LightRAG
https://github.com/HKUDS/LightRAG
Entity-relationship graph + broader-theme retrieval. Incremental update support. Integrates with RAG-Anything for multimodal docs.
Active · Verified 2026-10-23 · fresh as of 2026-10-23 · 29 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Dual-level graph retrieval repo fix
- Tier
- T3
- Section
- Retrieval-as-memory hybrids
- Latest release
- v1.5.7 (2026-09-02) registry fix
- Pricing
- searched not found fix
- Funding
- not applicable — not commercial fix
- Freshness
- 2026-10-23 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- SDK languages
- python, rest repo fix
- Developer activity
- OpenRank 16 (12-mo avg 14.19) · 91 participants — 2026-09 third-party fix
Memory taxonomy
- storage
- graph
- retrieval
- graph-traversal
- persistence
- long-term
- update
- read-only
- unit
- chunk
- 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
Simpler than GraphRAG with reasonable quality — good middle-ground for shops avoiding heavy GraphRAG indexing.
Cons
Less rich retrieval than GraphRAG; quality on community-summary queries is weaker.
Claims & capabilities
EMNLP 2025 Findings. Recent updates added OpenSearch unified storage backend and reranker support.
Technical surface
- API surface
- not applicable — research paper
- Backend storage
- not applicable — research paper
- Deployment
- searched not found
- Embedding model
- not applicable — research paper
- Multi-tenancy
- not applicable — research paper
- MCP
- not applicable — research paper, no deployed product
- A2A
- not applicable — research paper, no deployed product
- OpenTelemetry
- not applicable — research paper, no deployed product
Alternatives to LightRAG → 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.
- GraphRAG (Microsoft) T1
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.
- 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.
Sources (28 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 Dual-level graph retrieval repo
- What it does & what's distinct Entity-relationship graph + broader-theme retrieval. Incremental update support. Integra… repo
- Claims / benefits EMNLP 2025 Findings. Recent updates added OpenSearch unified storage backend and reranke… repo
- Created 2024-10 repo
- Latest release v1.5.7 (2026-09-02) registry
- License MIT repo
- GitHub HKUDS/LightRAG — ~39.3k stars, last commit 2026-09+ repo
- Founders / pedigree HKUDS (University of Hong Kong Data Intelligence Lab) + Beijing University of Posts and … paper
- Reproducibility Independently reproduced paper
- Code/weights release Code public + weights closed repo
- Versioning none repo
- Schema evolution schema with migration repo
- Validated verticals research, RAG developers (horizontal); some have production deployments repo
- Anti-fit most are research papers; production fitness varies by maintainer repo
- Optimised for retrieval quality / accuracy on long-context QA repo
- Adjacent infrastructure BYO LLM + vector store; OSS reference implementations exist repo
- Pros Simpler than GraphRAG with reasonable quality — good middle-ground for shops avoiding he… repo
- Cons Less rich retrieval than GraphRAG; quality on community-summary queries is weaker. repo
- Project & sources GitHub HKUDS/LightRAG repo
- commit-trajectory [{"ym":"2026-01","cum":6257},{"ym":"2026-02","cum":6363},{"ym":"2026-03","cum":6829},{"y… repo
- citation-trajectory [] paper
- download-trajectory [{"ym":"2025-11","monthly":26062,"cum":26062},{"ym":"2025-12","monthly":58162,"cum":8422… 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":291.04,"as_of":"2026-09","openrank_12mo":14.19,"openrank_current":16,"partic… third-party
- sdk-languages python,rest 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
References (1)
- GraphRAG (Microsoft) cites — S2 isInfluential citation
Referenced by (1)
- Phidata (now Agno) integrates with — Agno ships a lightrag vector DB integration module (agno.vectordb.lightrag). (verified 2026-10-29)