A neurobiologically inspired long-term memory framework that builds a knowledge graph over documents and retrieves with Personalized PageRank, enabling continual integration of knowledge. HippoRAG 2 improves multi-hop associativity and sense-making.
- Storage
- Open knowledge graph built from extracted entities/relations over a document corpus, plus passage embeddings. Pluggable vector-database backends (Qdrant or ChromaDB) were added June 2026 (PR #184), beyond the default in-memory store.
- Retrieval
- Personalized PageRank over the knowledge graph for single-step multi-hop retrieval. HippoRAG 2 adds a 'Recognition Memory' step (Sec. 3.4) that uses an LLM to filter candidate triples matched to the query before they become PPR seed nodes — so retrieval is graph traversal with one online LLM-filtering call in the loop, not purely deterministic.
- Self-host
- Self-host: moderate
- License
- MIT
- Pricing
- Open source (MIT), free to self-host · Free / OSS
- GitHub stars
- 3,933
- Last release
- 2025-02-27
- Last commit
- 2026-07-29
- First catalogued
- 2026-06-28
Strengths
- Peer-reviewed (NeurIPS'24); HippoRAG 2 follow-up paper (Feb 2025)
- Single-step multi-hop retrieval via Personalized PageRank
- More efficient offline indexing than GraphRAG/RAPTOR/LightRAG per the authors
- Actively maintained — community feature merges through June 2026 (e.g. pluggable Qdrant/ChromaDB backends)
Watch out
- Primarily a research artifact (no managed/hosted offering); PyPI package is still on a 2.0.0 alpha line
- Targets corpus QA / continual knowledge integration more than conversational user memory
Best for
- Multi-hop retrieval and knowledge integration over large document corpora
How it integrates
Benchmark results
No sourced results yet.
Sources
- Monthly card re-verification — GitHub API repo metadata: 3,901 stars, license MIT confirmed, archived=false, last commit on the default branch 2026-07-29 (third-party)
- https://github.com/OSU-NLP-Group/HippoRAG (vendor)
- PR #184 — pluggable vector database backends (Qdrant, ChromaDB), merged 2026-06-29 (vendor)
- hipporag on PyPI — v2.0.0a4, home_page = OSU-NLP-Group/HippoRAG (vendor)
- HippoRAG: Neurobiologically Inspired Long-Term Memory for LLMs (paper)
- From RAG to Memory: Non-Parametric Continual Learning for LLMs (HippoRAG 2) (paper)
- HippoRAG 2 full text, Sec 3.4-3.5 — confirms 'Recognition Memory' LLM triple-filtering step runs before PPR seeding (paper)
- GitHub API re-check — 3883 stars, MIT license confirmed, not archived, pushed 2026-07-13; active development (recent commits on hipporag2 IRCoT and chunking module through 2026-07-13) (third-party)
- PyPI re-check — still on pre-release v2.0.0a4, no new tagged release since 2025-02-27 (vendor)
Last verified 2026-08-01 · updated by refresh-framework-cards