mcp-memory-service v10.66 — Now Available
Memory for AI Agents
Persistent memory for AI agents — REST API, MCP, OAuth, CLI, dashboard. Semantic search, knowledge graph, automatic consolidation. One self-hosted service, every transport.
mcp-memory-service v10.66 — Now Available
Persistent memory for AI agents — REST API, MCP, OAuth, CLI, dashboard. Semantic search, knowledge graph, automatic consolidation. One self-hosted service, every transport.
Reasoning engine (RFC #732): transitive closure, abductive inference, entity grouping, insight cards. SQL-level time filter enforcement. ~1,828 tests.
Phase 1a of the reasoning engine (RFC #732). Transitive closure walks multi-hop graph edges to surface indirect memory connections. Abductive inference proposes the most plausible explanations for observed memory patterns using NLI-backed scoring. (PR #1009)
Phase 1b clusters co-referenced entities across memories into canonical groups, enabling accurate cross-memory entity resolution. Entity groups feed directly into the transitive closure engine so edges between aliased entities are correctly traversed. (PR #1010)
Phase 3 introduces insight cards — structured summaries synthesised from related memory clusters, surfaced via REST API and the memory_graph tool. Also fixes time-range filters (start_date, end_date, stale_days) to be enforced at SQL level, eliminating out-of-window results. (PR #1011, #1014)
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.