Awesome GitHub RepositoriesKnowledge Graph Retrieval

Embedchain is an LLM memory management framework and RAG orchestration engine designed to provide AI agents with a persistent storage layer. It functions as a long-term memory pipeline that extracts facts from unstructured interactions and stores them as permanent knowledge base entries to retain user preferences and interaction history across sessions. The system employs a hybrid vector database interface that combines semantic embeddings with traditional keyword search. It utilizes an entity-linking knowledge graph to connect related information points and applies temporal ranking to distin

LightRAG is a graph-based retrieval framework designed to build retrieval-augmented generation pipelines. It structures unstructured text into knowledge graphs, enabling multi-hop reasoning and complex query synthesis across large document collections. By integrating dense vector embeddings with structured knowledge graphs, the system facilitates both similarity-based and relationship-aware information retrieval. The framework distinguishes itself through a dual-level retrieval strategy that combines low-level keyword matching with high-level semantic graph traversal to capture both specific

Cognee is an agentic memory management platform designed to provide autonomous agents with long-term semantic recall and structured knowledge. It functions as a framework for building persistent memory systems that connect large language models to graph-based knowledge and vector storage, enabling agents to maintain context across complex tasks and multiple sessions. The platform distinguishes itself through a hybrid approach that combines semantic similarity search with structural graph traversal, allowing for context-aware information retrieval. It features a modular architecture that orche

Neo4j is a native graph database management system designed to store and query highly connected data using a property-graph model. It provides an ACID-compliant transaction engine that ensures data integrity, supported by a distributed cluster architecture that maintains causal consistency across nodes. Users interact with the system through a declarative query language, which allows for complex pattern matching and path traversal without requiring manual traversal logic. The platform distinguishes itself through its hybrid approach to data retrieval, combining traditional graph-based queries

Planning with files is an enterprise knowledge graph platform designed to transform unstructured organizational data into a searchable, interconnected network. By utilizing a graph-based retrieval-augmented generation engine, the system grounds language model outputs in verified internal data, ensuring that responses are explainable, traceable, and free from hallucinations. The platform distinguishes itself through a focus on data sovereignty and secure, private infrastructure deployment. It enables organizations to maintain full control over sensitive information by processing data locally o

This project is a multi-model database system designed to store and manage information as documents, graphs, and key-value pairs within a single engine. It functions as a graph database and knowledge graph platform, providing the infrastructure to build, query, and visualize structured data models. By integrating vector search capabilities, the system serves as a vector database that supports retrieval-augmented generation for artificial intelligence applications. The platform distinguishes itself through a unified query language that allows users to perform document lookups, graph traversals

jcode es un framework para desarrollar agentes de codificación de IA autónomos que automatizan tareas de desarrollo de software. Funciona como un orquestador de agentes, tiempo de ejecución de herramientas y motor de memoria semántica, permitiendo la creación de agentes que pueden modificar código, ejecutar pruebas e iterar sobre su propia funcionalidad. El proyecto se distingue por su uso de enjambres de agentes recursivos, donde una jerarquía de agentes colaboradores puede generar agentes hijos para descomponer tareas complejas. Implementa un sistema de memoria semántica que combina la recuperación basada en vectores con el mapeo de relaciones basado en grafos para mantener el contexto a través de las sesiones. Para gestionar el riesgo, el sistema utiliza una gobernanza de acciones escalonada que requiere aprobación humana para operaciones sensibles y aísla las actividades de los agentes dentro de worktrees de git separados. El framework incluye un kit de herramientas de automatización de navegador completo para interactuar con páginas web, extraer instantáneas del DOM y capturar capturas de pantalla. También implementa el Model Context Protocol para integrar herramientas y datos externos, y admite recarga en caliente de binarios para actualizar el servidor sin perder conexiones de red activas. El sistema proporciona una interfaz de línea de comandos para gestionar las memorias de los agentes e incluye herramientas de auditoría para rastrear el progreso del plan y visualizar la topología del enjambre de agentes.

