HippoRAG / HippoRAG2
https://github.com/OSU-NLP-Group/HippoRAG
Hippocampus-inspired RAG. LLMs + knowledge graphs + Personalized PageRank to mimic neocortex/hippocampus roles. NeurIPS 2024.
At a glance
- Type
- Personalised PageRank over KG
- Tier
- T3
- Section
- Retrieval-as-memory hybrids
- Created
- 2024-05
- Latest release
- v1.0.0 2025-02-27
- License
- MIT
- GitHub
- 3.5k★ Python
- Pricing
- searched not found
- Funding
- not applicable — not commercial
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
Hippocampus-inspired single-pass retrieval — strong on multi-hop questions where multi-pass retrieval struggles.
Cons
Index build cost is high; eval primarily on synthetic multi-hop tasks.
Claims & capabilities
Up to +20% on multi-hop QA over SOTA. Single-step retrieval ≥ iterative IRCoT at 10–30× lower cost and 6–13× faster. v2 (Feb 2025) outperforms GraphRAG / RAPTOR / LightRAG.
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
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).
- 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.
- 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.
- 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.
Related systems
Referenced by (3)
- CAM cites — S2 isInfluential citation
- From Human Memory to AI Memory (survey) cites — S2 isInfluential citation
- KAG cites — S2 isInfluential citation