# FlowElement-xinliuyuansu/m_flow

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

Repository: https://github.com/FlowElement-xinliuyuansu/m_flow
Canonical: https://ross.abutalabs.com/products/m_flow
Homepage: https://flowelement.ai
Language: Python
License: Apache-2.0
License Family: permissive
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
Last push: 2026-08-03T12:06:18+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 47, longevity 11
- inputs: {"age_days": 155, "days_push": 30, "days_rel": 143, "gap_med": null, "n_releases_24m": 1}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4500, forks 257 (observed 2026-08-28T04:08:51.465866+00:00)

## What it is
M-flow is a Python bio-inspired cognitive memory engine that treats graph topology as the retrieval scoring engine rather than a supportive structure. It stores knowledge in a four-layer cone graph (Episode → Facet → FacetPoint → Entity) and scores relevance by propagating evidence along typed, semantically weighted edges from vector-search entry points.

## Use cases
- build long-term memory for ai agents
- implement graph rag with reasoning-based retrieval
- give llm chatbots episodic and semantic memory
- retrieve answers by evidence paths instead of vector similarity
- add multi-granularity memory recall to rag pipelines
- expose agent memory via mcp server

## When to choose
- you need relevance based on reasoning chains rather than embedding similarity
- you're building agentic ai that must remember and associate events over time
- you want a graph-native alternative to chunk-based GraphRAG systems
- you need MCP-compatible memory for LLM tooling

## When to avoid
- you need a simple, battle-tested vector-only RAG stack
- your corpus is small enough that plain similarity search suffices
- you require a managed database product rather than a Python library
- you're outside the Python 3.10–3.13 ecosystem

## Facets
- artifact type: library
- maturity: active
- function: rag, vector-database, search-engine, agent-framework, mcp, llm-inference
- domain: artificial-intelligence, large-language-models, databases
- platform: python, cross-platform
- tags: graph-rag, agent-memory, knowledge-graph, episodic-memory, semantic-memory, memory-engine, cognitive-architecture, evidence-path-scoring, retrieval-augmented-generation, ai-agents, natural-language-processing

## Member repositories
- FlowElement-xinliuyuansu/m_flow (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:51.465866+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:20:25.247717+00:00, confidence not recorded.
  - readme: https://github.com/FlowElement-xinliuyuansu/m_flow (fetched 2026-08-28T04:08:51.465866+00:00, sha 6f72e2a36e36)
  - homepage: https://flowelement.ai (fetched 2026-08-29T09:06:29.180875+00:00, sha 7ef6dcf343c7)
- Data as of 2026-08-30T08:39:29.467469+00:00.