QASystemOnMedicalKG is a medical knowledge graph question answering system designed to retrieve disease-centered information from a structured data store. It functions as both a constructor for building medical knowledge graphs and a retrieval system that extracts answers regarding symptoms, causes, and treatments. The system employs a pipeline that converts unstructured medical web data into a graph database using dictionary-based entity segmentation. It utilizes query-based intent classification to parse natural language inputs and maps these queries to specific nodes and edges within the g

Potpie is an LLM codebase analysis platform and multi-agent orchestration framework designed to act as an AI software engineer. It parses repositories into a structured code knowledge graph, enabling AI agents to perform multi-hop reasoning, dependency tracing, and grounded technical analysis across large codebases. The system distinguishes itself through a spec-driven development framework where agents generate detailed technical specifications and architecture plans before implementing multi-file code changes. It utilizes a durable execution engine to coordinate specialized AI personas for

Memgraph is an in-memory, distributed graph database designed for high-performance labeled property graph management. It utilizes a Cypher query engine for declarative data retrieval and manipulation, providing a scalable knowledge graph backend that integrates vector search and graph traversals. The system distinguishes itself as a real-time graph analytics platform, employing native C++ and CUDA implementations to execute complex network analysis and dynamic community detection on streaming data. It provides specialized support for AI integration, including GraphRAG capabilities, the constr

Cartography es un framework de visualización de infraestructura y análisis de seguridad basado en grafos. Ingiere datos de diversos proveedores de nube, identidad y software-as-a-service para modelar relaciones complejas entre recursos, usuarios y hallazgos de seguridad dentro de una base de datos de grafos centralizada. Al mapear estas interdependencias, la plataforma permite a las organizaciones obtener visibilidad de su entorno e identificar posibles riesgos de seguridad mediante consultas de recorrido de grafos. La plataforma se distingue por su normalización basada en ontologías y correlación de entidades multiplataforma, que mapean datos heterogéneos de múltiples fuentes en un modelo unificado y consistente. Emplea pipelines de ingestión modulares y filtrado basado en esquemas para mantener este grafo, asegurando que los datos de infraestructura permanezcan precisos mediante la poda automatizada basada en el estado de nodos obsoletos. Este enfoque permite el descubrimiento de rutas de ataque complejas y configuraciones de seguridad erróneas que abarcan sistemas dispares de nube, dispositivos y gestión de identidades. Más allá del modelado central, el sistema proporciona capacidades extensas para el inventario de activos, gobernanza de identidades y análisis de la cadena de suministro de software. Admite una amplia gama de integraciones, incluyendo recursos de computación y redes nativos de la nube, telemetría de gestión de endpoints y metadatos del ciclo de vida de desarrollo. Los usuarios pueden extender la funcionalidad de la plataforma definiendo reglas de seguridad personalizadas, añadiendo trabajos de análisis de datos especializados o integrando nuevas fuentes de inteligencia a través de su framework modular. El proyecto está implementado en Python y proporciona documentación para configurar módulos de ingestión y definir consultas de grafos personalizadas.

FalkorDB is a high-performance graph database management system and vector graph database. It serves as a knowledge graph construction tool and a GraphRAG knowledge store, integrating structured property graphs with vector search to provide grounded context for large language models. The engine is designed as a multi-tenant graph engine, capable of hosting thousands of isolated datasets within a single instance. The system distinguishes itself by using linear algebra for query execution, treating relationship tensors as matrix multiplications to achieve low-latency multi-hop traversals. It ut

Memary is a memory-augmented agent framework that stores and retrieves contextual information from a knowledge graph to personalize responses and maintain long-term memory across interactions. It automatically captures all agent interactions and stores them as structured memories without requiring explicit instrumentation, then injects top-ranked user entities and themes into the active context window to tailor agent responses dynamically. The framework distinguishes itself through a multi-retriever memory search that combines COLBERT reranking with recursive graph queries across databases, e