosted by an Avalon based micro kernel. An agent is represented by an XML document and is distributed as a JXTA Codat.
Agents contain script code, which is interpreted by an AIsland (a JXTA peer) in a secure manner.- Project JXTA - a set of open, generalized peer-to-peer protocols that allow any connected device (cell phone, to PDA, PC to server) on the network to communicate and collaborate.
- AORML - Agent-Object Relationship Modeling Language (Eindhoven University) - has a richer set of basic ontological concepts than ER, UML and AUML, allows the capture of more semantics of a domain, systematically distinguishes between external and internal models and accounts for the phenomenon of internalization, and uses reaction rules for behavior modeling.
- KSU Multiagent & Cooperative Robotics Lab (Kansas State University) - research incorporates existing methodologies and techniques from other related disciplines – including artificial intelligence, robotics, and software engineering – into an integrated agent development methodology for multiagent systems.
- agentTool - a Java-based graphical development environment to help users analyze, design, and implement multiagent systems. It is designed to support the Multiagent Systems Engineering (MaSE) methodology. The system designer defines high-level system behavior graphically using the Multiagent Systems Engineering methodology. The system design defines the types of agents in the system as well as the possible communications that may take place between agents. This system-level specification is then refined for each type of agent in the system. To refine an agent, the designer either selects or creates an agent architecture and then provides detailed behavioral specification for each component in the agent architecture.
- MaSE Multiagent Systems Engineering (at Kansas State University) - a research project attempting to define a methodology for designing and developing multi-agent systems (MAS) that draws from the legacy of object-oriented methodologies such as Rumbaugh's Object Modeling Technique (OMT) and the Unified Modeling Language (UML) by extending the concept of object-orientation to multi-agent systems.
- ALIAS Project (Intelligent Interactive Distributed Systems Group at the Vrije Universiteit Amsterdam) - studies the legal and technical implications of the use of software agents. In this project the research areas of Computer Science, Artificial Intelligence, and Law are combined to analyse legal possibilities and limitations of agent technology and so be able to try and find technical solutions to meet legal requirements. The aim of this project is to provide guidelines for both AI-researchers and Legal-researchers.
- Conscious Software Research Group (University of Memphis) - focuses on the design and implementation of conscious software agents which are autonomous agents with human-like cognitive capabilities (cognitive agents) that operate under the constraints of the global workspace theory of consciousness. The architectures and mechanisms that underlie consciousness and intelligence in humans can be expected to yield information agents that learn continuously, that adapt readily to dynamic environments, and that behave flexibly and intelligently when faced with novel and unexpected situations.
- TrademarkBots.com - offers a single-source Trademark Intelligence Service. It actively and continuously monitors intelligence on trademarks, famous names and celebrities among hundreds of online sources from the visible and invisible web, including trademark databases, domain names databases, newspapers, publications, catalogs, webfeeds, Usenet groups, message boards and specialty databases for the US pharmaceutical industry.
- The Semantic Web - a vision: the idea of having data on the web defined and linked in a way that it can be used by machines not just for display purposes, but for automation, integration and reuse of data across various applications.
- Resource Description Framework (RDF) is a foundation for processing metadata; it provides interoperability between applications that exchange machine-understandable information on the Web. RDF emphasizes facilities to enable automated processing of Web resources. RDF can be used in a variety of application areas; for example: in resource discovery to provide better search engine capabilities, in cataloging for describing the content and content relationships available at a particular Web site, page, or digital library, by intelligent software agents to facilitate knowledge sharing and exchange, in content rating, in describing collections of pages that represent a single logical "document", for describing intellectual property rights of Web pages, and for expressing the privacy preferences of a user as well as the privacy policies of a Web site. RDF with digital signatures will be key to building the "Web of Trust" for electronic commerce, collaboration, and other applications.
- Web-Ontology (WebOnt) Working Group - chartered to design a Web ontology language, that builds on current Web languages that allow the specification of classes and subclasses, properties and subproperties (such as RDFS), but which extends these constructs to allow more complex relationships between entities including: means to limit the properties of classes with respect to number and type, means to infer that items with various properties are members of a particular class, a well-defined model of property inheritance, and similar semantic extensions to the base languages.
- MIT Media Lab Software Agents Group - investigates computer systems to which one can delegate tasks. Software agents differ from conventional software in that they are long-lived, semi-autonomous, proactive, and adaptive. The group develops techniques and builds prototype agent systems that can be tested.
- Autonomous Agents Conference - Agents (adaptive or intelligent agents and multi-agent systems) are one of the most prominent and attractive technologies in Computer Science at the beginning of the new century. Agent and MAS technologies, methods, and theories are currently contributing to many diverse domains such as information retrieval, user interface design, robotics, electronic commerce, computer mediated collaboration, computer games, education and training, smart environments, ubiquitous computers, social simulation, etc. They are not only a very promising technology, they are emerging as a new way of thinking, a conceptual paradigm for analyzing problems and for designing systems, for dealing with complexity, distribution and interactivity, and perhaps a new perspective on computing and intelligence. Yet to realize this promise further advances are required in agent architectures, languages, theories, and design techniques. This joint conference combines three conferences: Autonomous Agents, Multi-Agent Systems, and Agent Theories, Architectures, and Languages.
- Intelligent Software Agents Lab (Carnegie Mellon University Robotics Institute) - envisions a world in which autonomous, intelligent software programs, known as software agents, undertake many of the operations performed by human users of the World Wide Web, as well as a multitude of other tasks. They have developed the RETSINA multi-agent system infrastructure and has applied that infrastructure and its agents to many domains, including financial portfolio management, personalized web information management, book-buying auctions, logistics planning in military operations; and wireless, mobile communications.
- RETSINA (Software Agents Group at Carnegie Mellon University Robotics Institute) - an open multi-agent system (MAS) that supports communities of heterogeneous agents. The RETSINA system has been implemented on the premise that agents in a system should form a community of peers that engage in peer to peer interactions. Any coordination structure in the community of agents should emerge from the relations between agents, rather than as a result of the imposed constraints of the infrastructure itself. In accordance with this premise, RETSINA does not employ centralized control within the MAS; rather, it implements distributed infrastructural services that facilitate the interactions between agents, as opposed to managing them.
- Tryllian Agent Development Kit (ADK) - a commercially available agent development toolkit that allows Java Developers to easily build, deploy and manage secure, large-scale distributed solutions that operate regardless of location, environment or protocol, enabling an adaptive, dynamic response to changes. It is a component-based development platform that features dynamic tasking and peer-to-peer architecture and offers solutions for distributed computing that are secure, flexible, adaptive, scaleable and fault tolerant.
- Agent Technology at HP Labs (agents@hp labs) - describes a range of active research projects within HP Labs that fall under the collective description of agent technology. Current research interests include e-commerce negotiation, artificial life, and agents for personalisation, identity and privacy on the web.
[ Home | Blog | Books | Links | Glossary | Software Agent Manifesto | 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 07:57:00 PM -0500
Copyright © 2006 John W. Krupansky d/b/a Base Technology