The substrate

CoreCrux

Our database: a GPU-backed, append-only spine for knowledge and decisions. Every write is a signed receipt, every state is reconstructable to the instant, and the whole history replays deterministically. Not a vector store bolted onto a chatbot: the evidence layer the entire platform stands on.

How the substrate holds

An event store you can audit byte by byte

CoreCrux never edits in place. Every state mutation appends once, ordered by a monotonic sequence, and segments are sealed with a BLAKE3 hash that commits to the seal before them. That one design decision is what everything above the substrate borrows its credibility from: a verifier can walk the seal chain offline and prove that nothing was inserted, reordered or quietly rewritten.

The spine is also why the platform scales down as well as up: cold segments hibernate to near-zero memory and rehydrate on demand, and the chain is indifferent to where a segment sleeps. Storage tiering is an operational choice, never an integrity one.

segment #1041

seal b3:7c2f…

hibernated

segment #1042

seal b3:a90d…

warm · mmap

segment #1043

seal b3:e614…

warm · mmap

segment #1044 · open

appending: monotonic sequence

hot

Within a segment, records are covered by a sealed hash and ordered by monotonic sequence. Each seal commits to the hash and sequence of the seal before it, which is what makes a gap detectable rather than deniable. Cold segments hibernate to near-zero memory and rehydrate on demand; the chain does not care where a segment sleeps.

evidencereceipt specCROWN ADRverifier vectors

Not a vector database

Most "AI databases" store embeddings and hope. CoreCrux stores the three things that make an answer defensible: the evidence, its provenance, and time. It is append-only (facts and decisions are events on a spine, never silently overwritten), so you can always ask not just "what does it know?" but "how did it come to know it, and when?"

A receipt for every write

Every write and every answer carries a signed CROWN receipt: a byte-stable, independently verifiable record of what happened. Nothing has to be taken on trust: a third party can re-check the receipt without access to your data.

Verify a live receipt yourself →

Reconstruct any moment in time

CoreCrux can return a signed KnowledgeStateSnapshot: exactly what the system knew at a specific instant. Answer an auditor's "what did you know on the 3rd, and what did you act on it?" with a cryptographic snapshot, not a guess.

Retrieval that shows its work

Answers come from fused lanes: lexical (BM25) and dense, combined and token-budgeted, over a compact on-disk index (the .ccxdi doc-index). This is the same real answer path the benchmark and IQ suites run: no shortcuts, no mock corpus.

Built for audit, and for forgetting

The whole history replays deterministically, so an audit reproduces the exact bytes rather than a plausible re-run: the infrastructure layer beneath regulatory audit. And when something must be erased, erasure is receipt-scoped: the record is removed and the manifest rewritten, with proof of the removal.

Where it surfaces

  • Crux Engine reads CoreCrux to produce answers with evidence.
  • The Crux Daemon ships CoreCrux + the Engine as one local binary.
  • WikiCrux and MemoryCrux are knowledge products built on top of it.

Substrate capabilities

Deep guides