New to SEMQ? Start with the overview
What becomes possible
Six properties that only exist when an AI system has verifiable, portable state.
Reproducibility
Deterministic encodings make AI pipeline outputs stable across hardware and time.
Portability
Hardware-agnostic encoding, so you can move workloads freely without state migration pain.
Versioning
Diff model outputs across versions like source code and catch semantic drift early.
Observability
Structured angle sequences make AI state auditable and loggable.
Caching
Stable angle keys enable exact-match and approximate semantic caches at scale.
Compression
16× smaller state footprint than PQ.
Benchmarks
The numbers speak for themselves
Measured on public datasets. MTEB, BEIR and OMB v1.
vs −36 pp for PQ
Accuracy loss on banking77 (77-class). Same bit budget, 1,200× less damage.
over full context
On LongMemEval-S. SEMQ retrieval beats stuffing the entire transcript into a 1M-context model.
9,511 queries
Bit-identical results across 1,000+ concurrent processes. Cross-architecture. No exceptions.
Early access
Be first to ship with SEMQ.
The SDK lands soon. Join the waitlist to get early access and updates as we ship.
Supported by
