FalkorDB

FalkorDB is a Redis-based graph database that supports the property graph model and the OpenCypher query language, includes a built-in graph algorithm module, and stores graph data as sparse matrices.

FalkorDB is an open-source graph database compatible with the Redis protocol and the openCypher query language.

有 Groq API 密钥时，Groq 可以驱动工具循环；没有时，确定性回放会针对 FalkorDB 执行相同的工作流。

BatchZero 是一个为 FalkorDB 赛道打造的 Graph Hacks 2026 项目，使用合成数据演示疫情调查工作流，并非真实公共卫生系统。

FalkorDB is implemented in C and compatible with the Redis protocol, offering sub-10-millisecond graph query latency.

GraphGuard persists completed investigations and evidence as first-class nodes (Investigation, Evidence) in FalkorDB, enabling cross-session agent memory.

FalkorDB provides full support for MERGE, ensuring that seed scripts and event log updates do not create duplicate entities.

The GraphGuard project combines the graph database FalkorDB with an AI agent based on Gemini and LangChain for cybersecurity investigations.

LedgerLens's search_memory tool retrieves via FalkorDB full-text index, based on keyword matching and without relying on embedding models, so latency is extremely low.

LedgerLens's read operations are executed through GRAPH.RO_QUERY, which is enforced read-only on the server side and cannot write or modify the graph structure.

In v6, FalkorDB's algorithm API is inconsistent: most procedures accept a configuration map, but algo.pageRank still accepts positional parameters.

LedgerLens uses FalkorDB graph algorithms as part of its tool menu, including algo.WCC for gang components, algo.pageRank and algo.betweenness for hubs and brokers, algo.SPpaths for up to three shortest money paths, and algo.maxFlow for funnel capacity between accounts.

The LedgerLens anti-fraud Agent does not use a vector database or hand-written Cypher queries; all memory, data, SOPs, and audit trails are stored in the same FalkorDB graph database.

FalkorDB supports multiple named graphs, so multiple isolated graphs can coexist within the same instance, each with its own schema and data.

In ZEHN Core's graph, every edge is physically of type RELATES, with the semantic type stored in the r.rel_type property, so querying :DEPENDS_ON returns empty.

The ZEHN Core project is built on FalkorDB, took part in the FalkorDB Graph Hacks hackathon, and its code is open-sourced.

The team modeled provenance information as a graph structure: Document-PART_OF->Chunk<-MENTIONED_IN-Entity, and Entity-RELATES {rel_type, fact, spans}->Entity.

Cypher is a graph query language proposed by Neo4j, and FalkorDB is compatible with its syntax.

Pedigree's workflow is: after entering a model ID, it reads the public metadata on the Hugging Face Hub (license, base model, declared training datasets), writes it into the FalkorDB graph database, then traverses upward along the lineage, comparing each child model's declared license against the obligations required by the parent model's license.

The Helio team used FalkorDB to build a synthetic fintech knowledge graph with 7 node types and 14 edge types, simulating an organization of 120 people during a payments migration.