# Hybrid memory

> Retrieve relevant context without allowing memory to become automatic truth.

Source: https://accd.github.io/verchestra/docs/concepts/hybrid-memory/
Content digest: `sha256:6ce7d3fd0fcffcc06ca47e8ab36fd2806ad39576fdab755d3e269d2676412f51`

Verchestra combines local relational storage with vector and textual retrieval.

The relational layer preserves identities, versions, provenance, policy, and deterministic filters. Vector search finds semantically related knowledge even when wording differs. Text search remains valuable for exact names, identifiers, and error messages.

Retrieved memory is a candidate source. It must keep provenance and recency, pass policy filters, and be confirmed against authoritative project evidence before it changes delivery state.

Shared, source-bound knowledge may be committed. Local indexes, embeddings, caches, credentials, and machine history remain rebuildable and untracked.