Coherent Knowledge Systems (http://coherentknowledge.com/) is happy to announce the first open-source release of its flagship ErgoAI (https://github.com/ErgoAI) software, an advanced tool for enterprise knowledge representation and reasoning (KRR). ErgoAI greatly extends the well-known open-source Flora-2 system (https://flora.sourceforge.net/) and, with this release, Flora-2 as a distinct system is being retired. ErgoAI is a best-of-breed system for logical AI, that is based on fundamental research advances. It has been used to develop applications in a number of commercial and government organizations. It shines at decision analytics & automation tasks in financial, legal, defense, and other domains, such as compliance with policies, regulations, contracts, guidance, and information integration mappings, where knowledge is complex, high accuracy is crucial, and good explainability is required.
ErgoAI is a highly extended, logic programming system, with cleanly declarative semantics. It has a uniquely capable combination of expressivity, computational scalability, and explainability. It answers queries and is analogous to a database system “on steroids” – that manages more complex knowledge sentences (e.g., rules) rather than just data. It provides a detailed explanation for every answer, which can be presented in English (or other natural language), in a drill-down manner, readily comprehended and navigated by end users, subject matter experts, project sponsors, and other non-programmers.
ErgoAI features object-oriented, higher-order syntax, defeasibility (argumentation and exception rules), restraint (bounded rationality), and well-founded negation, in-built restricted natural language processing (via templates), dependency-aware smart cacheing of inferences (“incremental tabling”), modules (information hiding), as well as several other lesser extensions of logic programming.
ErgoAI is highly composable with other AI and non-AI systems that are typically required to develop an overall application solution. It can orchestrate and dynamically query, or import/export, information from/to a variety of external systems and components. It has connectors to major programming languages and data formats, including Python, knowledge graphs, relational databases, JSON, C/C++, Prolog, and many others. Integration of strong probabilistic/fuzzy uncertainty, machine learning (ML), and natural language processing (NLP) capabilities is available via compatible open-source AI tools plus ErgoAI’s connectors[1] ; tighter integration is under development.
One can install ErgoAI most simply by using its automatic installers for the latest official stable release (https://github.com/ErgoAI/.github/releases). Or install the system and its source code by cloning the Github repositories and compiling the sources https://github.com/ErgoAI#installing-ergoai-from-the-sources). ErgoAI comes with extensive documentation, tutorials, and examples. Please see https://github.com/ErgoAI for more details.