Awesome GitHub RepositoriesSemantic Mapping Tools

GraphRAG is a data processing pipeline and retrieval engine designed to transform unstructured text into interconnected knowledge graphs. By utilizing language models to extract entities and relationships, it builds structured representations of information that enable context-aware retrieval for downstream applications. The system distinguishes itself through hierarchical graph clustering and large-scale data synthesis, which organize massive document corpora into multi-level structures. This approach allows for both vector-based semantic searches and graph-based traversals, providing a comp

The .NET Compiler Platform is a collection of open-source APIs for C# and Visual Basic that provides deep code analysis, refactoring, and automated source code generation. It serves as the core infrastructure for building development tools, offering a platform to inspect, modify, and understand source code through immutable syntax trees and semantic models. The platform distinguishes itself by providing full-fidelity syntax trees that preserve every character of source code, including whitespace and comments, alongside an incremental compilation pipeline that enables near-instant feedback dur

Memori is an AI agent memory middleware platform designed to provide persistent, context-aware recall for language models. It functions as a non-intrusive layer that intercepts outbound model requests to automatically capture interaction history and execution traces, ensuring that agents maintain continuity across sessions without requiring modifications to existing application logic. The platform distinguishes itself through a dual-model storage architecture that maintains information as both structured relational primitives for precise fact retrieval and rolling narrative summaries for situ

This project provides an integration of Tree-sitter into the Neovim editor to enable structural code analysis. It serves as a framework for structural code navigation, context-aware syntax highlighting, and the management of language-specific parsers. The system distinguishes itself through a multi-language injection handler that identifies and parses embedded languages within a single document. It uses a dedicated parser manager to install, update, and remove grammar definitions and their associated query files. The tool covers several capability areas including incremental text selection,

KAG is a graph-augmented retrieval augmented generation system and knowledge graph engine. It functions as a framework that integrates large language models with graph retrieval and numerical calculation to resolve natural language queries. The system creates unified knowledge representations by aligning unstructured data and expert rules through semantic mapping. It maintains mutual indexing between graph structures and original text blocks to ensure that reasoning processes remain linked to verifiable source data. The project provides capabilities for semantic information integration, grap

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

go-ast-book es una colección de recursos técnicos y educativos centrados en el análisis de árboles de sintaxis abstracta (AST), desarrollo de compiladores y verificación estática de código. Proporciona guías y manuales para analizar, recorrer y examinar código fuente en Go con el fin de extraer su significado semántico. El proyecto sirve como referencia para construir frontends de compiladores, cubriendo la traducción de código de alto nivel a representaciones intermedias y formas de asignación estática única (SSA). También proporciona instrucciones para utilizar estas técnicas en el desarrollo de herramientas de lenguaje y análisis estático de código. Los recursos cubren una amplia gama de capacidades de análisis estático, incluyendo tokenización léxica, análisis estructural de expresiones y declaraciones, y seguimiento de coordenadas para archivos fuente. También detalla procesos de análisis semántico como la resolución de identificadores, verificación de corrección de tipos y análisis de flujo de control para concurrencia y ejecución diferida.

MiniOB is an open-source educational relational database kernel designed for learning the internals of database systems. It implements a dual-engine storage architecture combining B+ Tree and LSM-Tree, supports SQL parsing and query execution, and provides transactional processing with multi-version concurrency control. The system communicates with clients using the MySQL wire protocol and includes a vector database extension for storing and querying high-dimensional vectors. The project distinguishes itself through its comprehensive coverage of core database concepts in a single, learnable c