Last updated
March 16, 2026
MCP profile
Github DiaaAj A Mem Mcp
Self-evolving memory system for AI agents
Developer ToolsPackagePythonOpen SourceExternal
Visibility
Public
ByRegistry
About This MCP Server
1. Add a memory → A-MEM extracts keywords, context, and tags via LLM 2. Find neighbors → Searches for semantically similar existing memories 3. Evolve → Decides whether to link, strengthen connections, or update related memories 4. Store → Persists to ChromaDB with full metadata and relationships
The result: a knowledge graph that grows smarter over time, not just bigger.
Capabilities
Memories aren't static. When you add new knowledge, A-MEM automatically finds related memories and strengthens connections, updates context, and evolves tags.Combines vector similarity with graph traversal. Find memories by meaning, then explore their connections.Start with breadth-first search to capture relevant memories via lightweight metadata (id, context, keywords, tags). Then drill depth-first into specific memories with read_memory_note for full content. This minimizes token usage while maximizing recall.
Tools & Endpoints1
Why Use Github DiaaAj A Mem Mcp?
- Memories aren't static. When you add new knowledge, A-MEM automatically finds related memories and strengthens connections, updates context, and evolves tags.
- Combines vector similarity with graph traversal. Find memories by meaning, then explore their connections.
- Start with breadth-first search to capture relevant memories via lightweight metadata (id, context, keywords, tags). Then drill depth-first into specific memories with read_memory_note for full content. This minimizes token usage while maximizing recall.
Specifications
Status
live
Industry
Developer Tools
Category
General
Server type
Package
Language
Python
License
Open Source
Verified
Yes
Hosting
Hosting Options
- Package
API
Integrate this server into your application. Choose a connection method below.
1
Install
Install command
Python
pip install a-mem2
Configure
Configuration
json
{
"mcpServers": {
"a-mem": {
"command": "a-mem-mcp",
"env": {
"LLM_BACKEND": "openai",
"LLM_MODEL": "gpt-4o-mini",
"OPENAI_API_KEY": "sk-..."
}
}
}
}Performance
Usage
Quick Reference
- Name
- Github DiaaAj A Mem Mcp
- Function
- Self-evolving memory system for AI agents
- Available Tools
- A-MEM exposes 8 tools to your coding agent:
- Transport
- Package
- Language
- Python
- Install
- pip install a-mem
- Source
- External (Registry)
- License
- Open Source
Get started
Ready to integrate this MCP server?
Book a demo to see how this server fits your workflow, or explore the full catalog.