# 1517005260/graph-rag-agent

拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construction and search. Combine DeepSearch for private RAG reasoning. Create a custom evaluation framework for GraphRAG.

Repository: https://github.com/1517005260/graph-rag-agent
Canonical: https://ross.abutalabs.com/products/graph-rag-agent
Homepage: https://deepwiki.com/1517005260/graph-rag-agent
Language: Python
License: MIT
License Family: permissive
Topics: deepresearch, deepsearch, evaluation, graphrag, lightrag, reasoning, kg, agentic-rag, chain-of-exploration, graphsearch, think-on-graph
Last push: 2025-11-05T08:15:51+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 50, release rhythm 35, longevity 40
- inputs: {"age_days": 567, "days_push": 301, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2326, forks 322 (observed 2026-08-28T04:06:37.441354+00:00)

## What it is
A Python framework that integrates GraphRAG, LightRAG, and Neo4j-based graph building to construct knowledge graphs and perform explainable, reasoning-driven question answering. It combines multi-agent Plan-Execute-Report orchestration with DeepSearch techniques and includes a custom evaluation framework for GraphRAG pipelines.

## Use cases
- build a knowledge graph from private documents and query it
- implement graph-based RAG question answering with reasoning traces
- run deep research agents over a private document corpus
- evaluate and compare GraphRAG retrieval quality
- visualize and explore a knowledge graph with a chat interface
- orchestrate multi-agent plan-execute-report research workflows

## When to choose
- you need knowledge-graph-enhanced RAG over private domain data
- you want explainable, agentic retrieval with multi-hop graph exploration
- you need a built-in evaluation framework for GraphRAG pipelines
- you want a self-hosted full stack with API, frontend, and Neo4j backend

## When to avoid
- you only need simple vector-based RAG without graph structure
- you want a lightweight plug-and-play library with minimal setup
- you cannot operate Neo4j and LLM API infrastructure
- you need production-hardened enterprise support

## Facets
- artifact type: framework
- maturity: active
- function: rag, agent-framework, search-engine, llm-inference, chatbot, data-visualization, benchmarking, caching
- domain: large-language-models, databases, developer-tools
- platform: python, self-hosted, cross-platform
- tags: graphrag, lightrag, knowledge-graph, neo4j, deepsearch, multi-agent, agentic-rag, chain-of-exploration, think-on-graph, community-detection, evaluation-framework, fastapi, retrieval-augmented-generation, ai-agents, natural-language-processing, search, docker, web-server

## Member repositories
- 1517005260/graph-rag-agent (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.441354+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 2026-08-30T02:38:14.930030+00:00, confidence not recorded.
  - readme: https://github.com/1517005260/graph-rag-agent (fetched 2026-08-28T04:06:37.441354+00:00, sha e76dec01c809)
  - homepage: https://deepwiki.com/1517005260/graph-rag-agent (fetched 2026-08-29T10:18:41.509872+00:00, sha 4c581a0c8b0e)
- Data as of 2026-08-30T08:39:29.467469+00:00.