HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Repository profile
"RAG-Anything: All-in-One RAG Framework"
Repository updates
Get generated HKUDS/RAG-Anything development summaries by email, or follow the weekly and monthly RSS feeds.
Sign in to subscribe by email. RSS feeds are public.
Sign in to subscribeTracked growth, recent movement, and commit velocity from stored repository snapshots.
Latest capture 2026-07-15 03:12
5 captures since 2026-05-25
Stars from baseline +1581
All tracked data
Frameworks, package managers, ecosystems, and dependency manifests found during catalog scans.
Scanned 2026-07-15 03:12
Searchable topics, generated tags, and stack labels that explain where this repository fits.
Agent instructions and tool configuration paths found in the repository tree.
Nearest indexed repositories by embedding similarity.
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.
RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
http://arxiv.org/abs/2510.12323
README403 Forbidden | https://api.github.com/repos/HKUDS/RAG-Anything/readme | message=API rate limit exceeded for user ID 260990068. If you reach out to GitHub Support for help, please include the request ID C13E:15C0C8:D44FDE0:C96C26D:6A56FAB2 and timestamp 2026-07-15 03:12:50 UTC. For more on scraping GitHub and how it may affect your rights, please review our Terms of Service (htt | rate_limit_remaining=0 | rate_limit_reset=1784088007