mcp-memory-service v10.51 — 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 v10.51

Plugin hooks live — wire your logic into every memory event. ~1,838 tests.

Plugin Hooks Are Live

Fire points wired into MemoryServiceon_store, on_delete, on_retrieve, on_consolidate now called at actual lifecycle events. Install a plugin package and it receives live events automatically. (PR #864, @filhocf)

Dynamic Type Dropdowns

New GET /api/types endpoint returns all valid memory types — built-in and custom (MCP_CUSTOM_MEMORY_TYPES). Dashboard filter and store-form dropdowns now populate dynamically, so custom ontology entries appear in the UI automatically. (PR #863, @filhocf)

📄

Audit-Log Example Plugin

Reference implementation in examples/plugins/audit_log/ demonstrating all four hooks with standard entry_points packaging. A complete, working plugin you can fork as a starting point. Living documentation for the plugin API. (PR #867, @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