These are web resources that we believe are reasonably current (or of significant historical value) for software agent technology, including software agents, intelligent agents, intelligent software agents, autonomous agents, multi-agent systems (MAS), agent technology, agent-based computing, and topics in artificial intelligence and the Semantic Web that are deemed relevant to software agents.
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.
Note: This list is now segmented by year since it became too long for Google to properly index!
[ Home | Blog | Books | Links | Glossary | Software Agent Manifesto | Pre-2001 | 2001 | 2002 | 2003 | 2004 | 2005 | 2006 ]
| Please let us know if you wish to add (or change) a link. Click here. |
- Web Intelligence Consortium (WIC) - an international, non-profit organization dedicated to advancing world-wide scientific research and industrial development in the field of Web Intelligence (WI). Web Intelligence (WI) has been recognized as a new direction for scientific research and development to explore the fundamental roles as well as practical impacts of Artificial Intelligence (AI) (e.g., knowledge representation, planning, knowledge discovery and data mining, intelligent agents, and social network intelligence) and advanced Information Technology (IT) (e.g., wireless networks, ubiquitous devices, social networks, wisdom Web, and data/knowledge grids) on the next generation of Web-empowered products, systems, services, and activities. It is one of the most important as well as promising IT research fields in the era of Web and agent intelligence.
- A Taxonomy Primer from Lexonomy - Taxonomies…thesauri…classification systems…synonym rings. We’ve heard all of these terms in the context of the Web. As Web sites expand, the task of organizing them has become increasingly problematic and complex. All of the terms mentioned above are controlled vocabularies. That means that they are organized lists of words and phrases, or notation systems, that are used to initially tag content, and then to find it through navigation or search. Unfortunately, a great deal of disagreement exists as to the individual definitions of each of the terms mentioned above; we spend too much of our valuable time misunderstanding each other. The terminology is in flux; hopefully, at some point, specific definitions will be standardized. Until then, we need to focus on the possibilities of various types and levels of controlled vocabulary. Frankly, the specific terminology isn’t nearly as important as knowing what each example can accomplish, and be used most effectively.
- Singularity Institute for Artificial Intelligence, Inc. (SIAI) - based on the concepts behind Ray Kurzweil's book The Singularity Is Near : When Humans Transcend Biology, SIAI was founded for the pursuit of ethically enhanced cognition by creating beneficial AI. SIAI expects the ethical and significant enhancement of cognition will help solve contemporary challenges - disease and illness, poverty and hunger - more readily than other charitable pursuits. SIAI envisions a world where ethical cognitive enhancement creates immense benefit, including the end to many present calamities. SIAI expects that stepping beyond present human cognition will help overcome numerous humanitarian challenges, such as 20 million children dying from starvation each year, 680 million people with an illness, 3 billion still living in poverty, and countless other afflictions. SIAI seeks to be a force for effective philanthropy within a wider movement of people dedicated to understanding how they can maximize the benefit of their choices.
- Web Service Modeling Ontology (WSMO) Working Group - their mission is to create a Web Service Modeling Ontology (WSMO) for describing various aspects of Semantic Web Services. By exhaustively deploying WSMO, they aim to solve the integration problem. The main features of WSMO – simplicity (a solution to the integration problem that is as simple as possible), completeness (solves all aspects of the integration problem), executability (a set of execution semantics exists as well as a reference implementation) - should provide a world-wide standard, which will be developed together with industrial partners and other research groups, and will be aligned with many different research projects. The pillars of the project will be provided by the Web Service Modeling Framework (WSMF), which serves as a conceptual basis that will be further developed in the course of the project. Moreover, they shall align with current available initiatives and standards that try to address similar problems and overcome drawbacks in existing approaches. The case studies for showcasing the Web Service Modeling Ontology will be based on different applications areas: tourism, banking, marketplace, supply chains, etc., These case studies will be based on the requirements of different industrial partners and research groups joining this initiative. They aim to develop an ontology that can be easily used by research groups, research projects, software developers and user communities in the Semantic Web area.
- Knowledge Media Institute (KMi) at the Open University - was set up in 1995 in recognition of the need for the Open University to be at the forefront of research and development in a convergence of areas that impacted on the OU's very nature: Cognitive and Learning Sciences, Artificial Intelligence and Semantic Technologies, and Multimedia. They chose to call this convergence knowledge media. Knowledge Media is about the processes of generating, understanding and sharing knowledge using several different media, as well as understanding how the use of different media shape these processes. KMi operates with reference to a number of basic tenets, which define the context in which they formulate and pursue their research objectives:
Strategic Threads. Their research is aligned with a number of broad strategic threads, currently Narrative Hypermedia, Knowledge Management, Social Software, New Media Systems and Semantic Web and Knowledge Services. These themes have not come about by chance, but represent the collective view of KMi researchers on the research issues that are important to the overarching mission of the Institute.
Learning. In keeping with a lifelong learning perspective, their research agenda takes a broad definition of learning, embracing distance learning, learning in the classroom, and learning in the workplace.Real Systems, Real Users. To demonstrate that technologies work requires that they be grounded (in authentic work contexts, with genuine user communities), and interdisciplinary: hence their mix of computer science, knowledge representation, cognitive science, sociology, human-computer interaction, multimedia, and the visual arts. KMi has an enviable track record in deploying and evaluating knowledge media both in the commercial world and in the wider community.
