Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.
| Date | Stars |
|---|---|
| 2026-07-31 | 3898 |
| 2026-08-03 | 3898 |
| 2026-08-06 | 3915 |
Today
+17 stars today
This week
— stars this week
This month
— stars this month
Momentum
68.0
growth rate 0.00%/day
<h1 align="center">HippoRAG 2: From RAG to Memory</h1>
<p align="center">
<img src="https://github.com/OSU-NLP-Group/HippoRAG/raw/main/images/hippo_brain.png" width="55%" style="max-width: 300px;">
</p>
[<img align="center" src="https://colab.research.google.com/assets/colab-badge.svg" />](https://colab.research.google.com/drive/1nuelysWsXL8F5xH6q4JYJI8mvtlmeM9O#scrollTo=TjHdNe2KC81K)
[<img align="center" src="https://img.shields.io/badge/arXiv-2502.14802 HippoRAG 2-b31b1b" />](https://arxiv.org/abs/2502.14802)
[<img align="center" src="https://img.shields.io/badge/🤗 Dataset-HippoRAG 2-yellow" />](https://huggingface.co/datasets/osunlp/HippoRAG_2/tree/main)
[<img align="center" src="https://img.shields.io/badge/arXiv-2405.14831 HippoRAG 1-b31b1b" />](https://arxiv.org/abs/2405.14831)
[<img align="center" src="https://img.shields.io/badge/GitHub-HippoRAG 1-blue" />](https://github.com/OSU-NLP-Group/HippoRAG/tree/legacy)
HippoRAG 2 is a memory framework for LLMs that recognizes and uses connections in new knowledge, mirroring a key function of human long-term memory.
Our experiments show that HippoRAG 2 improves associativity (multi-hop retrieval) and sense-making (the process of integrating large and complex contexts) in even the most advanced RAG systems, without sacrificing their performance on simpler tasks.
Like its predecessor, HippoRAG 2 remains cost and latency efficient in online processes, while using significantly fewer resources for offline indexing compared to other graph-based solutions such as GraphRAG, RAPTOR, and LightRAG.
<p align="center">
<img align="center" src="https://github.com/OSU-NLP-Group/HippoRAG/raw/main/images/intro.png" />
</p>
<p align="center">
<b>Figure 1:</b> Evaluation of continual learning capabilities across three key dimensions: factual memory (NaturalQuestions, PopQA), sense-making (NarrativeQA), and associativity (MuSiQue, 2Wiki, HotpotQA, and LV-Eval). HippoRAG 2 surpasses other methods across all
categories, bringing it one step closer to true long-term memory.
</p>
<p align="center">
<img align="center" src="https://github.com/OSU-NLP-Group/HippoRAG/raw/main/images/methodology.png" />
</p>
<p align="center">
<b>Figure 2:</b> HippoRAG 2 methodology.
</p>
### Papers
* [**HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models**](https://arxiv.org/abs/2405.14831) [NeurIPS '24].
* [**From RAG to Memory: Non-Parametric Continual Learning for Large Language Models**](https://arxiv.org/abs/2502.14802) [ICML '25].
----
## Installation
Use Conda or `uv` to create a Python 3.10 environment. A project-local `.venv` is recommended for development.
```sh
conda create -n hipporag python=3.10
conda activate hipporag
pip install hipporag
```
Set only the environment variables required by the models you use:
```sh
export CUDA_VISIBLE_DEVICES=0,1,2,3
export HF_HOME=<path to Huggingface home directory>
export OPENAI_API_KEY=<your openai api key> # if you want to use OpenAI model
conda activate hipporag
```
For a project-local environment managed by `uv`:
```sh
uv venv --python 3.10 .venv
source .venv/bin/activate
uv pip install -e .
```
## Quick Start
### OpenAI
The complete runnable version is [`examples/demo_openai.py`](examples/demo_openai.py). A minimal workflow is:
Set `OPENAI_API_KEY` before using OpenAI models:
```sh
export OPENAI_API_KEY=<your OpenAI API key>
```
```python
from hipporag import HippoRAG
docs = ["George Rankin is a politician."]
queries = ["What is George Rankin's occupation?"]
hipporag = HippoRAG(save_dir="outputs", llm_model_name="gpt-4o-mini", embedding_model_name="text-embedding-3-small")
hipporag.index(docs=docs)
results = hipporag.rag_qa(queries=queries)
```
#### OpenAI-compatible endpoints
Pass custom base URLs for OpenAI-compatible LLM and embedding servers:
```sh
export OPENAI_API_KEY=<the API key required by your endpoint>
```
For endpoints that do not require authentication, set this to a non-empty placehExcerpt of 19,776 characters
Read on GitHub
57
47
19
3
3
Chasing · China
2
1
1
1
Sebastion OSS · Foundation Machines · United Kingdom
1
Cheney Zhang · @zilliztech · China
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:11134a425eed3779, desc:rag framework, desc:long-term memory