Question 1

What is Statewave?

Accepted Answer

Statewave is an open-source memory runtime for AI agents. It records raw events as immutable episodes, compiles them into typed semantic and episodic memories with provenance, and returns ranked, token-bounded context bundles that LLM applications can drop straight into a prompt.

Question 2

How is Statewave different from a vector database?

Accepted Answer

A vector database stores embeddings and returns nearest neighbours. Statewave is a memory runtime that uses a vector store (pgvector) underneath, but adds typed semantic and episodic memories, deterministic ranking with explainable signals, idempotent compilation, provenance back to source episodes, temporal validity windows, conflict resolution, and a token-bounded context-assembly step. It also persists raw episodes append-only so memory can be recompiled.

Question 3

Can Statewave be self-hosted?

Accepted Answer

Yes. Statewave is designed to be self-hosted. The storage layer is Postgres-only with the pgvector extension. A Docker Compose setup runs the full stack locally in two minutes; production deployments target Fly.io, Railway, or any container platform. There is no managed Statewave cloud — episodes and compiled memories stay in your infrastructure.

Question 4

Is Statewave open source? What about commercial use?

Accepted Answer

Yes. Statewave is open source under the Apache License 2.0 — server, Python and TypeScript SDKs, connectors, and this site. Apache-2.0 is permissive and includes an explicit patent grant, so you can use, modify, distribute, self-host, and build proprietary or commercial products with Statewave without a separate agreement. Optional enterprise support — SLA, indemnity, procurement, managed hosting, architecture review — is available as a services contract: contact licensing@statewave.ai.

Open-source memory runtime for AI agents