Generic Technologies. Although a small proportion of their work produces discipline-specific solutions, most of their technologies are generic in nature, designed to be customised for different fields, learning contexts and learners. KMi is a world-class R & D centre at the leading edge of web, semantic, learning and new media technologies. Over the years they have come to embody the unique character of the Open University, the world's largest distance teaching institution, in the world of innovation and technology research.- OCML modelling language (Operational Conceptual Modelling Language) - supports the construction of knowledge models by means of several types of constructs. It allows the specification and operationalization of functions, relations, classes, instances and rules. It also includes mechanisms for defining ontologies and problem solving methods, the main technologies developed in the knowledge modelling area. About a dozen projects in KMi are currently using OCML to provide modelling support for applications in areas such as knowledge management, ontology development, e-commerce and knowledge based system development. OCML modelling is also supported by a large library of reusable models, providing a useful resource for the knowledge modelling community. This library can be accessed through the WebOnto editor.
- Agent Technology Group at the Czech Technical University in Prague- a research team focusing on various issues of distributed cooperation in multi-agent systems and their applications. In their research, they emphasize the practical orientation and verify their theoretical conclusions on fully-fledged multi-agent systems. Their work is practically oriented and aims to solve real problems of current and future systems. Core competencies of ATG include: production planning, simulation, supply-chain management and virtual organizations, cooperation in environments with communication inaccessibility and communication optimization in general, security, trust, social structures and collaboration in adversarial environments, meta-reasoning in multi-agent systems, development and maintenance of A-globe agent platform, and development of agent systems based on A-globe and Jade agent platforms. ATG participates in numerous European and International projects and is supported by EU, US, and Czech funding, as well as by industrial contracts. Besides their research activities, they teach several specialized subjects for CTU students.
- The Impermanence Agent - explores a model for literature/art that is specific to the Internet-connected personal computer and a peripheral model of attention. It is not like a book, which we pick up and read. It is not like a painting, which we visit and inspect. It is not like a hypertext artwork, on which we click. And, similarly, it is not like a story on a Web page, a picture on a Web page, a Web-based hypertext, or any other stand-alone artwork that is intended for our full attention. Instead, The Impermanence Agent is an artwork that operates as functions of the user's Web browser. The browser is approached as a daily computer tool, in which the artwork becomes a peripheral part of the daily browsing experience. When The Agent is engaged, user browsing causes a story to be told. This story is experienced in a corner of the PC screen, over a period measured in days rather than minutes. And while it is presented in a small Web browser window, The Agent's story does not act as other Web content. It will only move forward as the user clicks on other Web sites (those not associated with The Agent), and there is no way in which to "click on" or navigate The Agent's content directly. Simultaneously, The Agent monitors the user's Web traffic, and here takes on the semi-autonomous character from which parallels with more traditional software agents (discussed below) can be drawn. The Impermanence Agent continually alters its story using material from the user's browsing (and occasionally intervenes in browsing itself). Over the time The Agent's story is told, the story's contents are altered until they are nearly entirely determined by browsing actions of the individual reader.
- Swarm.org and SwarmWiki - a software package for multi-agent simulation of complex systems, originally developed at the Santa Fe Institute. Swarm is intended to be a useful tool for researchers in the study of agent based models. Swarm software comprises a set of code libraries which enable simulations of agent based models to be written in the Objective-C or Java computer languages. These libraries will work on a very wide range of computer platforms. The basic architecture of Swarm is the simulation of collections of concurrently interacting agents: with this architecture, we can implement a large variety of agent based models.
Towards a Semantic Web for Culture by Kim H. Veltman - Today’s semantic web deals with meaning in a very restricted sense and offers static solutions. This is adequate for many scientific, technical purposes and for business transactions requiring machine-to-machine communication, but does not answer the needs of culture. Science, technology and business are concerned primarily with the latest findings, the state of the art, i.e. the paradigm or dominant world-view of the day. In this context, history is considered non-essential because it deals with things that are out of date. By contrast, culture faces a much larger challenge, namely, to re-present changes in ways of knowing; changing meanings in different places at a given time (synchronically) and over time (diachronically). Culture is about both objects and the commentaries on them; about a cumulative body of knowledge; about collective memory and heritage. Here, history plays a central role and older does not mean less important or less relevant. Hence, a Leonardo painting that is 400 years old, or a Greek statue that is 2500 years old, typically have richer commentaries and are often more valuable than their contemporary equivalents. In this context, the science of meaning (semantics) is necessarily much more complex than semantic primitives. A semantic web in the cultural domain must enable us to trace how meaning and knowledge organisation have evolved historically in different cultures.
- Neurosphere - The Human-Human Interface - The idea is that the Internet and related technologies, Network Infrastructure, connect more and more people. The interfaces between humans and technology, Personal Infrastructure, in turn can help bring us closer to each other. The combination of personal and network infrastructure leads us to a broader and more immediate awareness of The World Right Now. And finally, images and approaches to Wholeness are the goal - the place where technology turns out to have a spiritual component.
- Noosphere - website for integrative thinking about the future of human interaction. The Noosphere Website is to be seen as a part of the evolution of mankind towards a more synergetic world, characterized by integral approach, free and constructive interaction and Peer to Peer cooperation. From this progressive intellectual integration, the Noosphere is gradually emerging.
- Parallel Simulation Technology LLC - sells hardware and software tools for agent-based control, scheduling, and simulation systems. Their customers include major corporations involved in manufacturing, transportation, utilities, and semiconductor fabrication, who are using these unique tools and techniques to solve very difficult problems. Their parallel programming language, Paracell, is used to construct these multi-agent simulation and control systems. These applications run on Parallel Simulation Technology's Parallel Inference Machine (PIM), a VME-based massively parallel real-time platform. In combination, Paracell and the PIM result in systems that are developed more quickly with significantly less source code, running in a guaranteed, predictable, and scalable environment.
