Core Concepts
The architecture behind CortexDB — five memory layers, event sourcing, bi-temporal time, scopes, and hybrid retrieval.
CortexDB is built on a small set of ideas that fit together. Read these in order for the full model, or jump to what you need.
- The Five Memory Layers — Events → Episodes → Facts → Beliefs → Understanding. Only Events are not derived.
- Event Sourcing — the immutable event log is the source of truth; every other store is a rebuildable cache.
- Bi-temporal Model — two time axes: when something was true, and when CortexDB learned it.
- Scopes — the single hierarchical namespace primitive that carries ACLs, quotas, and audit.
- The Experience Envelope — one payload shape for every kind of ingest.
- Lifecycle & Async Writes — the six atomic operations and the SSE stream; writes are async by default.
- Authorization — PASETO tokens and the four-tier capability stack.
- Knowledge Graph — an entity graph emergent from Facts and Beliefs (opt-in).
- Hybrid Retrieval — BM25 + vectors + graph + rerank, fused with RRF.
Running CortexDB yourself? Several capabilities (Facts/Beliefs extraction, graph traversal, cross-encoder rerank) are opt-in and off by default self-hosted. See Self-hosting defaults.
Connecting AI Assistants
Give Claude, ChatGPT, Cursor and other AI assistants CortexDB memory, through the local MCP package or remote MCP served by your own server with OAuth sign-in.
The Five Memory Layers
How CortexDB models memory across Events, Episodes, Facts, Beliefs, and Understanding — and why single-layer systems fail.