Awesome-RAG and Awesome-GraphRAG

These are complementary resources, as the second tool specifically curates resources for graph-based RAG, which is a specialized subfield of the broader RAG applications covered by the first tool, allowing a user to first explore general RAG applications and then deep-dive into graph-based approaches if relevant.

Awesome-RAG
60
Established
Awesome-GraphRAG
55
Established
Maintenance 17/25
Adoption 10/25
Maturity 16/25
Community 17/25
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 19/25
Stars: 1,071
Forks: 86
Downloads:
Commits (30d): 9
Language:
License: CC0-1.0
Stars: 2,181
Forks: 183
Downloads:
Commits (30d): 0
Language:
License: MIT
No Package No Dependents
No Package No Dependents

About Awesome-RAG

Danielskry/Awesome-RAG

😎 Awesome list of Retrieval-Augmented Generation (RAG) applications in Generative AI.

Compiles tools, frameworks, and architecture patterns for building RAG systems—covering everything from naive retrieval pipelines to advanced approaches like agentic RAG, graph-based retrieval, and multimodal generation. Organizes resources across Python ecosystems (LangChain, LlamaIndex, Haystack), vector databases, evaluation metrics, and production deployment strategies. Serves as a structured knowledge map connecting RAG theory, implementation tutorials, and best practices for reducing hallucinations through grounded context retrieval.

About Awesome-GraphRAG

DEEP-PolyU/Awesome-GraphRAG

Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.

Organizes GraphRAG research into three core dimensions—knowledge organization (graph construction via entity extraction or hierarchical indexing), retrieval mechanisms (semantic similarity, logical reasoning, GNN-based, and LLM-based approaches), and knowledge integration (fine-tuning vs. in-context learning)—with accompanying benchmarks and open-source implementations. The repository maps distinct GraphRAG paradigms including knowledge-based approaches that extract entity-relation graphs from raw text and index-based approaches that build topic hierarchies, contrasting both against traditional chunk-based RAG. Covers integration patterns across LLM frameworks and provides curated links to peer-reviewed papers, established benchmarks like GraphRAG-Bench, and reference implementations including LinearRAG and LogicRAG.

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