- Amblit Technologies - develops next generation productivity tools and programs for consumers, web developers and enterprise software architects using state-of-the-art man-machine interfaces and the latest in intelligent multi-agent software technologies.
- Open Agent Architecture (OAA) - A framework for integrating a community of heterogeneous software agents in a distributed environment.
- Journal of Web Semantics - an interdisciplinary journal published by Elsevier based on research and applications of various subject areas that contribute to the development of a knowledge-intensive and intelligent service Web. These areas include: knowledge technologies, ontology, agents, databases and the semantic grid, obviously disciplines like information retrieval, language technology, human-computer interaction and knowledge discovery are of major relevance as well. All aspects of the Semantic Web development are covered. The publication of large-scale experiments and their analysis is also encouraged to clearly illustrate scenarios and methods that introduce semantics into existing Web interfaces, contents and services. The journal emphasizes the publication of papers that combine theories, methods and experiments from different subject areas in order to deliver innovative semantic methods and applications.
- Agents for the Masses? by Jeffrey M. Bradshaw, Mark Greaves, Heather Holmback, Tom Karygiannis, Barry Silverman, Niranjan Suri, and Alex Wong - a vintage 1999 article that looked into the issue of the rate of uptake of new research results in fielded systems being "glacially slow".
- iRobot Corporation - Founded in 1990 by roboticists from the Massachusetts Institute of Technology, iRobot designs behavior-based, artificially intelligent robots. Powered by iRobot’s unique AWARE Robot Intelligence Systems, the robots can navigate in complex and dynamic real-world situations, including navigating around furniture and searching abandoned buildings. Their robots are highly sophisticated, yet practical. These innovative robots get the job done and are easy to use. To date, more than 1.2 million iRobot Roomba Vacuuming Robots have been sold worldwide and over 200 iRobot PackBot Tactical Mobile Robots are protecting our troops in Afghanistan and Iraq.
- LogicEase Solutions, Inc. (AKA ComplianceEase) - designs, develops and provides intelligent business solutions that employ a broad range of advanced artificial intelligence technologies, including optimization algorithms, rule-based decision-making, case-based reasoning, and neural networks reasoning. In addition, they also utilize advanced Natural Language Processing technology to empower business users to understand how to apply situation-specific business rules within LogicEase's CriticalDecision systems. This capability is a powerful tool allowing clients to take timely preventive action or to act immediately when opportunities arise. LogicEase's intelligent business solutions enable clients to make innumerous critical decisions in real time as events are occurring. Such business solutions substantially enhance overall performance, including financial, while simultaneously reducing risk. Alternate URL.
- PolarLake Limited - a Dublin-based leader in standards-based incremental integration, provides a complete suite of products for implementing XML and Web Services-based solutions, including those based on the Enterprise Service Bus (ESB) architecture. PolarLake's solutions deliver code-free orchestration and mediation of software services, enabling integration solutions to be extended and re-used without extensive re-engineering. PolarLake's products deliver rapid Return on Investment by focusing on solving high value business problems with a standards-based approach capable of evolving and expanding to address the longer term objectives of the organization. Leveraging its unique Dynamic XML Runtime technology and XML Circuits application assembly framework, PolarLake's products allow customers to deliver solutions at a fraction of the normal time and cost. While addressing different requirements, each of PolarLake's products delivers: Technology integration with PolarLake's Dynamic XML Runtime, which provides a highly scalable, high performance runtime server that integrates with enterprise infrastructure such as queuing systems, management infrastructure and legacy applications, Business integration with PolarLake's data-centric XML Circuits approach, which allows developers and business users to rapidly deliver new solutions with minimum disruption to existing systems and maximum leveraging of existing assets and skills, and Unique tools that leverage existing skills to provide an intuitive XML-centric environment, and which support the software life cycle and are based exclusively on open standards.
- Talk to My Agent: Software Agents in Virtual Reality by John Horberg - ruminations about software agents, including references to synthetic agent characters in works of fiction. Vintage1995, for historical reference.
- Data Privacy Lab (Laboratory for International Data Privacy) at Carnegie Mellon University - dedicated to creating technologies and related policies with provable guarantees of privacy protection while allowing society to collect and share private (or sensitive) information for many worthy purposes.
- Numenta, Inc. - developing a new type of computer memory system modeled after the human neocortex. The applications of this technology are broad and can be applied to solve problems in computer vision, artificial intelligence, robotics and machine learning. The Numenta technology, called Hierarchical Temporal Memory (HTM), is based on a theory of the neocortex described in Jeff Hawkins' book entitled On Intelligence (with co-author Sandra Blakeslee).
- OnIntelligence.org - the companion Web site for the book On Intelligence. Hierarchical Temporal Memory (HTM), is based on a theory of the neocortex described in the book. The web site is intended as a communications tool for people interested in building intelligent memory systems and contributing to the theory presented in the book. Engineers, computer scientists and neuroscientists interested in formalizing the concepts in the book, implementing the algorithms in software and testing the theory biologically should find material of interest here.
- Center for the Study of Complex Systems at the University of Michigan - a broadly interdisciplinary program designed to encourage and facilitate research and education in the general area of nonlinear, dynamical and adaptive systems. Participating faculty represent nearly every college of the University. The Center is based on the recognition that many different kinds of systems which include self-regulation, feedback or adaptation in their dynamics, may have a common underlying structure despite their apparent differences. Moreover, these deep structural similarities can be exploited to transfer methods of analysis and understanding from one field to another. In addition to developing deeper understandings of specific systems, interdisciplinary approaches should help elucidate the general structure and behavior of complex systems, and move us toward a deeper appreciation of the general nature of such systems.
