Persistent memory for AI agents — REST API, MCP, OAuth, CLI, dashboard. Semantic search, knowledge graph, automatic consolidation. One self-hosted service, every transport.
Interactive 3D knowledge graph — every memory a glowing node, every relationship a curved edge.
MINOR release: the knowledge-graph layer actually works now. Entity extraction was discarding every memory tag, so memory_explore returned nothing on any store. ~2,839 tests.
maintain's batch extraction discarded every memory tag before it reached the entity extractor, and two graph features were gated on a storage attribute nothing ever set. A 16,986-memory store had zero entities. (#218, #219)
The memory CLI's launch/stop/restart/info/health commands verify certificates by default now, completing the self-signed-cert opt-in, and a stray .env no longer decides the CLI's scheme behind your back. (#216, #224, thanks timkjr)
Milvus implements the storage methods the web API was calling unguarded, fixing 501s on /api/tags (#214, reported by @ghulands). Token-efficient retrieval and the two-phase entity tools get their first user-facing docs. (#215, #217, #220, #222)
Claude.ai connects to your memory server through Streamable HTTP with OAuth 2.1 authentication.
Battle-tested with comprehensive testing and optimized for performance.
Talks and coverage from the community.
Heavybit's Humans in the Loop deep dive talks to maintainer Heinrich Krupp about agent amnesia and why persistent memory is the missing infrastructure layer for agentic systems.
Maintainer Heinrich Krupp presents mcp-memory-service at the AI Tinkerers Zürich meetup — persistent memory architecture, semantic search, and multi-agent memory sharing. Watch the full video →
Install from PyPI and connect your AI agents to persistent memory.
I help teams run self-hosted memory in production — OAuth, hybrid sync, multi-client rollout. Free 30-minute intro call.
Get in touch