OpenCyc
Cyc began in 1984 as a long-running effort to write down the everyday knowledge people take for granted, the kind of common sense that lets you infer that a person cannot be in two places at once. OpenCyc is the freely released slice of that work, offering a large ontology of concepts and the assertions that relate them.
The knowledge is organised for reasoning rather than plain lookup, so it captures categories, rules, and relationships that support inference. The public OpenCyc releases are no longer maintained, but the final dumps remain available if you want to study the approach or reuse the ontology.
For RAG, OpenCyc is more of a specialist and historical resource than an everyday fact source. It is interesting if you are working on structured reasoning or want a hand-curated backbone of concepts, rather than broad, current coverage.
Related sources
DBpedia
A knowledge graph built by pulling the structured parts of Wikipedia, mainly the infoboxes, into machine-readable data. It holds billions of facts about people, places, organisations, and more as RDF triples, small subject, predicate, object statements, which you can search with the SPARQL query language.
Freebase
A collaborative knowledge base once run by Google, now retired but still available as downloadable data dumps. It holds structured facts about millions of entities, and much of its content has since moved into Wikidata.
Wikidata
A free, collaborative knowledge base that holds structured facts for Wikipedia and the other Wikimedia projects. More than 100M items, each one machine-readable with statements, relationships, and identifiers, so you can pull clean facts instead of parsing article prose. Released into the public domain under CC0.
Wikipedia
Complete database dumps of Wikipedia and the other Wikimedia projects, in every language, refreshed roughly twice a month. The most widely used knowledge source for RAG systems, and an easy first corpus to build a retrieval pipeline on.