- Knowledge Web - a 4 year Network of Excellence project funded by the European Commission 6th Framework Programme to support the transition process of ontology technology from academia to industry. Alternate link.
- NetBotz, Inc. - provides IP-based monitoring solutions that protect critical assets from environmental harm such as extreme temperatures and humidity, human error and sabotage, and virtually all other threats, from power spikes to radioactive and chemical materials. This protection closes the coverage gap between traditional security solutions-"guards, guns and gates," and IT security-virus, hacker, intrusion detection, identity management-to give customers complete protection of their assets. Leveraging the affordability and ubiquity of the IP network, NetBotz provides the ability to actively monitor the environment and immediately alert about the presence of threatening conditions. The result: a customer instantly can take action to preempt potential problems, thereby reducing downtime, speeding time to recovery, without adding headcount.
- Project Halo - an effort by Vulcan Inc. towards the development of a "Digital Aristotle" -- a staged, long-term research and development initiative that aims to develop an application capable of answering novel questions and solving advanced problems in a broad range of scientific disciplines. The Digital Aristotle is being developed with a focus on two primary functions: as a tutor capable of instructing and assessing students in the sciences, and as a research assistant with broad, interdisciplinary skills to help scientists in their work.
- Multiagent and Grid Systems (MAGS) - An International Journal - a scholarly journal from IOS Press which aims to provide a timely and focal research forum for academics and practitioners in the thematic areas of Multiagent Systems, Grid Computing, Autonomic/Adaptive Computing, and their intersections. It publishes peer-refereed research and application papers of high technical quality and scientific standard. The journal features original research papers, comprehensive and sound survey papers about the state-of-the-art, technical papers about implementation issues of general interest, applications and field works. Moreover, from time to time it presents special issues on contemporary problems of profound research challenge in its thematic areas.
- Dublin Core Metadata Initiative (DCMI) - an organization dedicated to promoting the widespread adoption of interoperable metadata standards and developing specialized metadata vocabularies for describing resources that enable more intelligent information discovery systems. The mission of DCMI is to make it easier to find resources using the Internet through 1) the development of metadata standards for discovery across domains, 2) the definition of frameworks for the interoperation of metadata sets, and 3) the facilitation of the development of community- or disciplinary-specific metadata sets that are consistent with items 1 and 2. The range of activities of DCMI includes standards development and maintenance, such as organizing international workshops and working group meetings directed toward developing and maintaining DCMI recommendations, tools, services, and infrastructure, including the DCMI metadata registry to support the management and maintenance of DCMI metadata in multiple languages, and educational outreach and community liaison, including developing and distributing educational and training resources, consulting, and coordinating activities within and between other metadata communities.
- E-commerce and Agents course at University of Bath - introduces students to the principles of agents, agency, institutions and agent software development. Students will learn the factors that differentiate agents from other software systems and be able to classify agents according to their competencies. Students will be able to describe and contrast different agent architectures, platforms and approaches to agent development. Students will be able to develop simple agent-based software systems.
- WSMO (Web Service Modeling Ontology) Working Group - working group includes the WSML working group, which aims at developing a language called Web Service Modeling Language (WSML) that formalizes the Web Service Modeling Ontology (WSMO).
- Version 0.7.1 of Jason (Java-based agentSpeak interpreter used with saci for multi-agent distribution over the net) - an interpreter for a much extended version of AgentSpeak, which is a BDI logic-based agent-oriented programming language. Besides implemented in Java, Jason has various customisation and extension mechanism which make integration with Java code very easy and neat. In the sourceforge download page, besides the main Jason package you'll also find other resources. In particular, there is an example showing the access to web services from within an internal action. Various other extension (such as the use of ontological reasoning, organisational structures, and various others) are also under development. We will also provide teaching resources (e.g., slides and exercises) soon. Because of the simplicity of the basic AgentSpeak constructs, Jason is quite appropriate for under- and post-graduate teaching.
- LSDIS (Large Scale Distributed Information Systems) lab at University of Geaorgia - actively involved in research projects in the areas of Databases, Workflows, Information Integration, Web Services, and the Semantic Web initiative.
- Jackdaw - technology from Calico Jack which provides a multi-agent system that works to integrate existing services, enhance security and provide mechanisms for new applications in the mobile world. Though technically sophisticated, the concept that Jackdaw implements is simple: one user is represented in the electronic world by one agent. That agent protects the user's data, and autonomously acts on the user's behalf. A user's agent is their single point of contact to whatever services a user may wish to employ. A user's agent is always there, always contactable. Using Jackdaw means users and agents can communicate wherever and whenever: by phone, PDA, web, email, fax, TV, ...
- Acklin B.V. "Agent-Based Support" (Netherlands) - specializes in applying agent technology to business related problems in commercial projects. In its three years existence Acklin already has served several European companies with state-of-the art distributed solutions based on agent, grid and knowledge technology. These companies include insurance companies, local governments, travel agencies, transport companies, retailers, energy providers, service companies and industrials. Acklin's team is consists of highly skilled engineers, business consultants and researchers. In order to maintain its level of expertise Acklin participates in several national and international research projects. National projects include research on developing academic concepts into business applicable solutions, such as the Combined project (funded by The Dutch Ministry of Economic Affairs) which has as aim to develop agent-based solutions for complex decision-making. Furthermore, research on agent based computing and embodied conversational agents has been done in close collaboration with national universities. International projects include the projects IBROW (IST-1999-19005), mini-projects for the Agentcities initiative (IST-2000-28385) and participation in AgentLink (IST-1999-29003).
