English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

GraphRAG Open-Source Projects Compared: Microsoft GraphRAG, LightRAG, KAG, HippoRAG and More

Forum topic · ✨步子哥 · 2026-06-30

Summary

A deep comparison of mainstream open-source GraphRAG frameworks explains why traditional vector RAG fails at cross-document reasoning and global summarization, then breaks down nine projects: Microsoft GraphRAG (Leiden community detection, Local/Global/DRIFT search, very expensive indexing), LightRAG from HKUDS (dual-level node/edge retrieval, cheap incremental updates), nano-graphrag (800-line teaching implementation), KAG from Ant Group (schema-constrained, auditable logical reasoning), HippoRAG (Personalized PageRank multi-hop retrieval), PathRAG (path pruning to cut noise and tokens), Yuxi-Know (a full GUI platform built on LightRAG), plus graph databases NebulaGraph and Neo4j as infrastructure. The article provides feature/cost/engineering comparison matrices, a five-step selection decision tree, a pragmatic hybrid architecture (LightRAG for routine queries, GraphRAG for deep analysis, shared graph storage), five common pitfalls such as underestimating indexing costs and skipping Chinese prompt tuning, and trends including LazyGraphRAG's claimed 0.1% indexing cost, domain-specific reasoning, multimodal ingestion, and Agentic GraphRAG fusion.

Why traditional RAG falls short

Conventional RAG splits documents into fragments and retrieves by vector similarity, so it excels at finding "the most similar chunk" but fails at cross-document reasoning, multi-hop questions, and global summarization. GraphRAG rebuilds scattered fragments into a knowledge network: entities as nodes, relations as edges, communities as clusters — retrieval walks the graph instead of only matching text.

Key points

  • Microsoft GraphRAG (31k+ stars): LLM entity/relation extraction → Leiden hierarchical community detection → community summaries. Offers Local, Global, and DRIFT search. Indexing cost is extremely high (reportedly ~10x LightRAG on the same dataset); Global Search uses Map-Reduce with many LLM calls. Incremental indexing (0.5.0) still recomputes communities. Best for high-value, low-frequency global analysis (financial research, literature reviews).
  • LightRAG (29k+ stars, HKU HKUDS): dual-level retrieval — vector search over nodes (Local/concrete keywords) and edges/relations (Global/abstract keywords), plus Hybrid and Mix modes. Incremental updates merge as unions without recomputing communities. Reported benchmarks vs GraphRAG: ~99.98% retrieval efficiency gain, ~12x lower latency, >99% fewer API calls, >12x fewer tokens (only two LLM calls per query). Multimodal support via RAG-Anything. Weaker at deep logical reasoning.
  • nano-graphrag (2k+): ~800-line GraphRAG core for learning/research; recomputes communities on every insert — not production-ready.
  • KAG (8k+, Ant Group + OpenKG): built on OpenSPG with DIKW-inspired LLMFriSPG knowledge representation; mutual indexing of knowledge and text chunks for auditable reasoning, a logical-form planner decomposing questions into operator chains, and semantic knowledge alignment. Native Chinese optimization. Ideal for healthcare, legal, finance.
  • HippoRAG (3k+, OSU NLP): LLM as "neocortex," graph + Personalized PageRank as "hippocampus"; single-step PPR diffusion enables multi-hop reasoning cheaply. Academic-oriented, low production adoption.
  • PathRAG (1k+, BUPT GAMMA): a LightRAG-derived denoising patch — streaming path pruning via DFS three-hop neighbors and resource-allocation-based branch pruning, plus path-guided prompts describing graph structure in text. Lower noise and token use.
  • Yuxi-Know (4k+): full GUI platform (LangChain v1 + FastAPI + Vue) wrapping LightRAG; MinerU PDF parsing, permissions, dashboards, ScrapeGraphAI integration. No-code GraphRAG.
  • NebulaGraph / Neo4j RAG: distributed graph database infrastructure (trillion-scale edges, 99.999% availability) and Cypher-based graph retrieval for building your own GraphRAG stack.
  • Selection decision tree

    1. Data scale: TB+/trillion edges → NebulaGraph + custom layer; millions to hundreds of thousands of docs → any framework below. 2. Query type: global summarization → GraphRAG; auditable multi-hop → KAG (or HippoRAG for low cost); entity-specific lookups → LightRAG; balanced → LightRAG Hybrid or PathRAG. 3. Update frequency: static data → GraphRAG; daily/real-time updates → LightRAG/PathRAG. 4. Budget/team: large budget + expert team → GraphRAG or KAG; small team → LightRAG; no-code → Yuxi-Know; learning → nano-graphrag. 5. Domain needs: auditable chains → KAG; financial global analysis → GraphRAG; real-time Q&A → LightRAG; multi-hop research → HippoRAG; noise-sensitive → PathRAG.

    A pragmatic hybrid architecture

    1. Route ~90% of daily queries through LightRAG (speed + cost control). 2. Escalate low-confidence or explicitly global-analysis queries to GraphRAG. 3. Share the underlying knowledge graph storage to avoid duplicate indexing. Trade-off: running two systems adds maintenance overhead.

    Common pitfalls

  • GraphRAG does not replace vector RAG — for precise text retrieval, plain vector RAG is faster and more accurate; hybrid retrieval often wins.
  • Indexing costs are easy to underestimate — pilot on a small dataset before full runs.
  • Default prompts are English-tuned; Chinese entity extraction quality drops without prompt adjustment (KAG is the exception with native Chinese optimization).
  • nano-graphrag is not production-grade.
  • Watch LazyGraphRAG: Microsoft claims ~0.1% of original indexing cost via cluster-then-summarize-on-demand; not yet fully merged.
  • Trends

  • Cost collapse: GraphRAG → LightRAG (1/12 cost) → LazyGraphRAG (three orders of magnitude lower claimed), moving GraphRAG from enterprise-only to mainstream.
  • Domain specialization: schema constraints + logical reasoning (KAG) deliver more ToB value than general-purpose frameworks.
  • Multimodal fusion: RAG-Anything, MinerU — "any format into the graph."
  • Agentic GraphRAG: agents deciding when to use graph vs vector retrieval (e.g., LangGraph + LightRAG).

Project links

| Project | GitHub | Paper | |---|---|---| | Microsoft GraphRAG | github.com/microsoft/graphrag | arxiv.org/abs/2404.16130 | | LightRAG | github.com/HKUDS/LightRAG | arxiv.org/abs/2410.05779 | | nano-graphrag | github.com/gusye1234/nano-graphrag | — | | KAG | github.com/OpenSPG/KAG | arxiv.org/abs/2409.13731 | | HippoRAG | github.com/OSU-NLP-Group/HippoRAG | arxiv.org/abs/2405.14831 | | PathRAG | github.com/BUPT-GAMMA/PathRAG | — | | Yuxi-Know | github.com/xerrors/Yuxi-Know | — | | NebulaGraph | github.com/vesoft-inc/nebula | — | | Neo4j RAG | github.com/neo4j/neo4j-rag-framework | — |

> Data as of June 2026; star counts and project status change continuously — check GitHub for current numbers.

Tags

#graphrag#rag#knowledge-graph#lightrag#microsoft-graphrag#kag#hipporag#llm

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208327