mcp-memory-service v10.54 — 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.

GitHub PyPI Package

What's New in v10.54

AND/OR tag filtering for memory_search. ~1,875 tests.

🏷

AND/OR Tag Filtering in memory_search

The tag_match parameter (already in memory_delete) is now available in memory_search. Use "all" to require every tag to match (AND), or "any" (default) for OR — existing callers are unaffected. (PR #890, @filhocf, closes #889)

Milvus Consolidation Fixed

Completes a 4-PR series that fixes a production failure on Milvus deployments where consolidation produced 0 clusters/associations. All backends now pass include_embeddings=True on bulk reads. (PR #885, @henry201605)

🔍

Cascading Search Fallback

Opt-in BM25 + tag-intersection fallback in retrieve_memories for sparse semantic results. Merged and de-duplicated up to n_results. Default off — no breaking change. (PR #883, @filhocf)

How It Works

Claude.ai connects to your memory server through Streamable HTTP with OAuth 2.1 authentication.

Browser
Claude.ai
Transport
Streamable HTTP
Auth
OAuth 2.1 + PKCE
Server
MCP Memory
Storage
Knowledge Graph
Data flow Auth boundary

Built for Production

Battle-tested with comprehensive testing and optimized for performance.

0
Tests
0
AI Apps Supported
0
Read Latency
0
Cache Speedup

Get Started in Seconds

Install from PyPI and connect your AI agents to persistent memory.

Click to copy pip install mcp-memory-service