Home Projects arag
arag
Python

arag

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.

by Ayanami0730 · GitHub
Stars
Forks
Trending
Created
Last commit
Category
Language
agentagentic-aiagenticragPython
View on GitHub
In plain words

Use advanced tools to answer complex questions by retrieving and combining information from multiple sources.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
arag — GitHub preview card
📈 Star history
332315
2026-07-202026-08-31
📈 Track arag

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

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.

arag has 332 stars on GitHub. It has been forked 50 times. arag is written mainly in Python. It has been in active development since 2026. Its main topics are agent, agentic-ai, agenticrag, deepresearch.

Frequently asked questions

What is arag?

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.

Is arag open source?

arag is an open-source project.

Is arag free?

Yes. arag is free and open source — you can use, modify and self-host it.

What language is arag written in?

arag is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — arag

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=ayanami0730-arag)](https://olud.ai/project/ayanami0730-arag.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.