RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
RAGFlow is an open-source Retrieval-Augmented Generation engine that combines document retrieval, context management, and agent capabilities to help build AI applications. Developers use it to turn complex data into searchable, context-aware systems through workflows, datasets, and agent templates; the catalogue entries support working with RAGFlow.
Latest release v1.0.0-rc3 · 30 Oct 2026
3 files for Claude Code, Codex, GitHub Copilot and OpenCode: go-naming, ragflow copilot-instructions.md, ragflow AGENTS.md — 4,062 tokens loaded in every session.
.github/copilot-instructions.md A 156 tok AGENTS.md A 3,906 tok .agents/skills/go-naming/SKILL.md A 49 tok These files are infiniflow/ragflow's own configuration — they tell Claude Code, Codex, GitHub Copilot and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.