Persistent memory for AI agents. Semantic search, knowledge graph, automatic consolidation — now accessible from Claude.ai via Streamable HTTP.
New Milvus storage backend — three deployment modes from one code path: Milvus Lite, self-hosted Docker, and Zilliz Cloud. Plus OAuth security hardening and 1,675 tests.
Zero-dependency local .db file via Milvus Lite. Ideal for scripts, CI, and single-user deployments. Set MCP_MEMORY_STORAGE_BACKEND=milvus and go. (PR #721, @zc277584121)
Same code path scales to self-hosted Docker (recommended for MCP servers) and Zilliz Cloud (managed, team/production). @zc277584121 committed to 6-month SLA on backend:milvus issues. (PR #721)
Defense-in-depth guards against CodeQL py/reflective-xss and py/url-redirection in the authorization-code redirect flow. Dangerous schemes rejected; meta-refresh and JS redirect strings properly escaped. (PR #745)
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.