GraphRAG (Microsoft)
https://www.microsoft.com/en-us/research/project/graphrag/
Modular graph-based RAG. Leiden community detection over knowledge graph; community summaries at multiple levels. DRIFT Search hybrid (Oct 2024). The GraphRAG repo is now largely in maintenance mode: no new features or PRs, only bug fixes and dependency/CVE updates.
Maintenance · Verified 2026-10-29 · fresh as of 2026-10-29 · 55 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Community summary + Leiden detection vendor fix
- Tier
- T1
- Section
- Retrieval-as-memory hybrids
- Latest release
- v3.3.0 (2026-10-08) registry fix
- Pricing
- searched not found fix
- Funding
- not applicable — not commercial fix
- Freshness
- 2026-10-29 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- Developer activity
- OpenRank 1.66 (12-mo avg 8.79) · 20 participants — 2026-09 third-party fix
Memory taxonomy
- storage
- graph
- retrieval
- graph-traversal
- persistence
- long-term
- update
- extraction
- unit
- document
- governance
- inspectable
- conflict
- n/a
When to use
Optimised for: retrieval quality / accuracy on long-context QA
Anti-fit: most are research papers; production fitness varies by maintainer
Pros & cons
Pros
Most cited RAG-as-memory pattern of 2024 — graph extraction + community summaries gives it macro-level semantic recall most flat-RAG misses.
Cons
Indexing cost is high (extraction LLM passes per chunk); operational complexity exceeds vanilla RAG significantly.
Claims & capabilities
v1.0 GA; PyPI distributed. Indexing cost reported at $50–200 per 500 pages.
Technical surface
- API surface
- Python SDK / CLI
- Backend storage
- Parquet files / pluggable
- Deployment
- searched not found
- Embedding model
- BYO
- Multi-tenancy
- not applicable — library
- MCP
- not documented publicly
- A2A
- not supported
- OpenTelemetry
- not documented publicly
Alternatives to GraphRAG (Microsoft) → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other retrieval-as-memory hybrids in the catalog, ranked by inbound references.
- RETRO T3
DeepMind. Retrieval-Enhanced Transformer with chunked cross-attention over a 2T-token retrieval database. Frozen BERT retriever + differentiable encoder.
- Atlas T3
Meta AI. Jointly fine-tunes retriever + LM for few-shot tasks. The facebookresearch/atlas repo is no longer maintained; the code is provided as is.
- RAPTOR T3
Stanford recursive-summarisation tree over the corpus — clusters and summarises documents into a hierarchical index; retrieves at multiple levels. ICLR 2024.
- Self-RAG T4
Trains an LLM end-to-end to emit reflection tokens that decide whether to retrieve, assess passage relevance, and critique output quality — all within a single model.
- HippoRAG / HippoRAG2 T3
Hippocampus-inspired RAG. LLMs + knowledge graphs + Personalized PageRank to mimic neocortex/hippocampus roles. NeurIPS 2024.
- MemoRAG T4
RAG variant with a long-context global memory model that drafts answer clues used to guide passage retrieval — improves recall in noisy multi-hop QA.
Sources (54 cited facts, 1 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Community summary + Leiden detection vendor
- What it does & what's distinct Modular graph-based RAG. Leiden community detection over knowledge graph; community summ… repo
- Claims / benefits v1.0 GA; PyPI distributed. Indexing cost reported at $50–200 per 500 pages. vendor
- Created 2024-03 vendor
- Latest release v3.3.0 (2026-10-08) registry
- License MIT repo
- GitHub microsoft/graphrag — ~35.1k stars, last commit n/a (PyPI release 2026-10) repo
- Mindshare 1 inbound vendor
- Founders / pedigree Microsoft Research; lead authors Darren Edge (Sr Director), Ha Trinh (Sr Data Scientist)… paper
- API surface Python SDK / CLI vendor
- Backend storage Parquet files / pluggable vendor
- Embedding model BYO vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling LLM resolves and overwrites vendor
- A2A support not supported vendor
- Webhooks / events no vendor
- Import / export Parquet, CSV, GraphML repo
- Validated verticals research, RAG developers (horizontal); some have production deployments vendor
- Anti-fit most are research papers; production fitness varies by maintainer vendor
- Optimised for retrieval quality / accuracy on long-context QA vendor
- Adjacent infrastructure BYO LLM + vector store; OSS reference implementations exist vendor
- Pros Most cited RAG-as-memory pattern of 2024 — graph extraction + community summaries gives … vendor
- Cons Indexing cost is high (extraction LLM passes per chunk); operational complexity exceeds … vendor
- Project & sources GitHub microsoft/graphrag docs site project page Azure accelerator vendor
- obs-langsmith no vendor
- obs-datadog no vendor
- obs-helicone no vendor
- obs-weave no vendor
- obs-langfuse no vendor
- obs-arize no vendor
- obs-custom Azure Application Insights when deployed via Azure AI Search vendor
- cost-token-budget no vendor
- cost-prompt-caching no vendor
- cost-semantic-caching no vendor
- cost-batching no vendor
- cost-model-routing yes vendor
- cost-streaming-only no vendor
- cost-observability-cost-attribution no vendor
- eval-langsmith-evals no vendor
- eval-braintrust no vendor
- eval-weights-and-biases-agent no vendor
- eval-helicone-evals no vendor
- eval-custom-test-harness yes vendor
- eval-human-loop no vendor
- eval-production-traffic-replay no vendor
- commit-trajectory [{"ym":"2024-07","cum":77},{"ym":"2024-08","cum":148},{"ym":"2024-09","cum":195},{"ym":"… repo
- download-trajectory [{"ym":"2025-11","monthly":27345,"cum":27345},{"ym":"2025-12","monthly":68349,"cum":9569… registry
- architecture-deployment-locus local repo
- licensing-bucket open-source repo
- positioning-platform-vs-product platform repo
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":42.02,"as_of":"2026-09","openrank_12mo":8.79,"openrank_current":1.66,"partic… third-party
- sdk-languages python repo
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
Related systems
Referenced by (14)
- AutoGen / AG2 integrates with — Microsoft AutoGen autogen-ext ships a GraphRAG search tool (autogen_ext.tools.graphrag). (verified 2026-10-29)
- CAM cites — S2 isInfluential citation
- ComoRAG cites — S2 isInfluential citation
- Generative Semantic Workspace (GSW) cites — S2 isInfluential citation
- LazyGraphRAG extends — Being integrated into the main GraphRAG library.
- LightRAG cites — S2 isInfluential citation
- LightRAG cites — S2 isInfluential citation
- MemTree cites — S2 isInfluential citation
- PathRAG cites — S2 isInfluential citation
- PathRAG cites — S2 isInfluential citation
- Qdrant integrates with — Qdrant's documentation has a GraphRAG (Microsoft) integration page. (verified 2026-10-29)
- RGMem cites — S2 isInfluential citation
- RouteRAG cites — S2 isInfluential citation
- StructRAG cites — S2 isInfluential citation