v10.42 — Now Available
MCP Memory Service
Persistent memory for AI agents. Semantic search, knowledge graph, automatic consolidation — now accessible from Claude.ai via Streamable HTTP.
v10.42 — Now Available
Persistent memory for AI agents. Semantic search, knowledge graph, automatic consolidation — now accessible from Claude.ai via Streamable HTTP.
Milvus backend reaches feature parity with SQLite-vec: graph storage, BM25 hybrid search, and consolidation integration. ~1,722 tests.
Full knowledge-graph support for Milvus deployments: BFS traversal, shortest path, subgraph extraction — stored in a dedicated scalar collection with deterministic SHA-256 edge IDs. Zilliz Cloud-compatible schema (dim=2 dummy vector). (PR #762, @henry201605)
Milvus 2.5+ deployments get combined vector + keyword search via RRFRanker and a BM25 function index on the content field (enable_analyzer=True for Zilliz Cloud). Pre-2.5 collections fall back to vector-only automatically. (PR #762)
DreamInspiredConsolidator now initialises MilvusGraphStorage for Milvus backends via lazy async init with asyncio.Lock, enabling automatic relationship inference during consolidation cycles. (PR #762, @henry201605)
Claude.ai connects to your memory server through Streamable HTTP with OAuth 2.1 authentication.
Battle-tested with comprehensive testing and optimized for performance.
Install from PyPI and connect your AI agents to persistent memory.