- Agent-Based Software Engineering course at University of Calgary - begins with an overview of the agent systems and software agents, then focuses on agent system architecture and infrastructure from a software engineering viewpoint, including requirements for agent-based systems, modeling and design of agent-based systems, development process for agent-based systems. Topics such as agent architecture, communication, knowledge sharing, computing and uncertainty management are discussed. Studying society of agents and models of agency follows. Finally, a perspective on a methodology for agent-oriented software engineering and standards are presented.
- Semantic Web and Agent Technologies (SWAT) Lab at Lehigh University - the Semantic Web is a vision for extending the Web so that machines can more intelligently integrate and process the wealth of information that is available. Unlike HTML and ordinary XML, Semantic Web languages allow semantics (i.e., meaning) to be explicitly associated with the content. The semantics are formally specified in ontologies, which can be shared via the Internet and extended for local needs. The current standard for the Semantic Web is OWL, a W3C Recommendation. The Semantic Web and Agent Technologies (SWAT) lab is investigating many of the issues needed to realize the Semantic Web vision. The lab's research includes: evaluating the ability of Semantic Web systems to reason with large scale data and building systems that improve the state-of-the-art, designing a theory of distributed ontologies that, among other things, explictly addresses the ontology versioning problem, building Semantic Web agents and systems that can integrate data from multiple heterogeneous sources.
- How Might People Interact with Agents? - interesting essay by Don Norman, vintage 1997.
- robotstxt.org - the main source for information on the robots.txt Robots Exclusion Standard and other articles about writing well-behaved Web robots.
- SELF-STAR: International Workshop on Self-* Properties in Complex Information Systems - Information systems can be complex due to numerous factors including scale, decentralization, heterogeneity, mobility, dynamism, bugs and failures. Deploying, operating and maintaining such systems can be not only very difficult, but also very costly. A flurry of recent activity has been directed at this problem whereby future information systems are envisioned to be self-configuring, self-organizing, self-managing and self-repairing (self-*).
- eBots, Inc. - pioneering the integration of intra and inter businesses to provide a suite of applications that support the Toyota Production System (TPS), principles of lean manufacturing and other continuous improvement programs.
- SPARQL Query Language for RDF - standardized query language for RDF data with multiple implementations offers developers and end users a way to write and to consume the results of queries across this wide range of information, such as personal information, social networks, metadata about digital artifacts, as well as provide a means of integration over disparate sources of information. Used with a common protocol, applications can access and combine information from across the Web.
- SemWebCentral.com - open source tools for the Semantic Web.
- OWL-S API - supports creation and manipulation of OWL-S files.
- Semantic Web Service IDE tools developed at Softagent Lab, Carnegie Mellon - an end-to-end development environment in which a user can develop, host and use semantic web services.
- RulesPower, Inc. - has developed a comprehensive Business Rules Management System (BRMS) that offers rules engine functionality automating highly-complex business processes with exceptional agility, scalability and ease of use. The RulesPower solution enables organizations to define and capture business policies and procedures within a graphical user interface, then rapidly deploy these business rules as production solutions into an enterprise environment.
- AgentLink Agent Technology Roadmap - main web page for the roadmap.
- AgentLink III Agent Technology Roadmap (2005) - final release of the roadmap.
- UK Computing Research Committee Grand Challenges in Computing - ambitious, long-term research initiatives that might benefit from some degree of national and international coordination.
- media style agent technology literature - a collection of public literature in the area of agent technology.
- Agent Technology Glossary from Object Services and Consulting, Inc. - vintage 1999.
- Agent Technology Green Paper from Object Services and Consulting, Inc. - a paper to provide a basic understanding of agents and agent-based technology, a summary of how agent-based technology is currently being employed, brief discussions of the major issues being addressed by agent research and development, indications where agent technology is relevant to the OMG—and vice versa, and suggestions for standardizing areas of this new technology using the OMG process. Vintage 2000.
- Taskable Agent Software Kit (TASK) - a DARPA research program to extend the current scientific and mathematical foundations of agent-based computing with the goal of adding rigor and predictability to the engineering of agent-based systems for DoD. In particular TASK will develop mathematically correct techniques for modeling and analyzing agent behaviors, agent design methods, and the design of agent creation tools. Using these models, TASK will allow comparison of the performance of competing agent-creation approaches in the context of mathematically validated domain models. Key research goals include: Agent Behavior Models, Robust Agent behaviors, Modeling Agent Systems, and Agent Creation Tools. Vintage 2002.
- AgentLink III Agent Technology Roadmap (draft) - draft report of the 2005 roadmap for Agent Based Computing.
- Knowbot - a software system from Corporation for National Research Initiatives (CNRI) that implements a research infrastructure for mobile agents ("Knowbot programs") intended for use in widely distributed systems such as the Internet. The Knowbot software is written in Python, an interpreted object-oriented programming language. The software executes Knowbot programs also written in Python. However, the design of the Knowbot architecture allows multiple programming languages; support for Knowbot programs written in Java (in addition to Python) is planned for a future release. Knowbot programs written in Python and Java should then be able to interoperate.
- SoftwareAgents.NL - Legal Aspects of Software Agents - an overview of existing or proposed legislation, legal and in general technical articles, projects, implementations, companies and examples on the topic of Software Agents by Rik Geurts, who is writing his PhD thesis at the Tilburg Institute for Law, Technology, and Society (TILT) at the Tilburg University.
- Electronic Distribution Agent - third parties, or intermediaries, between publishers and libraries or publishers and end-users.
