mcp-memory-service v10.57 — 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 v10.57

Tag-match AND/OR filtering for memory_list and automatic session chunking. ~1,960 tests.

🏷

AND/OR Tag Filtering for memory_list

New tag_match parameter for the memory_list MCP tool and REST API: "any" (OR, default) returns memories matching at least one tag; "all" (AND) returns only memories matching every supplied tag. Implemented across sqlite_vec, cloudflare, and hybrid backends.

📋

Automatic Session Chunking

memory_store_session now auto-splits long sessions at turn boundaries (User:, Assistant:, Human:, etc.). Configure with SESSION_CHUNK_SIZE env var (default: 1500 chars, 0=disabled). Chunks tagged chunk:N/M for sequential retrieval. Fully backward compatible.

🔗

Built on v10.55-10.56 Foundation

Extends the entity extraction, insight cards, and configurable maintain scan limit capabilities introduced in recent releases. Complete AND/OR tag filtering now unified across memory_search, memory_delete, and memory_list.

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