v10.30 — Now Available

MCP Memory Service

Persistent memory for AI agents. Semantic search, knowledge graph, automatic consolidation — now accessible from Claude.ai via Streamable HTTP.

GitHub PyPI Package

What's New in v10.30

Memory Evolution: non-destructive updates, lineage tracking, staleness scoring, and automatic conflict detection.

🔁

Non-Destructive Versioned Updates

Update a memory without losing its history. update_memory_versioned() creates a child node atomically and marks the parent as superseded — full lineage preserved, active queries see only current versions.

🕐

Staleness Scoring & Decay

Time-decayed confidence: memories grow stale automatically. Configure decay window via MEMORY_DECAY_WINDOW_DAYS. min_confidence filtering on all backends keeps retrieval results fresh.

Automatic Conflict Detection

Every store operation checks for contradictions (cosine > 0.95 + Levenshtein divergence > 20%). New memory_conflicts and memory_resolve MCP tools. REST: GET /api/conflicts, POST /api/conflicts/resolve.

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