Awesome GitHub RepositoriesGraphRAG Frameworks

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

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

Graphiti is a backend framework and memory server designed to provide artificial intelligence agents with persistent, time-aware knowledge graph storage. It functions as a memory layer that enables agents to maintain context across long-term interactions by recording and evolving structured data over time. The system distinguishes itself through a specialized temporal graph database that tracks how entities and relationships change using validity windows. By combining semantic vector similarity, keyword matching, and graph topology traversal, the engine performs hybrid retrieval to locate rel

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

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

nano-graphrag est un système de récupération qui utilise des graphes de connaissances pour fournir un contexte structuré aux réponses des grands modèles de langage (LLM). Il fonctionne comme un indexeur de graphe de connaissances qui transforme le texte non structuré en un réseau d'entités et de relations, ainsi qu'un système de récupération de graphe hybride. Le projet se différencie en combinant des recherches de voisinage local avec des résumés de communautés globales pour répondre à des questions complexes en langage naturel. Il inclut un visualiseur de graphe de connaissances qui génère des représentations HTML des entités et de leurs relations pour cartographier les connaissances indexées. Le framework couvre un large ensemble de capacités, y compris l'extraction d'entités-relations, le clustering de graphes basé sur la communauté et l'indexation incrémentale basée sur le hachage. Il fournit une couche d'intégration pour connecter des modèles open source et des fournisseurs d'embedding locaux, pris en charge par des backends de stockage enfichables pour les données clé-valeur, vectorielles et de graphe. Une utilité supplémentaire est fournie via la mise en cache des réponses basée sur les arguments et des fonctions de post-traitement pour réparer les sorties JSON instables des modèles de langage.

Fast-GraphRAG is a system for generating and querying knowledge graphs from domain data. It uses a GraphRAG retrieval workflow to traverse structured data and isolate precise evidence for answering complex questions. The project utilizes an agent-driven retrieval framework to coordinate the querying of knowledge graphs and the synthesis of final answers. It supports incremental data synchronization, allowing structured knowledge bases to be updated in real time as source information evolves. The system integrates with API-compatible language models and embedding providers to power its data p

If you find our work helpful, please kindly cite our paper.

Semantica 🧠 • Build AI systems that can explain, trace, and justify every decision. Knowledge graphs, context graphs, reasoning engines, provenance, and governance for production AI.

ApeRAG is a powerful RAG system that deeply analyzes documents and multimedia content while building vector indexes in parallel and measuring retrieval quality. It streamlines workflows with integrated LLM management, data source handling, automatic syncing, and seamless office tool compatibility.

The simplest, most accurate GraphRAG framework built on FalkorDB

VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data — runs locally or in the cloud.

LogicRAG enables structured retrieval without building knowledge graphs on corpora. By constructing query logic dependency graphs to guide structured retrieval adaptively, it enables test-time scaling of graphRAG on large/dynamic knowledge bases. This work has been accepted to AAAI'26, with…

English | Simplified Chinese