Is the metronix-memory MCP server actively maintained?

The metronix-memory MCP server was last committed 1mo ago and has 16 contributors. Issue health: 46% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

metronix-memory MCP Server

Name: mtrnix/metronix-memory
Rating: 4.0 (1 reviews)
Author: mtrnix

mtrnix/metronix-memory

Score: 75.7 Rank #2960 Search & RAG

[![AgentRank](https://agentrank-ai.com/api/v1/badge/mtrnix--metronix-memory)](https://agentrank-ai.com/tool/mtrnix--metronix-memory/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of mtrnix/metronix-memory? Claim this listing →

Self-hosted AI agent memory — MCP memory server with durable recall for agents

Add AgentRank to Claude Code Discover and compare tools like mtrnix/metronix-memory — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

mtrnix/metronix-memory is a Python tool licensed under Apache-2.0. Self-hosted AI agent memory — MCP memory server with durable recall for agents Topics: agent-memory, ai-agents, mcp, rag, self-hosted, llm, neo4j, qdrant, hybrid-search, knowledge-graph, long-term-memory, mcp-server, memory.

Ranked #2960 out of 24846 indexed tools.

Has 16 contributors.

Ecosystem

Python Apache-2.0

agent-memoryai-agentsmcpragself-hostedllmneo4jqdranthybrid-searchknowledge-graphlong-term-memorymcp-servermemory

Score Breakdown

Stars 15% 107

107 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → recently updated

Issue Health 25% 46%

68/148 issues closed → many open issues

Contributors 10% 16

16 contributors → active community

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 15

Description Good

License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Issue Health high impact

You have 80 open vs 68 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/mtrnix--metronix-memory)](https://agentrank-ai.com/tool/mtrnix--metronix-memory/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/mtrnix--metronix-memory/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/mtrnix--metronix-memory" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="mtrnix/metronix-memory"></script>

Details

Stars: 107
Forks: 15
Open Issues: 80
Closed Issues: 68
Contributors: 16
Dependents: —
Language: Python
License: Apache-2.0
Last Commit: 1mo ago

Matched Queries

topic:mcptopic:mcp-server

From the README

# Metronix Memory

<p align="center">
  
</p>

**Self-hosted AI agent memory — an MCP memory server with durable recall, hybrid RAG, and Neo4j graph context.**

Metronix is self-hosted memory infrastructure for AI agents: ingest files and SaaS knowledge, retrieve with dense + sparse + graph context, store durable facts and preferences per agent, and keep long-lived knowledge fresh as projects change.

<p align="center">
  
  
  
  
</p>

## What you get

- **Durable memory for every agent** — facts, preferences, and pinned context with workspace and agent scoping
- **Hybrid knowledge retrieval** — dense + SPLADE sparse + Neo4j graph context, with source citations
- **Self-hosted control** — Docker Compose stack, bundled local models, optional external answer generation
- **One integration surface** — MCP memory server today; REST and OpenAI-compatible APIs when you need them

## Quick start

Requirements: Docker with **≥6 GB RAM** (8 GB recommended) and ~15 GB free disk.

```bash
# One

Read full README on GitHub →