What is Agent Memory?

Agent Memory is a Model Context Protocol (MCP) server that provides persistent, cross-session memory capabilities for AI agents to store, recall, search, and summarize information effectively.

How does Agent Memory improve AI agent performance?

It enables AI agents to retain context and knowledge across sessions, aggregate diverse information about users or entities, and access a unified memory store for more informed decision-making and interactions.

How are memories retrieved from Agent Memory?

Memories can be efficiently retrieved by keyword search, with results sorted by relevance and recency. You can also aggregate specific knowledge about users or entities from all managed agents.

What kinds of data can Agent Memory store?

Agent Memory can store various types of information including facts, user preferences, interaction records, learned insights, and session context, with an optional time-to-live (TTL).

Can I search for memories across multiple AI agents?

Yes, Agent Memory is designed to manage memories comprehensively across all connected agents, allowing you to search, recall, and aggregate information seamlessly across agent boundaries.

Agent Memory

Name: Agent Memory
Author: mdfifty50-boop

0•

Provides persistent, cross-session memory for AI agents to store, recall, search, and summarize information.

Agent Memory is an MCP server designed to empower AI agents with robust, persistent, and cross-session memory capabilities. It enables agents to store, retrieve, search, and summarize various types of information across different interactions and agent boundaries, ensuring long-term knowledge retention and continuity. The server includes a suite of tools for remembering facts, preferences, interactions, and learned insights, alongside advanced functionalities to aggregate user profiles, summarize past sessions, and perform comprehensive searches across all agents. By classifying memories into distinct types like `fact`, `preference`, `interaction`, `learning`, and `context`, Agent Memory facilitates structured and highly effective knowledge management crucial for developing sophisticated and context-aware AI applications.

主な機能

01Store and classify memories with optional time-to-live (TTL).

02Aggregate knowledge about a user or entity from all connected agents.

03Delete memories using exact keys, wildcard prefixes, or clear all.

04Retrieve memories by keyword search, sorted by relevance and recency.

05Search and access memories comprehensively across all managed agents.

060 GitHub stars

ユースケース

01Developing personalized AI assistants capable of remembering user preferences and past interactions.

02Creating AI systems that maintain a long-term knowledge base for complex decision-making and problem-solving.

03Building intelligent AI agents that retain context and learn across multiple sessions.