Describe
Version datasets, transformations, indexes, and retrieval policy.
CoreCortex is an evidence-first engine for configuring, operating, and evaluating retrieval across the storage your corpus actually needs.
CoreCortex gives the corpus a durable contract—what came in, what was derived, where it is indexed, how it is retrieved, and how well that strategy performs.
Version datasets, transformations, indexes, and retrieval policy.
Keep source identity, lineage, relationships, and access boundaries intact.
Return ranked evidence through an explicit, inspectable query plan.
Test relevance, latency, cost, and policy against stable evaluations.
Datasets, transformations, storage, indexes, and query policies live in a reviewable configuration. Validate it before anything changes.
Read the configuration guide →apiVersion: corecortex.io/v1alpha1
kind: Corpus
metadata:
name: support-kb
spec:
datasets:
- support-articles
indexes:
- lexical
- vector
retrievalPlan:
support-hybridCore stays portable and inspectable. CoreCortex Enterprise operates the pipelines and experiments that become expensive at scale.
Build and inspect your own evidence system on open contracts.
Continuous corpus operations for production retrieval systems.
Inspired by the disciplined loop behind autoresearch, CoreCortex Enterprise is designed to test one storage, schema, or mapping decision at a time—and keep only measured improvements.
Validate a configuration and inspect its retrieval plan in ten minutes.
Get started →02 · CONCEPTSLearn the canonical model behind records, fragments, and relations.
Read concepts →03 · RETRIEVALReturn ranked evidence with the plan and index versions that produced it.
Read querying →04 · ARCHITECTURESee why lexical, vector, relational, and graph strategies are pluggable.
Read architecture →Start with open contracts today. Help shape the Enterprise ingestion and research layer for tomorrow.