Awesome GitHub RepositoriesHybrid Vector-Graph Databases

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

Supermemory is an artificial intelligence memory management platform designed to provide autonomous agents with persistent, long-term knowledge bases. It functions as a centralized repository that synchronizes multimodal data, enabling agents to maintain context and historical information across complex, multi-session workflows. By serving as a knowledge graph engine and vector database orchestrator, the platform ensures that information remains accessible and relevant for automated tasks. The system distinguishes itself through its hybrid indexing approach, which combines vector similarity s

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

This project is a comprehensive framework for developing, orchestrating, and deploying autonomous agents. It provides a structured environment for building agents that utilize reasoning loops to perform multi-step tasks, manage state through graph-based workflows, and interact with external tools. By mapping unstructured model outputs into typed schemas, the framework ensures reliable integration with downstream application logic. The platform distinguishes itself through a focus on production-grade reliability and security. It incorporates hybrid memory systems that combine vector embeddings

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

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

txtai is an artificial intelligence platform designed for building semantic search applications, managing vector storage, and orchestrating language model workflows. It functions as a comprehensive engine for processing unstructured data, enabling the development of autonomous agents and complex content automation pipelines. The platform distinguishes itself through a hybrid indexing architecture that combines dense vector embeddings with relational graph structures, allowing for multi-dimensional retrieval across both semantic meaning and entity relationships. It supports multimodal analysis

This project is an LLM knowledge base builder and personal knowledge management tool. It is a desktop application designed to transform diverse documents into a persistent, interlinked wiki through LLM analysis and incremental ingestion. The system distinguishes itself with a knowledge graph visualizer that uses community detection algorithms to map relationships between concepts and identify topical clusters. It features a hybrid retrieval system that combines keyword matching, vector embeddings, and graph relevance to locate information. The platform covers a wide range of capabilities inc

Ce projet est une stack de développement conteneurisée et un framework d'application pour construire des systèmes de génération augmentée par récupération (RAG). Il fournit un sandbox IA dockerisé qui intègre des runtimes de modèles locaux, des graphes de connaissances et des vector stores pour permettre la création de chatbots contextuels. La stack se distingue par son vector store basé sur les graphes, qui combine des graphes de connaissances structurés avec des index vectoriels pour la récupération de données sémantiques et structurelles. Elle permet l'hébergement de modèles locaux avec accélération CPU ou GPU, permettant des tâches génératives sans dépendance aux API cloud externes. Le framework couvre un large éventail de capacités, notamment le traitement et l'indexation de documents PDF, l'orchestration de services IA basés sur des conteneurs et l'implémentation d'une génération de réponses ancrées (grounded). Il inclut une interface de chat web avec streaming de réponse incrémentiel et une interface standardisée pour basculer entre différents fournisseurs de modèles de langage. L'environnement est amorcé via l'orchestration de conteneurs pour déployer rapidement une stack préconfigurée de modèles et de bases de données.

Tiny Universe is an educational monorepo that delivers multiple independent implementations of core AI subsystems as self-contained Jupyter notebooks. It provides from-scratch constructions of foundational architectures including a complete Transformer model built from the original paper specification, a denoising diffusion probabilistic model for image generation, and a ReAct-style autonomous agent framework that equips an LLM with tools for planning and multi-step task execution. The project distinguishes itself by covering the full lifecycle of modern AI systems through hands-on implementa

ruvector est une base de données vectorielle et un moteur de graphes basé sur Rust, conçu pour l'inférence locale et la recherche de plus proches voisins. Il utilise une architecture de base de données de graphes vectoriels et un index de réseau de neurones sur graphe pour affiner les résultats de recherche via une attention structurelle. Le système intègre un simulateur de circuit quantique accéléré par le matériel pour exécuter des simulations d'état vectoriel et des modèles de recherche complexes, ainsi qu'un moteur d'inférence WebAssembly pour exécuter la recherche vectorielle et l'exécution de modèles directement dans les navigateurs web. Le projet utilise un format de conteneur cognitif qui regroupe modèles, données et un micro-noyau amorçable dans un seul binaire pour le déploiement. Il propose des outils de configuration de modèles spécialisés, incluant une méthode de consolidation des poids pour prévenir l'oubli catastrophique et un mécanisme d'adaptateur léger pour une adaptation instantanée des poids. Le système couvre un large éventail de fonctionnalités, notamment la recherche vectorielle accélérée par le matériel, l'interrogation de relations de graphes et l'analyse de documents scientifiques pour l'extraction LaTeX et MathML. Il fournit également un chaînage de preuves cryptographiques pour vérifier les mutations de données, une synchronisation des métadonnées basée sur Raft pour la haute disponibilité, et une compression de données à résolution étagée pour gérer les coûts de stockage.

Apache AGE is a graph database extension for PostgreSQL that adds openCypher graph query capabilities directly within the relational database environment. It functions as a loadable extension that translates Cypher graph traversal queries into SQL expressions, enabling users to run pattern matching and path analysis alongside standard SQL operations within a single database instance. The extension stores labeled, directed property graphs as isolated schemas with internal relational tables for vertices, edges, and labels, preventing cross-graph interference. It supports hybrid query execution

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

Zep is a long-term memory layer and persistent storage system for large language model applications. It functions as a memory service and vector database orchestrator that manages chat history, user preferences, and context retrieval to reduce hallucinations in AI agents. The system maintains a temporal knowledge graph that stores interaction data as dated facts to track how user preferences and environments evolve over time. It combines these knowledge graphs with a store for persisting unstructured message data at the user and session levels. The platform provides capabilities for AI conte

Kùzu is an embedded property graph database engine designed for high-performance analytical queries and local data management. It operates as a library within the host application process, utilizing a columnar-based storage architecture and just-in-time query compilation to execute complex graph traversals and pattern matching efficiently. By mapping database files directly into system memory, it ensures data durability and high-speed access while maintaining ACID-compliant transactional integrity. The engine distinguishes itself by integrating vector similarity search and full-text search di

Helix DB is a distributed graph database and knowledge graph platform that persists nodes and edges on object storage for durable and unlimited scaling. It operates as an ACID-compliant system, ensuring data consistency through serializable snapshot isolation during concurrent operations. The project distinguishes itself by combining a vector search engine and a property graph, utilizing hybrid vector and full-text search to locate entry points for graph traversals. It enables dynamic graph querying through a domain-specific language, allowing complex logic and recursive queries to be execute

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