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 re-embedding migration no longer drops your knowledge graph, locale-aware NER/NLI ship as YAML plugins, and both Docker images now carry the maintenance and migration scripts. ~2,698 tests.
migrate_sqlite_vec_embeddings.py rebuilt the database from memories alone, silently dropping memory_graph edges and derived beliefs on every re-embed. Both now survive the swap, keyed on their content hashes. (#189, reported by @tecnobrat)
Entity extraction and contradiction detection now load per-locale YAML pattern files instead of hardcoded regex. Ships with en and pt_BR; adding a language is two YAML files and zero Python code. (#54)
scripts/maintenance and scripts/migration are now in both published images, so re-embedding or cleanup no longer needs a docker cp into a running container first. (#188)
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