awesome-rag and Awesome-RAG

These are ecosystem siblings—both are curated resource collections documenting the same RAG technology domain, with B appearing to focus more specifically on LLM-centric RAG development while A takes a broader approach to RAG-related tools and techniques.

awesome-rag
39
Emerging
Awesome-RAG
39
Emerging
Maintenance 2/25
Adoption 10/25
Maturity 15/25
Community 12/25
Maintenance 10/25
Adoption 10/25
Maturity 8/25
Community 11/25
Stars: 176
Forks: 14
Downloads:
Commits (30d): 0
Language:
License: MIT
Stars: 439
Forks: 19
Downloads:
Commits (30d): 0
Language:
License:
Stale 6m No Package No Dependents
No License No Package No Dependents

About awesome-rag

Poll-The-People/awesome-rag

awesome-rag: a collection of awesome thing related to Retrieval-Augmented Generation

Curated resource directory spanning 20+ categories: open-source frameworks (LangChain, LlamaIndex, Haystack), vector databases, embedding models, research papers, retrieval techniques (dense/sparse/hybrid), and evaluation benchmarks. Covers emerging approaches including graph-based RAG, multimodal retrieval, and knowledge-graph integration alongside foundational concepts like chunking strategies, prompt optimization, and hallucination mitigation. Includes vendor tools, SDKs across Python/JavaScript/JVM/Rust ecosystems, educational content, and 2024-2025 trend tracking for production RAG deployment.

About Awesome-RAG

liunian-Jay/Awesome-RAG

💡 Awesome RAG: A resource of Retrieval-Augmented Generation (RAG) for LLMs, focusing on the development of technology.

Curated repository tracking peer-reviewed RAG research across top-tier conferences (NeurIPS, ACL, ICML, ICLR) and recent arxiv papers, organized by publication date and venue. Includes comprehensive evaluation datasets (HotpotQA, TriviaQA, ASQA, etc.) for benchmarking retrieval and generation systems. Actively maintains associated frameworks and tools like LightRAG, AgenticRAG-RL, and QAgent, with community contributions encouraged for staying current with rapidly evolving RAG methodologies.

Scores updated daily from GitHub, PyPI, and npm data. How scores work