🧠 Agent Memory MCP

Persistent key-value memory for AI agents — like Redis, but simpler. Built for the MCP ecosystem.

MCP Server Python 3.10+ MIT License v1.0.0
⭐ Star on GitHub 💎 Go Pro — $19/mo

Why Agent Memory?

AI agents lose all context between sessions. Every conversation starts from zero. Agent Memory MCP fixes this by giving agents a persistent, searchable memory that survives restarts, crashes, and context-window limits.

⏱️ TTL Support

Auto-expiring memories with second-level precision. Set it and forget it.

📁 Namespaces

Organize memories by project, user, or domain. Isolated storage per namespace.

🔍 Fuzzy Search

Find memories by keyword across all namespaces. Case-insensitive, ranked by relevance.

📊 Access Tracking

Every memory tracks create time, last access, and access count for analytics.

🔒 Thread-Safe

POSIX file locking ensures safe concurrent access from multiple agents.

💰 Free Tier

1,000 entries free. Need more? Go Pro for unlimited storage at $19/month.

Quick Install

pip install agent-memory-mcp

Tools

memory_remember — Store a value with optional TTL
memory_recall — Retrieve a value + metadata
memory_forget — Delete a key permanently
memory_search — Search all namespaces by keyword
memory_list_namespaces — List namespaces with counts
memory_clear_namespace — Wipe a namespace
memory_stats — Global storage statistics