- Agent-Based Architectures - a wiki for a computer science course that includes material related to software agents, including JADE.
- W3C Web Services Architecture - A Web service is an abstract notion that must be implemented by a concrete agent. The agent is the concrete piece of software or hardware that sends and receives messages, while the service is the resource characterized by the abstract set of functionality that is provided.
- SeMoA (Secure Mobile Agents) - an extensible and open server for mobile agents. The server is written in Java, and agents can be written in Java as well (JDK 1.3). The focus is on all aspects of mobile agent security, including protection of mobile agents against malicious hosts. Another important feature is SeMoA's interoperability with other platforms such as Aglets and JADE, which enables you to run their agents in a SeMoA server environment.
- Black Pearl - financial software uses intelligent agents to identify "opportunities and risks that meet predefined criteria". They use Reactive agents triggered on discrete events, such as a new order message received, and Periodic agents that execute on a user-defined schedule and constantly monitor the environment for trends, exceptions, or threshold conditions.
Laboratory for Intelligent Agents at the School of Information Sciences and Technology at The Pennsylvania State University - aims to develop team-based agent technologies that facilitate a distributed team to collaborate and make decisions in a dynamic environment by proactively exchanging and fusing information based on a "shared mental model" about the team and seeks to develop market-based agent technologies for addressing critical issues regarding negotiation, resource allocation, supply chain management, and web services.
Research Center for Team-Based Agents at the School of Information Sciences and Technology at The Pennsylvania State University - aims to develop agents with "team intelligence", which enables them to support and enhance collaborative activities of teams, which may include both human users and software agents. The center's research has built on the findings and theories about effective human team behaviors for incorporating them into intelligent agent technologies. Psychologists who study human teamwork have pointed out that intelligent team behaviors rely on overlapping shared mental models among team members. For example, a competent human team member can anticipate the needs of teammates, offer relevant information proactively, and avoid overloading teammates by assessing current load levels.
- Collaborative Agents for Simulating Teamwork (CAST) - the cornerstone of agent technologies developed at the Research Center for Team-based Agents. CAST was originally proposed as a general agent architecture to model and simulate human-involved teamwork activities for training purposes (see MURI project for further details). Motivated by psychological studies about human teamwork demonstrating that members of effective human teams can often anticipate needs of other teammates and exchange information proactively, CAST enables agents in a team to anticipate information needs of teammates, whether they are human or software agents. The formal foundation of proactive information exchange behaviors among agents in a team has been established using the SharedPlan theory. The design of CAST architecture is guided by three objectives: scalability, efficiency, and adaptability. Scalability is achieved using a high level language (MALLET) for describing team task knowledge. Efficiency is realized by algorithms that utilize the team task knowledge effectively. Adaptability is accomplished by dynamic responsibility assignment built into the architecture. MALLET (Multi-Agent Logic Language for Encoding Teamwork) is a high-level team knowledge representation language, which provides descriptors for encoding knowledge about individual/team actions and plans, as well as specifications of team structures (e.g., roles and responsibilities). CAST is a domain-independent team-based agent architecture. The domain knowledge of CAST agents came from MALLET. Team knowledge in MALLET is compiled into predicate nets, the computational shared mental model of CAST agents, which are used by CAST kernel for generating effective teamwork behaviors. The CAST kernel is composed of a set of algorithms that CAST agents use to decide what actions (including communication actions) they will take at each time step. All of the kernel algorithms rely on a computational shared mental model of the team. Two novel algorithms of CAST are DRS and DIARG. DRS dynamically selects agents for responsibilities in a team plan based on constraints specified in the plan. DIARG identifies opportunities for proactive delivery of information needed by teammates. The two algorithms together achieve efficiency (by sending information only to those who need them) and adaptability (through constraint-based dynamic responsibility assignments) for a team involving CAST agents.
"Architectures for Intelligent Systems" paper by John F. Sowa - proposes a framework for intelligent systems that consist of a variety of specialized components together with logic-based languages that can express propositions and speech acts about those propositions. The result is a system with a dynamically changing architecture that can be reconfigured in various ways: by a human knowledge engineer who specifies a script of speech acts that determine how the components interact; by a planning component that generates the speech acts to redirect the other components; or by a committee of components, which might include human assistants, whose speech acts serve to redirect one another. The components communicate by sending messages to a Linda-like blackboard, in which components accept messages that are either directed to them or that they consider themselves competent to handle. Published in a Special Issue on Artificial Intelligence of the IBM Systems Journal, vol. 41, no.3, pp. 331-349, 2002.
- Remembrance Agent - A continuously running automated information retrieval system, which augments human memory by displaying a list of documents which might be relevant to the user's current context. Unlike most information retrieval systems, the RA runs continuously without user intervention. Its unobtrusive interface allows a user to pursue or ignore the RA's suggestions as desired. MIT Media Lab, 1996. Alternative source at Bradley J. Rhodes web site.
- Zabaware, Inc. - develops and distributes the Ulta Hal chatterbot technology and products.
- Ultra Hal - chatterbot technology from Zabaware.
- Ultra Hal Assistant - a digital secretary and companion chatterbot from Zabaware that can converse in text of speech.
- Web Ultra Hal - web-based chatterbots from Zabaware.
- Ultra Hal Text-to-Speech Reader - an application from Zabaware that can read documents aloud.
- Ultra Hal Representative - a server-based application from Zabaware that enables chatterbot-based customer service for web sites.
