Most writing about graph databases and GraphRAG is either marketing copy or a research paper. This blog sits in between: engineering deep dives on graph query performance, knowledge-graph modeling, agent memory and retrieval-augmented generation, written by the team building FalkorDB.
https://www.youtube.com/watch?v=pHJ997s8N4U Webinar Recording Overview Roi Lipman, CTO & Co-founder, and Gabriel Gomez, Core Software Developer, break down how FalkorDB finds shortest paths at scale. Finding
FalkorDB 6.0 is the first release built on the new Rust engine. 39% fewer CPU instructions, 226 bugs closed, and existing Cypher queries work without changes.
80,000 lines of Rust, 357 merged pull requests, 1,585 TCK scenarios and 1,322 flow tests green. FalkorDB’s new engine is here, and this is the
The FalkorDB webinar demonstrates graph algorithms for cybersecurity: ransomware spread simulation, Log4Shell dependency tracing, and max-flow data leakage analysis, showing practical UDF and flow network applications.
Securin optimized their AI security agents by migrating from leading graph database provider to FalkorDB, achieving 0.3s latencies on complex 7-hop queries and eliminating a 25% query failure rate.
FalkorDB on Snowflake lets you query warehouse tables as native graphs with Cypher, SPCS-backed compute pools, reference binding security, and explicit lifecycle control for production workloads.
Context graphs transform AI agents from stateless responders into context-aware systems with institutional memory. Learn how to capture the “why” behind decisions using FalkorDB’s graph technology.
mem0-falkordb gives AI agents persistent graph memory via FalkorDB — replacing flat vector retrieval with entity-relationship traversal, per-user graph isolation, and sub-140ms query performance.
The FalkorDB canvas web component lets you take canvas data and embed the default browser canvas as a standalone component in your own UI.
Choosing the best database for knowledge graphs determines your AI stack’s performance ceiling. We compare FalkorDB, Neo4j, ArangoDB, Neptune, and JanusGraph—analyzing latency, GraphRAG readiness, and operational overhead.
FalkorDB introduces native array and range indexing for graph databases, enabling O(log n) queries on multivalued properties without schema normalization, delivering 10-100x speedups.
Vector databases fail at complex Text-to-SQL when queries span multiple tables. We built QueryWeaver using FalkorDB to map schema relationships as a knowledge graph, solving multi-hop queries that vectors miss.
FalkorDB introduces user-defined functions (UDFs) written in JavaScript, allowing developers to extend graph database functionality with custom logic. FLEX library provides pre-built functions for text processing, similarity metrics, and date manipulation.
Text-to-SQL systems hallucinate tables and columns because LLMs get no relational context. Graph-based semantic layers represent the schema as a knowledge graph, so retrieval can traverse real foreign keys, prune irrelevant tables, and ground every generated query in the actual database.
A technical guide to graph databases covering core concepts, query languages, use cases, and implementation practices for AI architects and developers.
FalkorDB v4.14.10 reduces memory footprint by 30% through compact storage architecture, accelerates write operations via batch processing, and implements auto-shrink for deletion cycles.
Code graph analysis converts source code into visual relationship maps. FalkorDB’s tool parses repositories to reveal function calls, class hierarchies, and module dependencies developers miss.
FalkorDB partners with Datax Solution FZC as Middle East distributor, extending access to low-latency graph database built for GraphRAG, AI workloads & real-time analytics across the region.
Learn how to implement Model Context Protocol agent memory using Graphiti MCP Server with FalkorDB for isolated, persistent context and multi-tenant knowledge graphs in production AI systems.
Connect your FalkorDB knowledge graph to N8N to take full advantage of your graph database. In a vector database, you’re searching for similarity. Sometimes the “most similar” document isn’t actually what you need. In a graph database, you’re traversing explicit relationships. Either a parameter belongs to an endpoint, or it doesn’t. There’s no guessing.
FalkorDB Browser now supports Personal Access Tokens for secure API authentication. Generate granular, long-lived JWT credentials for automated scripts and CI/CD pipelines using our documented API.
FalkorDBLite brings SQLite-style simplicity to graph databases. Spin up a lightweight sub-process with zero network overhead, process isolation, and no configuration required for prototyping and testing.
