by Ayanami0730 · AI 工具 · ★ 323
A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces If you find our project helpful, please give us a star ⭐ on GitHub! 🚀 Quick Start Note: Datasets hosted on HuggingFace 🤗, reformatted from Zly0523/linear-rag and GraphRAG-Bench into a unified format. Don't have ? Install it: ✨ News [Feb 2026] 📄 Paper released on arXiv [Feb 2026] 🚀 Initial code and evaluation suite released 📖 Overview Frontier language models have demonstrated strong reasoning and long-horizon tool-use capabilities. However, existing RAG systems fail to leverage these capabilities.
| Stars | 323 |
| Forks | 49 |
| Language | Python |
| Category | AI 工具 |
| Quality Score | 62.8582548304153/100 |
| Open Issues | 5 |
| Last Updated | 2026-02-06 |
| Created | 2026-02-03 |
| Platforms | python |
| Est. Tokens | ~172k |
These tools work well together with arag for enhanced workflows:
Explore other popular ai 工具 tools:
arag is A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.. It is categorized as a AI 工具 with 323 GitHub stars.
arag is primarily written in Python. It covers topics such as agent, agentic-ai, agenticrag.
You can find installation instructions and usage details in the arag GitHub repository at github.com/Ayanami0730/arag. The project has 323 stars and 49 forks, indicating an active community.