m_flow
A bio-inspired cognitive memory engine that performs reasoning and associative retrieval through graph structures.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 4.4k
- Source
- mcp-github
- Repository
- github.com/FlowElement-ai/m_flow
Overview
M-flow is a bio-inspired cognitive memory engine that adopts a novel Graph RAG paradigm. Instead of simple similarity matching, it performs reasoning and associative retrieval via graph structures. M-flow organizes knowledge into a four-layer conical graph, ranging from abstract summaries to atomic facts. During querying, the system conducts broad searches across multiple granularities, then propagates evidence paths through the graph, ultimately scoring each knowledge unit. This mechanism enables M-flow to deliver more accurate and relevant results when handling complex queries. Ideal for AI applications requiring advanced retrieval and association capabilities.
Capabilities
- ▪Multi-granularity vector search
- ▪Graph-based evidence propagation
- ▪Scoring based on strongest evidence chain
- ▪Knowledge organized in a four-layer conical graph
Use cases
Setup
pip install m_flow
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How is M-flow different from traditional RAG systems?
M-flow performs reasoning and associative retrieval through graph structures, rather than relying solely on similarity matching.
What programming languages does M-flow support?
M-flow primarily supports Python 3.10–3.13.
Related skills
OpenMetadata
OpenMetadata is an open data context layer that provides trustworthy data context and business semantics for AI.
XHS-Downloader
A link extraction and content collection tool for Xiaohongshu, supporting multiple download and information extraction features.
radiology-skills
A full-stack skill package for medical imaging research, covering the entire process from topic selection to grant application.
dbx
Lightweight cross-platform database management tool supporting over 70 databases.
nihaixia
A Chinese medicine AI capability developed based on Dr. Ni Haixia's teaching materials, covering Six-Channel Differentiation and classic formula selection.
powerbi-modeling-mcp
Power BI Modeling MCP Server provides AI agents with Power BI semantic modeling capabilities.