- DARX (Dynamic Agent Replication eXtension) - a framework for building applications as multi-agent systems that provide adaptive fault tolerance. The idea is to have each agent express its needs in terms of dependability. Concurrently, the environment is constantly monitored to gain on the fly knowledge of its behaviour. On a regular basis, both information sets are analyzed in order to select the optimal strategy.
Jadex - a research project of the Distributed Systems and Information Systems Group at the University of Hamburg to build a rational agent layer (BDI agent system) on top of a FIPA-compliant infrastructure that allows for easy intelligent agent construction with sound software engineering foundations. Intelligent agents are a modelling paradigm, based on the notion of agents with mental states. Jadex supports goal-oriented agents where the developer can define more abstract goals for the agents, thereby providing a certain degree of flexibility on how to achieve the goals. Goal-orientation is supported using the BDI Model, which is based on the mental attitudes belief, desire, and intention, and was first introduced as a philosophical model for modelling rational (human) agents, but later adopted and transformed into an execution model for software agents, based on the notion of beliefs, goals, and plans. Jadex incorporates this model into JADE agents, by introducing beliefs, goals and plans as first class objects, that can be created an manipulated inside the agent. In Jadex, agents have beliefs, which can be any kind of Java object and are stored in a belief base. Goals are implicit or explicit descriptions of states to be achieved. To achieve its goals the agent executes plans, which are procedural recipes coded in Java. Jadex is built on top of JADE.
JADE (Java Agent DEvelopment framework) - a software framework for agents fully implemented in the Java language. It simplifies the implementation of multi-agent systems through a middle-ware that complies with the FIPA specifications and through a set of graphical tools that supports the debugging and deployment phases. The agent platform can be distributed across machines (which not even need to share the same OS) 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 one, as and when required. JADE is completely implemented in Java language and the minimal system requirement is the version 1.4 of JAVA (the run time environment or the JDK). The synergy between the JADE platform and the LEAP libraries results in a FIPA-compliant agent platform with reduced footprint and compatibility with mobile Java environments down to J2ME-CLDC MIDP 1.0. The LEAP libraries have been developed with the collaboration of the LEAP project and can be downloaded as an add-on of JADE from this same Web site. Alternate web site.
JADE Tutorial and Primer - a primer aimed at the JADE beginner. It concentrates on the basic features of JADE and explains these in detail with lots of simple examples showing what works and what doesn't. Thus it is a useful introduction to more advanced tutorials as well as JADE's official documentation.
JADE project description - from the AOT Lab at the University of Parma.
Agent and Object Technology Lab (AOT) - part of Dipartimento di Ingegneria dell'Informazione of the University of Parma, Italy.
Software Agent-Based Groupware using E-Services(SAGE) - a project at Georgetown University to investigate architecture models and implementations that support an environment where humans can ubiquitously incorporate software capabilities into their daily routines. Given the recent advancements in service-oriented architectures (SOA), software services or web services provide for the capabilities of organizations to be openly exposed, easily searched and discovered, and made readily-accessible to humans and particularly to other machines. SAGE considers an environment where human stakeholders work together collaboratively on well-established or even ad-hoc networks to accomplish a particular mission. These stakeholders maintain their own information stores and may also have software tools that assist them in their daily routines. SAGE approaches provide assistive technologies to manage the collaboration of the information and services as they become relevant among the stakeholders. Autonomous software assistants or software agents hold the key to enabling the collaboration environment. Agents can store heuristics and rules that evolve over time as the requirements on the human-driven processes or workflow change. Also, agents can encapsulate the complexity of syntactically and semantically sharing both information and services. The investigations intersect with several broad research areas such as Workflow Management & Computer-Supported Cooperative Work, Intelligent Software Agents, and Web Services and Service-Oriented Computing.
- Agents of Alienation - a paper by virtual reality guru Jaron Lanier published in the July 1995 issue of ACM Interactions in which he lays out his rationale for being "enraged by the notion of agents."
- The Robotics Institute at Carnegie Mellon University - conducts basic and applied research in robotics technologies relevant to industrial and societal tasks. Seeking to combine the practical and the theoretical, the Robotics Institute has diversified its efforts and approaches to robotics science while retaining its original goal of realizing the potential of the robotics field.
- robots.net - a place to read the latest news on personal and industrial robotics, robot competitions, and other cool stuff.
- ABLE (Agent Building and Learning Environment) - a Java framework, component library, and productivity tool kit for building intelligent agents using machine learning and reasoning, made available by the IBM T. J. Watson Research Center. The ABLE framework provides a set of Java interfaces and base classes used to build a library of JavaBeans called AbleBeans. The library includes AbleBeans for reading and writing text and database data, for data transformation and scaling, for rule-based inferencing using Boolean and fuzzy logic, and for machine learning techniques such as neural networks, Bayesian classifiers, and decision trees. Developers can extend the provided AbleBeans or implement their own custom algorithms. Rule sets created using the ABLE Rule Language can be used by any of the provided inferencing engines, which range from simple if-then scripting to light-weight inferencing to heavy-weight AI algorithms using pattern matching and unification. Java objects can be created and manipulated using ABLE rules. User-defined functions can be invoked from rules to enable external data to be read and actions to be invoked.
- International Journal of Agent-Oriented Software Engineering (IJAOSE) - a quarterly publication established as a communication vehicle for researchers and practitioners to promote, publicise, and exchange ideas relating to the interface between research and commercial adoption of agent technology within the software development community. A further objective is to bring together the two relevant communities of agent technologists and (traditional) software engineers. Although software engineering necessarily encompasses research and application, an individual paper in IJAOSE may address one or both of these aspects.
