Inference engine

Grule is a business rule engine for Go that decouples complex decision-making logic from core application code. It provides a framework for defining, versioning, and executing business rules through a domain-specific language, allowing logic to be managed independently of the underlying software implementation. The engine distinguishes itself by utilizing a formal grammar-based parser and a Rete-inspired pattern matching algorithm to evaluate logic against data facts efficiently. It supports dynamic system modeling by enabling runtime updates to policies and providing thread-safe knowledge ba

Clara Rules is a declarative logic programming library and business rules management system designed for Clojure and Java applications. It functions as a forward-chaining inference engine that evaluates business logic by matching data patterns against defined rules, allowing developers to derive new information and trigger automated actions based on the current state of a fact set. The engine utilizes a directed acyclic graph for pattern matching, which enables efficient evaluation across complex rule sets. It incorporates a truth maintenance system that tracks dependencies between facts and

This project is a business rules and complex event processing engine designed to manage logical decision-making and stateful workflows. It functions as a computational framework that evaluates incoming data streams and facts against conditional logic to derive new conclusions and trigger automated actions. The engine distinguishes itself through a combination of forward-chaining inference and deterministic state machine orchestration. It uses salience-based conflict resolution to prioritize rule execution and supports persistent contextual state tracking to manage long-running business proces

MarkovJunior is a probabilistic programming language and constraint propagation engine designed to generate sequences based on probabilistic rules. It utilizes a pattern matching rewrite system and a probabilistic inference tool to manage state and ensure that generated runs reach defined goal states. The system distinguishes itself through the use of wave-based superposition to track possible value assignments and prune impossible states. It employs a pattern matching rewrite system to transform specific sequences of values within multi-dimensional grids into new states. The framework suppo

ReAct is an agentic workflow template and prompting framework for large language models. It implements a logic pattern that integrates chain-of-thought reasoning with external tool execution to solve complex, multi-step tasks. The framework uses an interleaved reasoning and acting logic, forcing the model to document its internal thought process before executing an action. This cycle of planning and acting allows the system to interact with external APIs or databases and inject real-world data back into the model context to refine reasoning paths. The project covers autonomous task execution

This project is a comprehensive Lisp AI implementation library that provides reference implementations for various artificial intelligence paradigms and symbolic algorithms. It functions as a multi-purpose toolkit containing a logic programming engine, a natural language processing suite, and a symbolic mathematics toolkit. The library is distinguished by its diverse architectural frameworks, including a Prolog-style execution engine that uses unification and goal-driven backtracking, and a system for simulating human decision-making through expert system shells and certainty factors. It also