Graph algorithms go beyond basic queries to surface hidden attack paths, insider threats, and structural vulnerabilities. Learn how Betweenness Centrality, WCC, and CDLP detect risk in real systems.
FalkorDB unites OLTP precision and OLAP speed through sparse adjacency matrices, enabling vectorized graph traversal and direct node access for AI-driven connected data workloads.
FalkorDB has been selected as one of three finalists for the Cyber Startup Challenge 2025, competing for a CHF 100,000 contract to integrate graph database technology into Swiss cyber defense.
FalkorDB’s new LangChain JS/TS package lets users query graph data with natural language. The integration auto-generates Cypher queries and returns plain language responses.
KuzuDB has gone through EOL. FalkorDB has put together a simple, 2-step migration guide for developers looking for an alternative graph database.
Read about security graphs to model complex cloud relationships between users, roles, policies, and resources. Using FalkorDB, query indirect access chains, enforce least privilege, and detect lateral movement risks in real time for CIEM and threat analysis.
Rewatch FalkorDB’s ‘Implementing Agentic Memory’ workshop with Graphiti and QueryWeaver, and read the questions and answers from the session.
G.V() 3.38.90 brings full FalkorDB support, letting AI developers connect their LLM-optimized graph database for instant visualization. Perfect for agentic AI applications and advanced chatbots.
Security teams need real-time attack path discovery across multi-cloud environments. Graph databases process entity relationships for sub-100ms threat analysis.
We built Text-to-Cypher to let you chat with FalkorDB graphs using plain English. Get instant Cypher query generation via REST API or MCP server. Open source, Docker-ready, with real-time SSE updates.
One of the lesser-known challenges is the memory consumed by storing identical string values over and over again. Think of common attributes like “city,” “category,” or “status” that might appear on thousands, or even millions, of nodes and edges. A powerful solution to this problem is string interning.
Zep founder Daniel Chalef joins FalkorDB, details Graphiti, a graph framework for real-time LLM memory and RAG. It handles dynamic data better than vector search.
Migrate from Neo4j to FalkorDB for ultra-low latency, multi-tenancy, and GenAI-ready graph solutions. Follow our step-by-step guide.
As a Cloud Security vendor, you’re building protection systems for environments that constantly change. Your customers deploy across containers, serverless, ephemeral compute, and IaC pipelines. You need to correlate misconfigurations, permissions, and runtime signals across identity, network, and workload layers, at scale, in real time, without losing performance or exceeding the scoped operational costs. That’s where graphs come in.
FalkorDB BYOC deployment now spans AWS and Google Cloud Platform. Run fully managed graph database instances directly within your cloud subscription while maintaining data sovereignty across all major cloud providers.
This post is a hands-on walkthrough for developers who want to get up and running with Graphiti and FalkorDB, fast.
This maintenance and enhancement release delivers significant performance improvements for parameter-heavy operations and strengthens operational reliability across cloud deployments.
Graphiti now supports FalkorDB backend for multi-agent environments, addressing performance and isolation requirements in production AI agent deployments with sub-10ms queries.
FalkorDB achieves SOC 2 Type II certification, demonstrating enterprise-grade security controls for multi-tenant graph database operations and mission-critical applications.
Knowledge graphs represent complex relationships as nodes and edges. This workshop demonstrated practical implementations through two systems: VCPedia for venture capital data extraction and Fractal KG for self-organizing graph structures.
Bank of America proves small LLMs and GraphRAG deliver scalable, compliant AI with low latency and precise context retrieval in production environments.
Developers voted FalkorDB HackerNoon Startup of the Year 2024 for Tel Aviv after shipping sparse-matrix storage, AVX-accelerated queries, and multi-tenant clustering with sub-10 ms tail latency.
Hands-on look at Multigraph Topology: how key-space slots isolate customer graphs, why replicas sustain 120 K QPS, and when to scale masters vs replicas in graph ACL systems.
MCP simplifies how LLMs access tools and graph databases. Learn how FalkorDB’s MCP server enables structured, scalable AI integrations.
Graph Query Language demystified: learn how FalkorDB simplifies querying for LLM and GraphRAG workflows using Cypher-like syntax.
