OpenCog is a project that aims to build an open source artificial intelligence framework. OpenCog Prime is an architecture for robot and virtual embodied cognition that defines a set of interacting components designed to give rise to human-equivalent artificial general intelligence as an emergent phenomenon of the whole system. OpenCog Prime's design is primarily the work of Ben Goertzel while the OpenCog framework is intended as a generic framework for broad-based AGI research. Research utilizing OpenCog has been published in journals and presented at conferences and workshops including the annual Conference on Artificial General Intelligence. OpenCog is released under the terms of the GNU Affero General Public License. OpenCog is in use by more than 50 companies, including Huawei and Cisco.
A graph database, dubbed the , that holds "atoms" together with their "values". An example of a value would be a truth value. Atoms are globally unique, immutable and are indexed ; values are fleeting and changeable.
A collection of pre-defined atoms, termed , used for generic knowledge representation, such as conceptual graphs and semantic networks, as well as to represent and store the rules needed to manipulate such graphs.
A collection of pre-defined atoms, that encode a type subsystem, including type constructors and function types. These are used to specify the types of variables, terms and expressions, and are used to specify the structure of generic graphs containing variables.
A collection of pre-defined atoms that encode a satisfiability modulo theories solver, built in as a part of a generic graph query engine, for performing graph and hypergraph pattern matching. This generalizes the idea of a structured query language to the domain of generic graphical queries; it is an extended form of a graph query language.
A generic rule engine, including a forward chainer and a backward chainer, that is able to chain together rules. The rules are exactly the graph queries of the graph query subsystem, and so the rule engine vaguely resembles a query planner. It is designed so as to allow different kinds of inference engines and reasoning systems to be implemented, such as Bayesian inference or fuzzy logic, or practical tasks, such as constraint solvers or motion planners.
An attention allocation subsystem based on economic theory, termed ECAN. This subsystem is used to control the combinatorial explosion of search possibilities that are met during inference and chaining.
An implementation of a probabilistic reasoning engine based on probabilistic logic networks. The current implementation uses the rule engine to chain together specific rules of logical inference, together with some very specific mathematical formulas assigning a probability and a confidence to each deduction. This subsystem can be thought of as a certain kind of proof assistant that works with a modified form of Bayesian inference.
A probabilistic genetic program evolver called Meta-Optimizing Semantic Evolutionary Search, or MOSES. This is used to discover collections of short Atomese programs that accomplish tasks; these can be thought of as performing a kind of decision tree learning, resulting in a kind of decision forest, or rather, a generalization thereof.
A natural language input system consisting of Link Grammar, and partly inspired by both Meaning-Text Theory as well as Dick Hudson's Word Grammar, which encodes semantic and syntactic relations in Atomese.
An implementation of Psi-Theory for handling emotional states, drives and urges, dubbed OpenPsi.
Interfaces to Hanson Robotics robots, including emotion modelling via OpenPsi. This includes the Loving AI project, used to demonstrate meditation techniques.
