Back to directory

Statewave

An open-source memory runtime for AI agents that compiles raw events into typed, provenance-tagged memories and assembles deterministic, token-bounded context bundles instead of retrieving them fresh at query time.

Statewave

Statewave is an open-source memory runtime for AI agents, giving them durable, structured memory instead of starting each conversation from scratch. It is infrastructure run alongside an application, not a chatbot framework, a vector database, a RAG pipeline or a hosted service.

It follows a four-step lifecycle organized around subjects such as a user, account, agent or repository: raw events are ingested append-only, compiled once per subject change into typed, summarized memories with confidence scores and provenance, assembled into ranked, token-bounded context bundles on demand, and governed by inspecting a subject's timeline, tracing a memory to its source, or deleting it. The same query against the same subject at the same point in time always returns the same bytes, and recompiling or reassembling produces no duplicates.

It self-hosts on Postgres with pgvector and provides Python and TypeScript SDKs.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.