Neo4j
The graph database behind most GraphRAG work — relationships as first-class data rather than joins.
Highlights
- Native vector indexes for storing and querying embeddings alongside graph data
- Cypher query language for multi-hop traversal of nodes and relationships
- GraphRAG patterns that ground LLM answers in a knowledge graph to cut hallucination
- Graph Data Science library with 65+ algorithms for centrality, similarity and pathfinding
- AuraDB fully managed cloud service across AWS, Azure and Google Cloud
- LLM Knowledge Graph Builder to construct graphs from unstructured documents
- Integrations with LangChain, LlamaIndex and major hyperscaler AI stacks
- ACID transactions and role-based access control for production workloads
External link — opens neo4j.com in a new tab. Neo4j is a third-party product; we are not affiliated with it.
About Neo4j
What it is
Neo4j stores data as nodes and relationships rather than rows and tables, which makes connected queries — paths, neighbourhoods, degrees of separation — natural rather than expensive. Founded in 2007, it has become central to GraphRAG, where an AI application queries a knowledge graph to ground answers in explicit, traceable relationships.
Why it's different
Its relevance to AI is newer than the product and worth understanding. Vector search retrieves text that is semantically similar to a question, which works until the answer requires connecting facts that appear in different documents — and similarity cannot follow a relationship. A graph can, and it can show the path it followed, which makes the answer inspectable in a way embeddings never are. The costs are real: building and maintaining a knowledge graph is substantial work, graph modelling is a skill most teams do not have, and Cypher is another query language to learn. Many problems that people reach for a graph for are adequately served by a relational database with decent indexes.
How people use it
It is used for fraud rings, supply chain dependencies, identity resolution, recommendations, and increasingly for grounding AI answers where provenance matters — regulated domains especially, because being able to show which relationships produced an answer is close to an audit trail. The practical route in is a narrow, genuinely connected problem, since the payoff appears where queries traverse several hops and disappears where they do not.
Written by the n3os team. We are not affiliated with Neo4j.
This listing was written from public information, without Neo4j’s involvement. If you own it and something here is wrong — or you would rather not be listed at all — email us and we will correct or remove it.
Get the ones worth knowing about
We write one of these for every tool worth the trouble. Get the new ones, plus what we have found genuinely useful lately.
Your address goes to Buttondown, who send the emails on our behalf. One click unsubscribes, and the list is never sold or shared.