5GitHub Trending (AI/LLM filtered)·
PageIndex: Open-source document indexing for reasoning-based RAG without vector embeddings
VectifyAI has released PageIndex, an open-source Python library that implements a 'vectorless' approach to retrieval-augmented generation, relying on reasoning-based document indexing rather than traditional vector embeddings. The project has accumulated 34,534 GitHub stars with 222 added today, indicating strong community traction. The approach challenges the dominant vector-store paradigm for RAG pipelines.
Related guides (2)
Related events (8)
Microsoft GraphRAG trending on GitHub
Microsoft's GraphRAG repository, a modular graph-based Retrieval-Augmented Generation system implemented in Python, is trending on GitHub with 34,340 total stars and 33 new stars today. GraphRAG structures knowledge as a graph to improve retrieval quality over flat vector search. The continued traction signals ongoing practitioner interest in graph-augmented retrieval approaches.
GLM-RAG: Graph Language Model retrievers outperform GNNs and vector search on out-of-domain multi-hop reasoning
A new arXiv preprint introduces GLM-RAG, a retrieval-augmented generation framework using graph language model (GLM)-based retrievers over knowledge graphs. The authors compare GLM-based, GNN-based, and vector-search retrievers across single- and multi-hop QA settings, finding that finetuned GLM retrievers generalize better to unseen domains and achieve state-of-the-art on two multi-hop benchmarks. GNN-based retrievers offer better graph coverage with efficient training, while vector search excels at single-hop tasks. The work provides a systematic comparison of retriever architectures for knowledge-graph RAG with practical implications for domain transfer.
LightRAG: Simple and Fast Retrieval-Augmented Generation (EMNLP 2025)
LightRAG is an open-source Python library for retrieval-augmented generation, accepted at EMNLP 2025, with nearly 38,000 GitHub stars. The project emphasizes simplicity and speed in RAG pipelines. Its high star count signals broad practitioner adoption in the RAG tooling space.
HippoRAG: RAG framework combining knowledge graphs and Personalized PageRank for continuous knowledge integration
HippoRAG is an open-source RAG framework published at NeurIPS 2024 by the OSU NLP Group that draws on models of human long-term memory to enable LLMs to continuously integrate knowledge across external documents. It combines retrieval-augmented generation with knowledge graphs and Personalized PageRank to improve multi-hop and associative retrieval. The repository has accumulated 3,742 GitHub stars with ongoing community traction.
Anthropic introduces Contextual Retrieval to reduce RAG retrieval failures by up to 67%
Anthropic published a technical method called Contextual Retrieval that combines Contextual Embeddings and Contextual BM25 to address the context-loss problem in traditional RAG pipelines. The approach prepends chunk-level context before encoding, reducing failed retrievals by 49% standalone and 67% when combined with reranking. The post also highlights prompt caching as a simpler alternative for knowledge bases under 200K tokens, and provides a cookbook for deployment with Claude.
RAGU: Open-source GraphRAG engine with compact 7B extractor model outperforming 32B baseline
RAGU is a new open-source modular GraphRAG engine that separates knowledge graph extraction from consolidation, using two-stage typed extraction, DBSCAN-backed deduplication, LLM summarization, and Leiden community detection. The authors train Meno-Lite-0.1, a 7B model specialized for language skills, which outperforms Qwen2.5-32B on knowledge-graph construction by 12.5% relative harmonic mean while matching it on English GraphRAG tasks. On GraphRAG-Bench (Medical), RAGU achieves evidence recall up to 0.84 versus ≤0.76 for competing systems. The system is MIT-licensed, pip-installable, and runs on a single GPU.
TurboVec: high-performance vector index built on TurboQuant with Rust/Python bindings
TurboVec is an open-source vector index library implemented in Rust with Python bindings, built on top of TurboQuant. The project has accumulated 7,019 GitHub stars with 1,533 added in a single day, indicating significant community interest. It targets high-performance approximate nearest neighbor search, a core component of RAG and embedding-based retrieval pipelines.
FastGPT: open-source knowledge-base platform with RAG and visual workflow orchestration
FastGPT is an open-source TypeScript platform for building knowledge-based question-answering systems on top of LLMs, featuring data processing pipelines, RAG retrieval, and a visual AI workflow editor. The project has accumulated 28,533 GitHub stars with modest daily growth (+65), indicating steady community traction. It targets developers who want to deploy RAG-based QA systems without extensive configuration.