13 repository-uri
Search systems that map relationships between entities to provide context-aware answers from interconnected data.
Distinguishing note: Focuses on entity-relationship mapping for retrieval rather than standard keyword-based search.
Explore 13 awesome GitHub repositories matching data & databases · Knowledge Graph Retrieval. Refine with filters or upvote what's useful.
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
Utilizes a knowledge graph for entity-relationship retrieval to connect associated data points for AI agents.
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
Building search systems that map relationships between entities to provide context-aware answers from large and interconnected document collections.
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
Defines structural rules and schemas to ensure consistent data organization within knowledge graphs.
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
Integrates large language models with structured graph data to improve retrieval accuracy and provide context-aware reasoning.
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
Structures organizational data as interconnected nodes and edges to enable verifiable, context-aware information retrieval.
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
Supplies large language models with trusted context by retrieving relevant entities and relationships from a knowledge graph.
jcode este un framework pentru dezvoltarea de agenți de codare AI autonomi care automatizează sarcinile de dezvoltare software. Acesta funcționează ca un orchestrator de agenți, runtime de instrumente și motor de memorie semantică, permițând crearea de agenți care pot modifica codul, rula teste și itera asupra propriei funcționalități. Proiectul se distinge prin utilizarea swarming-ului de agenți recursivi, unde o ierarhie de agenți colaboratori poate genera agenți copii pentru a descompune sarcini complexe. Implementează un sistem de memorie semantică care combină regăsirea bazată pe vectori cu maparea relațiilor bazată pe grafuri pentru a menține contextul între sesiuni. Pentru a gestiona riscul, sistemul utilizează guvernanța acțiunilor pe niveluri care necesită aprobarea umană pentru operațiuni sensibile și izolează activitățile agenților în worktree-uri git separate. Framework-ul include un toolkit cuprinzător de automatizare a browserului pentru interacțiunea cu paginile web, extragerea snapshot-urilor DOM și capturarea capturilor de ecran. De asemenea, implementează Model Context Protocol pentru a integra instrumente și date externe și suportă hot-reloading binar pentru a actualiza serverul fără a pierde conexiunile de rețea active. Sistemul oferă o interfață de linie de comandă pentru gestionarea memoriilor agenților și include instrumente de audit pentru a urmări progresul planului și a vizualiza topologia roiului de agenți.
Combines semantic vector search with graph-based relationship mapping to retrieve contextual memories.
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
Maps relationships between medical entities to provide context-aware answers from the knowledge graph.
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
Searches code structures using natural language or vector similarity to map relationships and retrieve elements.
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
The product returns specific nodes, properties, or expressions from a result set with aliasing.
Cartography este un framework de vizualizare a infrastructurii bazat pe grafuri și de analiză a securității. Acesta preia date de la diverși furnizori de cloud, identitate și software-as-a-service pentru a modela relații complexe între resurse, utilizatori și descoperiri de securitate într-o bază de date grafică centralizată. Prin maparea acestor interdependențe, platforma permite organizațiilor să obțină vizibilitate asupra mediului lor și să identifice riscurile potențiale de securitate prin interogări de traversare a grafului. Platforma se distinge prin normalizarea bazată pe ontologie și corelarea entităților cross-platform, care mapează date eterogene din surse multiple într-un model unificat și consistent. Utilizează pipeline-uri de ingestie modulare și filtrare bazată pe schemă pentru a menține acest graf, asigurându-se că datele infrastructurii rămân precise prin eliminarea automată a nodurilor învechite bazată pe stare. Această abordare permite descoperirea căilor de atac complexe și a configurărilor greșite de securitate care se întind pe sisteme disparate de cloud, dispozitive și gestionare a identității. Dincolo de modelarea de bază, sistemul oferă capabilități extinse pentru inventarul activelor, guvernanța identității și analiza lanțului de aprovizionare software. Suportă o gamă largă de integrări, inclusiv resurse de calcul și rețea cloud-native, telemetrie de gestionare a endpoint-urilor și metadate ale ciclului de viață al dezvoltării. Utilizatorii pot extinde funcționalitatea platformei prin definirea de reguli de securitate personalizate, adăugarea de joburi specializate de analiză a datelor sau integrarea de noi surse de informații prin framework-ul său modular. Proiectul este implementat în Python și oferă documentație pentru configurarea modulelor de ingestie și definirea interogărilor grafice personalizate.
Applies semantic labels and standardized properties to diverse resource types to enable consistent cross-platform queries.
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
Extracts schemas and relationships directly from existing graphs to eliminate manual definition.
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
Queries knowledge graphs with recursive and multi-hop reasoning to find relevant entities.