Awesome-Deep-Research and Awesome-RAG-Reasoning
These are complementary resources: deep research systems use agentic workflows to iteratively refine queries and gather information, while RAG reasoning systems focus on improving how retrieved documents are synthesized into answers—both techniques are often combined in production agentic-RAG pipelines.
About Awesome-Deep-Research
DavidZWZ/Awesome-Deep-Research
[Up-to-date] Awesome Agentic Deep Research Resources
Curates industry products, open-source implementations, research papers, and evaluation benchmarks for autonomous research agents that perform multi-step information gathering and reasoning. Covers frameworks like LangGraph and Claude-based multi-agent systems, along with reasoning-augmented retrieval (RAG) approaches that integrate web search with LLM inference. Includes comparative analysis of proprietary solutions from Google, OpenAI, and Anthropic alongside community-driven alternatives for building custom deep research agents.
About Awesome-RAG-Reasoning
DavidZWZ/Awesome-RAG-Reasoning
[EMNLP 2025] Awesome RAG Reasoning Resources
Curates papers, benchmarks, and implementations across three integration patterns: reasoning-enhanced RAG (optimizing retrieval and generation), RAG-enhanced reasoning (grounding with external knowledge), and synergized systems using iterative retrieval-reasoning loops. Organizes taxonomy covering chain/tree/graph-based workflows, single/multi-agent orchestration, and tool-using approaches within agentic AI frameworks. Provides evaluation resources spanning single/multi-hop QA, fact-checking, summarization, and domain-specific tasks alongside code implementations.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work