- Distributed Constraint Optimization Problem (DCOP) - datasets and variations of the ADOPT algorithm for solving distributed constraint optimization problems, in which cooperating agents, each in control of one or more variables, work together to optimize a set of constraints that exist upon the variables. .
- TopQuadrant, Inc. - a business that focuses on semantic web technology and intelligent systems and the engineering of ontologies and knowledge bases.
- AKIRA (Artificial Knowledge Interface for Reasoning Applications) - a development tool for building virtual worlds and populating them with agents manifesting high-level behaviour. The advanced underlying logic represents a general framework that allows integration of all relevant aspects of the interactions between agents and their world. AKIRA supports the modeling of agents, with varying degrees of intelligence and computational needs, that are able to act in an external world interacting with the AKIRA server using the AKIRA XML Transmission Protocol.
- Tracy - a modular, component-oriented, and extendable toolkit to execute stationary and mobile software agents written in the Java programming language. Tracy is the result of a collaborative project distributed between universities in Germany and Australia. Tracy uses the standard Java (Version 1.4) execution environment without any modifications, neither of the virtual machine nor of any of the core Java APIs. Large parts of Tracy are free software for non-commercial purposes distributed by the University of Jena. In contrast to existing mobile agent toolkits, Tracy has a plugin-oriented architecture. Tracy consists of a micro kernel that provides basic services to execute agents and control their life-cycle. On top of the micro-kernel, an agency component manages all agents that are currently residing on this host. Additionally, an agency has the task to manage so-called plugins, which is our concept to provide high-level services within Tracy. A plugin is a software component that provides a single service that is not mandatory to run an agency and simply extends the functionality of it. Plugins can be added dynamically to a running agency, they can be stopped (for example in case of a fault) and restarted later. Tracy already comes with some plugins, for example inter-agent communication, migration, partial solutions of mobile agent security challenges, user management, management of overlay networks, and permission management.
- DEXTER Agents from Macsea - software agent technology from Macsea Limited for machinery health monitoring. The philosophy behind DEXTER Agents is to provide you with new tools to automate the equipment monitoring and performance analysis functions currently performed by your people. As the levels of plant automation increase, there’s simply too much process data to convert into useful business (maintenance) information. DEXTER Agents allows you to create software agents that automatically perform these tasks, 24 hours per day, 7 days per week. It’s a simple process to create a prognostic agent that acquires process data, performs historical trending analysis to detect anomalous equipment behaviors, and predicts failures before they have a chance to happen. The agents alert you if a problem is detected, otherwise they continue to do their job unobtrusively in the background as part of your enhanced automation system.
- Semantic Web - a W3C initiative that provides a common framework that allows data to be shared and reused across application, enterprise, and community boundaries. It is a collaborative effort led by W3C with participation from a large number of researchers and industrial partners. It is based on the Resource Description Framework (RDF), which integrates a variety of applications using XML for syntax and URIs for naming.
- Trading Agent Competition (TAC) - an international forum designed to promote and encourage high quality research into the trading agent problem. Includes annual games (the competition) as well as several software packages to be used for the games.
- General Magic - this is simply a placeholder link for one of the first companies to offer a commercial software agent product, the TeleScript agent programming language.
- TeleScript - this is simply a placeholder link for one of the first commercial agent programming languages, from a company named General Magic.
- MASA - Mobile Autonomous Software Agent Computing Group at the University of Connecticut. Appears to have been succeeded by the Dynamic Computing Research Group DCRG). This link is for historic purposes.
- Dynamic Computing Research Group (DCRG) at the University of Connecticut - pursues agent-based computing, adaptive or reconfigurable computing, and distributed computing. This is the successor to the MASA group, but even this group seems to be dormant (no changes to web page since 1999). This link is for historic purposes.
- AgentWise - a workgroup within the DistriNet research group of the computer science department of Katholieke Universiteit Leuven, which focuses on the investigation of various aspects of agents and multi-agent systems, including: 1) emergent behavior in multi-agent systems: design of complex systems, emerging out of cooperation between a number of agents who each are very simple, 2) organisations in multi-agent systems: some agents are able to form organisations dynamically, such as a hierarchy, 3) social conventions in multi-agent systems: when, why and how do agents interact and cooperate with each other, 4) reuse of generic agent architectures: can lead to several advantages: shorter design time, more efficiency, flexibility and robustness, ..., 5) multi-agent architectures for complex information processing: teams of cooperating agents help gathering, filtering and analysing all kinds of information, 6) configuration of software frameworks for agents: adaptive behavior of agents by means of framework instantiation, and 7) mobility of agents in distributed systems: mechanisms that enable agents to migrate from one location to another.
- Agent Modeling Language (AML) Specification from Whitestein Technologies, AG - a comprehensive semi-formal visual modeling language for specifying, modeling and documenting systems that incorporate concepts drawn from multi-agent systems theory. The primary application context of AML is to systems explicitly designed using software multi-agent system concepts. AML can however also be applied to other domains such as business systems, social systems, robotics, etc. The motivation for AML stems from the need for a ready-to-use, complete and highly expressive modeling language suitable for the development of a broad range of software solutions across commercial, industrial, and research fields. The current version of AML offers support for: MAS entities, ontologies, social aspects, behavior abstraction and decomposition, communicative interactions, services, observations and effecting interactions, mental aspects, deployment, and mobility.
[ Home | Blog | Books | Links | Glossary | Software Agent Manifesto | Pre-2001 | 2001 | 2002 | 2003 | 2004 | 2005 | 2006 ]
Updated: January 29, 2006 07:53:52 PM -0500
Copyright © 2006 John W. Krupansky d/b/a Base Technology