m_flow MCP Server
FlowElement-xinliuyuansu/m_flow
[](https://agentrank-ai.com/tool/FlowElement-xinliuyuansu--m_flow/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
FlowElement-xinliuyuansu/m_flow is a Python tool licensed under Apache-2.0. A bio-inspired cognitive memory engine — a new paradigm for Graph RAG. Topics: agent-memory, agentic-ai, ai-reasoning, episodic-memory, graph-database, knowledge-graph, llm, long-term-memory, mcp, memory-engine, python, rag, semantic-memory, vector-search.
Ranked #10721 out of 24846 indexed tools.
Has 4,515 GitHub stars.
Ecosystem
Score Breakdown
4,515 stars → well-known project
Last commit 2mo ago → moderate activity
11/24 issues closed → many open issues
8 contributors → small team
2 dependents → few downstream users
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Badge all embed codes →
[](https://agentrank-ai.com/tool/FlowElement-xinliuyuansu--m_flow/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/FlowElement-xinliuyuansu--m_flow/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/FlowElement-xinliuyuansu--m_flow" alt="AgentRank"></a> Matched Queries
From the README
<div align="center"> # M-flow **RAG matches chunks. GraphRAG structures context. M-flow scores evidence paths.** Retrieval through reasoning and association — M-flow operates like a cognitive memory system. [m-flow.ai](https://m-flow.ai) · [flowelement.ai](https://flowelement.ai) · [Quick Start](#quick-start) · [Architecture](docs/RETRIEVAL_ARCHITECTURE.md) · [Examples](examples/) · [OpenClaw Skill](https://clawhub.ai/flowelement-alexunbridled/mflow-memory) · [Contact](mailto:[email protected]) </div> --- ## What is M-flow? The real shift is not whether a system builds a graph, but what the graph is allowed to do at retrieval time. ### Graph topology encodes relevance. In most RAG systems, retrieval is still dominated by similarity: the query is embedded, textual units are ranked by vector distance, and structure—if present—mainly helps organize, summarize, or expand context. Many GraphRAG systems add entities, relations, and community structure, but the graph often reRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.