[GitHub Trending] infiniflow/ragflow
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Leading open-source RAG engine with agent capabilities, highly relevant to AI/ML and data engineering.
RAGFlow is an open-source RAG engine that combines retrieval-augmented generation with agent capabilities, offering a converged context engine and pre-built agent templates for enterprise AI workflows. It supports deep document understanding, template-based chunking, grounded citations, and heterogeneous data sources, with recent updates adding agentic workflows, MCP support, multi-channel chat (Feishu, Discord, Telegram), and integration with DeepSeek v4 and Gemini 3 Pro. Self-hosting requires 4 CPU cores, 16 GB RAM, Docker, and Python 3.13, with optional gVisor for code execution sandboxing.
infiniflow