Back to the chart

infiniflow/ragflow

Agent-native RAG and context engine

Chart
Not on a chart right now
Stars
94.4k

Open on GitHubHomepage

What it is

RAGFlow is an open-source RAG engine and agent-native database that extracts knowledge from complex unstructured data to build a context layer for LLMs. It provides an end-to-end workflow covering document parsing, chunking, and agentic retrieval.

Who it is for

It is suited for developers and enterprises building production RAG and AI agent systems over complex documents and heterogeneous data sources.

Why it is trending

It released v1.0.0 on November 6, 2026, and gained 2,170 stars today, reaching 94,303 total stars. It stands out by combining deep document understanding with Knowledge Compilation and multi-step Agentic Retrieval.

Main features

  • Deep document parsing across PDFs, Office files, images, and web pages
  • Knowledge Compilation into Wikis, Graphs, Trees, and Mind Maps
  • Multi-step Agentic Retrieval with Low to Ultra thinking modes
  • Chunk visualization and traceable citations to reduce hallucinations

Summarized on November 18, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary