MCPgee
MCPgee
MCPgeeMCPgee

Agentic Memory

v1.0.0•Knowledge & Memory•stable

Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.

agent-memoryagenticai-agentsbelief-revisionbinary-format
Share:
15
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Agentic Memory?

Agentic Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to persistent cognitive graph memory for ai agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. rust core + python sdk + mcp server.

Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Persistent cognitive graph memory for AI agents — facts, dec

Use Cases

Persistent fact and decision storage
Sub-millisecond semantic queries
Belief revision and reasoning chains
agentralabs

Maintainer

LicenseMIT
Languagerust
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx agentic-memory

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Agentic Memory

Agentic Memory is a persistent cognitive graph memory system for AI agents, built on a Rust core with a Python SDK and MCP server layer. It stores facts, decisions, reasoning chains, and corrections in a single portable .amem binary file — using a typed 6-node, 7-edge graph with BLAKE3 integrity chains. It exposes 13 MCP tools covering capture, retrieval, search, and verification, and delivers 16 distinct query types including BM25 full-text search (1.58ms at 100K nodes), hybrid vector+text search, PageRank centrality, belief revision, and analogical pattern matching.

Prerequisites

  • Claude Desktop, Cursor, Windsurf, or another MCP-compatible client
  • One of: Rust/Cargo, Python 3.9+/pip, or Node.js/npm depending on install method
  • curl for the one-liner installer (recommended)
1

Install Agentic Memory

The fastest method is the universal one-liner installer. Alternatively install via Cargo, pip, or npm.

# Recommended: universal installer
curl -fsSL https://agentralabs.tech/install/memory | bash

# Rust / Cargo
cargo install agentic-memory-cli agentic-memory-mcp

# Python / pip
pip install agentic-brain

# Node.js / npm (WASM)
npm install @agenticamem/memory
2

Configure environment variables

Set optional environment variables to control storage, auto-capture behavior, PII redaction, and authentication.

# Required for server mode
export AGENTIC_TOKEN=your-bearer-auth-token

# Optional tuning
export AMEM_AUTONOMIC_PROFILE=desktop          # desktop | cloud | aggressive
export AMEM_AUTO_CAPTURE_MODE=safe             # safe | full | off
export AMEM_AUTO_CAPTURE_REDACT=true           # strip PII before storage
export AMEM_STORAGE_BUDGET_BYTES=524288000     # 500 MB cap
export AMEM_HEALTH_LEDGER_DIR=/path/to/ledger  # operational snapshots
3

Configure Claude Desktop to use the MCP server

Add the Agentic Memory MCP server to your Claude Desktop configuration file.

{
  "mcpServers": {
    "agentic-memory": {
      "command": "agentic-memory-mcp",
      "args": ["--memory-file", "/Users/yourname/.agentic/agent.amem"],
      "env": {
        "AGENTIC_TOKEN": "your-bearer-auth-token",
        "AMEM_AUTO_CAPTURE_MODE": "safe"
      }
    }
  }
}
4

Use the Python SDK for programmatic access

Integrate Agentic Memory directly into Python agent code using the agentic_memory package.

from agentic_memory import Brain, MemoryAgent
from agentic_memory.integrations import AnthropicProvider

brain = Brain("my_agent.amem")
agent = MemoryAgent(brain=brain, provider=AnthropicProvider())

# Session 1: learn something
agent.chat("I'm building a Rust compiler", session=1)

# Session 2: recall it
response = agent.chat("What am I working on?", session=2)
print(response)  # → 'You are building a Rust compiler'
5

Verify memory integrity

The memory file uses BLAKE3 integrity chains. You can verify the file is uncorrupted using the CLI.

agentic-memory-cli verify --memory-file /Users/yourname/.agentic/agent.amem
agentic-memory-cli stats  --memory-file /Users/yourname/.agentic/agent.amem

Agentic Memory Examples

Client configuration

Full Claude Desktop configuration for Agentic Memory using the installed MCP server binary.

{
  "mcpServers": {
    "agentic-memory": {
      "command": "agentic-memory-mcp",
      "args": ["--memory-file", "/Users/yourname/.agentic/agent.amem"],
      "env": {
        "AGENTIC_TOKEN": "your-bearer-token",
        "AMEM_AUTO_CAPTURE_MODE": "safe",
        "AMEM_AUTO_CAPTURE_REDACT": "true"
      }
    }
  }
}

Prompts to try

Example prompts for using Agentic Memory's persistent storage and retrieval through Claude.

- "Remember that the database password is stored in the .env file and must never be committed to git"
- "What decisions have we made about the API authentication approach in previous sessions?"
- "Search my memory for anything related to the payment system refactor"
- "What was my reasoning when I chose PostgreSQL over MongoDB for this project?"
- "Store this decision: we are switching to event-driven architecture for the order service"

Troubleshooting Agentic Memory

agentic-memory-mcp command not found after installation

Ensure the install directory is in your PATH. For Cargo installs, add ~/.cargo/bin to PATH. For the curl installer, follow the post-install instructions printed to the terminal. Run 'source ~/.bashrc' or restart your shell.

Memory file grows unexpectedly large

Set AMEM_STORAGE_BUDGET_BYTES to enforce a maximum file size (e.g., 524288000 for 500 MB). The system will perform automatic rollup when the budget is reached. Also consider setting AMEM_AUTO_CAPTURE_MODE=safe to limit what gets stored automatically.

Authentication errors when connecting to the MCP server

Server mode requires the AGENTIC_TOKEN environment variable to be set in both the server process and any client connecting to it. Ensure the token in your claude_desktop_config.json env block matches the token the server expects.

Frequently Asked Questions about Agentic Memory

What is Agentic Memory?

Agentic Memory is a Model Context Protocol (MCP) server that persistent cognitive graph memory for ai agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. rust core + python sdk + mcp server. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Agentic Memory?

Follow the installation instructions on the Agentic Memory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Agentic Memory?

Agentic Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Agentic Memory free to use?

Yes, Agentic Memory is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Agentic Memory Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Agentic Memory? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "agentic-memory": { "command": "npx", "args": ["-y", "agentic-memory"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Agentic Memory?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides