Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

Knowledge graph

A knowledge graph stores information as entities (people, products, places, concepts) connected by named relationships, so software can follow links between facts instead of searching through loose text.

Also called: KG

By Divya Sharma · Checked Nov 15, 2026 · How we review

In a knowledge graph, "Acme Corp", "Jane Doe" and "Berlin" are nodes, and edges say how they relate: Jane Doe works at Acme Corp, Acme Corp is based in Berlin. Facts are often written as triples of subject, relation and object. Graph databases such as Neo4j and standards such as RDF and SPARQL are common ways to store and query them.

Why it matters for AI

Vector search finds passages that sound like the question. It is weaker at questions that need several hops, such as "which suppliers of our Berlin office also serve our competitors?" A graph can answer that by following edges. Graphs also give a model clean, structured facts to ground its answer, which can reduce hallucination.

How they are built

Curated graphs are built by hand or from structured data. Newer approaches use an LLM to pull entities and relationships out of documents automatically, which is the first step of GraphRAG. Extraction errors and duplicate entities ("IBM" vs "International Business Machines") are the usual problems.

Knowledge graph vs knowledge base

A knowledge base is any collection of information a system can draw on. A knowledge graph is one way to structure it, with explicit links between entities.

The knowledge graphs guide compares tools, and agent memory systems increasingly store facts as graphs too.

Related terms

GraphRAG
GraphRAG is a retrieval approach where an LLM first builds a knowledge graph from a document collection and writes summaries of related groups of entities, then answers questions using those summaries and graph links.
Knowledge base (AI)
In AI apps, a knowledge base is the collection of documents and data that an assistant or agent searches to answer questions, such as help articles, policies or product docs, kept separate from the model itself.
Retrieval-augmented generation
Retrieval-augmented generation (RAG) is a pattern where a system first searches a collection of documents for passages relevant to a question, then gives those passages to a language model so its answer draws on them.
Agent memory
Agent memory is the set of techniques that let an AI agent keep information beyond a single context window, such as facts about a user or past work, by storing it outside the model and loading it back when needed.
Grounding
Grounding is tying a language model's answer to specific, checkable sources, such as search results, documents or a database, so that its claims rest on supplied evidence rather than only on training data.

Sources