statewave
View on GitHubOpen-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.
Self-hosted memory runtime for AI agents that ingests events, compiles structured memories, and assembles deterministic, token-bounded context bundles with provenance. Runs on PostgreSQL and pgvector and offers Python and TypeScript SDKs.
Use Cases
Persist user preferences across agent sessionsProvide project memory to long-running coding agentsSupply returning-customer context to support agentsTrace assembled context back to source eventsGenerate handoff context for agent escalations
Built With
- Language
- Python
- Frameworks
- FastAPI · LiteLLM · SQLAlchemy · pgvector · PostgreSQL
Tags
agent memory · persistent memory · provenance · context assembly · memory runtime · self-hosted · multi-tenant · PostgreSQL