🚀 LightRAG: Simple and Fast Retrieval-Augmented Generation 🎉 News [2026.05]🎯[New Feature]: Merge RagAnything into LightRAG🎉. Multimodal content parsing and extraction via MinerU / Docling services. [2026.05]🎯[New Feature]: Introducing four selectable text chunking strategies: , , , and . [2026.05]🎯[New Feature]: Role-specific LLM configuration support, 4 distinct roles: EXTRACT, QUERY, KEYWORDS, and VLM, with independent LLM settings. [2026.03]🎯[New Feature]: Integrated OpenSearch as a unified storage backend, providing comprehensive support for all four LightRAG storage.
| Stars | 40,210 |
| Forks | 5,705 |
| Language | Python |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 61.948305801124/100 |
| Open Issues | 392 |
| Last Updated | 2026-10-15 |
| Created | 2024-10-02 |
| Platforms | cli, python |
| Est. Tokens | ~21k |
These tools work well together with LightRAG for enhanced workflows:
Explore other popular ai 工具 tools:
LightRAG is [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation. It is categorized as a AI 工具 with 40.2k GitHub stars.
LightRAG is primarily written in Python. It covers topics such as docling, genai, gpt.
You can find installation instructions and usage details in the LightRAG GitHub repository at github.com/HKUDS/LightRAG. The project has 40.2k stars and 5705 forks, indicating an active community.
LightRAG is released under the MIT license, making it free to use and modify according to the license terms.