Multi-graph and multi-tenancy
Run multiple graphs and tenant workloads on the platform, with graph access control available across the listed plans. This supports applications that keep distinct data domains or customer environments separated.
FalkorDB is a Redis-based graph database for graph analytics, GraphRAG, agent memory, and other applications built on interconnected data. It helps technical teams structure and query relationships for AI applications, chatbots, fraud detection, and security analysis.
FalkorDB is a Redis-based, open-source graph database for applications that depend on interconnected data. It is positioned for GraphRAG, agent memory, graph analytics, chatbots, fraud detection, and security workloads, with support for multiple graphs and tenants.
The platform lets teams represent domain entities and their relationships, then query that context for AI and operational applications. Its GraphRAG SDK adds ingestion for structured and unstructured sources, ontology discovery and refinement, knowledge-graph construction, and multi-agent orchestration. Deployment and operational features such as TLS, VPCs, clustering, high availability, automated backups, and enterprise support depend on the selected plan.
Run multiple graphs and tenant workloads on the platform, with graph access control available across the listed plans. This supports applications that keep distinct data domains or customer environments separated.
Combine large language models with domain-specific knowledge graphs to support natural-language queries, traceable retrieval logic, relationship-based context, and structured answers.
The GraphRAG SDK provides an ETL workflow for sources including PDF, CSV, HTML, TXT, JSON, and URLs, helping teams turn varied source material into graph-based knowledge.
Generative AI can detect and construct ontologies from datasets. Teams can review, modify, iterate on, and constrain the detected ontology before using it to build a knowledge graph.
FalkorDB supports Cypher queries and graph traversal for exploring entities and relationships. These capabilities are used for retrieval, recommendations, anomaly analysis, and investigations.
Plan-dependent operations include TLS, VPC support, clustering, high availability, multi-zone deployment, continuous persistence, automated backups, and enterprise support. The site lists AWS, Azure, and GCP as cloud providers.
Teams can connect LLMs to structured and unstructured domain knowledge, use ontology-driven graph construction, and retrieve relationship-aware context for more traceable and relevant responses.
Developers can combine graph traversal with vector search to build personalized agentic systems. User profiles, preferences, activities, and persistent context can be connected for adaptive interactions.
Conversational applications can extract entities, link facts, and map relationships across user, product, and session data to maintain longer-term context and provide real-time recommendations.
Financial crime teams can model transactions, accounts, institutions, IPs, and devices to trace fund flows, identify hidden relationships, correlate accounts, and investigate suspicious patterns.
Security vendors can store findings, vulnerabilities, assets, and related entities in a flexible graph, then query interconnected security domains for near-real-time analysis and threat surfacing.
FalkorDB is an open-source, Redis-based graph database focused on graph workloads such as GraphRAG, agent memory, graph analytics, and multi-tenant applications.
The SDK describes an ETL workflow for structured and unstructured data, including PDF, CSV, HTML, TXT, JSON, and URLs. It can use generative AI to construct knowledge graphs from those sources.
Yes. The GraphRAG SDK can detect and construct ontologies from datasets, while allowing users to review, modify, iterate on, and constrain the detected ontology.
Yes. The pricing page lists a free plan for building an MVP, with multi-graph and multi-tenancy and graph access control. TLS, clustering, high availability, backups, and other operational capabilities vary by paid plan.
The site lists AWS, Azure, and GCP as cloud providers. It also describes deployment through cloud infrastructure or containerized environments; specific operational features depend on the plan.
memgraph.com
Memgraph is an in-memory graph database for GraphRAG, AI memory, agentic AI, and real-time graph analytics. It uses Cypher and provides tools for querying, visualization, algorithms, and streaming data workflows.
wellapp.ai
Well connects business tools, documents, and data in one context graph, helping teams and agents capture, structure, reconcile, enrich, and query operational data.
neo4j.com
Neo4j Graph Intelligence Platform connects data as a graph so teams can query relationships, analyze connected data, and build knowledge layers for AI systems. It supports fully managed cloud services and self-managed deployments.
www.stardog.com
Stardog is an enterprise knowledge graph-powered semantic AI platform that unifies distributed data and adds ontology-based context for analytics, AI applications, and connected decision-making. It is available for on-premises and cloud enterprise deployments, with a free commercial license for exploration.
system.com
Explore connected scientific evidence with an AI-powered graph, research applications, and APIs.