Open-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.
-
Updated
Sep 8, 2026 - Python
Open-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.
Multiple agents, one source of truth: a Planner/Coder/Reviewer demo of how a shared Statewave subject prevents parallel-agent context collisions.
Multi-agent demo for Statewave conflict resolution. Concurrent agents write to a shared subject; the compiler detects contradicting facts via Jaccard similarity and supersedes the stale one with provenance. FastAPI + SSE, Apache-2.0.
FastAPI reference app for Statewave memory integration. Wraps every chat turn with get_context before the LLM call and record_episode after; seeded demo users show compiled facts and token-budgeted context. Self-hosted, Postgres + pgvector.
Statewave use case in TypeScript: a grounded product advisor and support assistant, with an Ops Assistant that tracks and closes content gaps.
Official website for Statewave — open-source memory runtime for AI agents
Runnable examples for Statewave — quickstart, support agent, and coding agent.
Connector ecosystem for Statewave — feed real-world events into agent memory
Architecture docs, API contracts, ADRs, and guides for the Statewave workspace.
Admin dashboard and CLI for Statewave — manage episodes, memories, and subjects.
Official TypeScript SDK for Statewave — fetch-based client, full type definitions.
Reusable Statewave chat packages — chat-core, chat-react, chat-widget
To associate your repository with the statewave topic, visit your repo's landing page and select "manage topics."