In computer science, a software agent is a piece of autonomous, or semi-autonomous proactive and reactive, computer software. Many individual communicative software agents may form a multi-agent system.

To be considered an agent, a software object must be a self-contained program that is capable of making independent decisions and taking actions to satisfy internal goals based upon its perceived environment.

Examples

• user agent - for browsing the World Wide Web
• mail transfer agent - for serving e-mail
• SNMP agent
• DAML
• daemons in Unix-like systems. See the mascot for BSD systems. CTSS first named daemons; see also Maxwell's demon.
• In Unix-style networking servers, httpd is an HTTP daemon which implements the Hyper-Text Transfer Protocol at the root of the World Wide Web
• Management agents used to manage telecom devices

The definition of agent processing can be approached from two interrelated directions:

• internal state processing and ontologies for representing knowledge
• interaction protocols - standards for specifying communication of tasks

Agent systems are used to model real world systems with concurrency or parallel processing.

See also

• GNUBrain - Implementation of a multi agent framework (GPL)

External links

• http://www.agentland.com/ - Commercial site
• http://fipa.org/ - Foundation for Intelligent Physical Agents
• http://www.msci.memphis.edu/~franklin/AgentProg.html - University of Memphis, Department of Mathematical Sciences paper entitled "Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents"
• http://agtivity.com/ - Focuses on turning the construction and deployment of Software Agent Technology into a science rather than folklore and ad-hoc art and craft
• http://agtivity.com/aglinks.htm - Extensive list of web-based resources for Software Agent Technology

Further reading

• Artificial Intelligence: A Modern Approach (2nd Edition) by Stuart J. Russell & Peter Norvig, (2002) Prentice Hall, ISBN 0137903952