mcp-memory-service v10.48 — 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 v10.48

Contradiction chain retrieval + auto-supersession on high-confidence conflicts. ~1,785 tests.

include_superseded Filter

All retrieval paths (memory_search, retrieve, retrieve_with_quality_boost, retrieve_hybrid) and all backends now accept include_superseded=True to surface the full contradiction chain. Default behavior unchanged. (PR #814, @filhocf)

📊

Auto-Mark Superseded

The consolidator automatically marks the older memory as superseded_by the newer one when a contradicts relationship is detected with confidence ≥ 0.75. Single batched transaction, thread-safe. No DB migration needed. (PR #814, @filhocf)

📦

Full Contradiction Chain

Contradiction chains are now first-class: store, auto-link, and retrieve conflicting memories across all storage backends. Partial implementation of RFC #732 โ€” write-side counterpart coming in a follow-up PR.

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