Awesome-RAG-Reasoning and agentic-rag

The first project, a collection of resources, complements the second project, an implementation of Agentic RAG, by providing foundational knowledge and research to support its development and understanding.

Awesome-RAG-Reasoning
50
Established
agentic-rag
50
Established
Maintenance 10/25
Adoption 10/25
Maturity 15/25
Community 15/25
Maintenance 2/25
Adoption 10/25
Maturity 15/25
Community 23/25
Stars: 408
Forks: 35
Downloads:
Commits (30d): 0
Language:
License: MIT
Stars: 198
Forks: 67
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: MIT
No Package No Dependents
Stale 6m No Package No Dependents

About Awesome-RAG-Reasoning

DavidZWZ/Awesome-RAG-Reasoning

[EMNLP 2025] Awesome RAG Reasoning Resources

This collection helps AI researchers and practitioners develop advanced AI systems that can accurately answer complex questions and solve problems. It brings together resources on combining external knowledge retrieval with sophisticated logical thinking, providing a roadmap for building more capable AI agents. Researchers, AI developers, and system architects working on advanced AI applications would use this.

AI research Large Language Models AI system design Agentic AI AI development

About agentic-rag

FareedKhan-dev/agentic-rag

Agentic RAG to achieve human like reasoning

This project helps financial analysts and researchers to deeply understand complex financial documents like SEC filings. It takes unstructured documents (10-K, 10-Q, 8-K reports) and processes them to generate structured insights, summaries, and trend analyses, mimicking how a human expert would reason and connect information. The output is a comprehensive, validated understanding of the data, going beyond simple fact retrieval.

financial-analysis market-research regulatory-compliance investment-due-diligence enterprise-search

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