Ross ROSS = Recommend OSS · open-source software intelligence for agents

infiniflow/ragflow

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs observed · 2026-08-28

github.com/infiniflow/ragflow · homepage · Go · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

93/100

  • Activity 99
  • Release rhythm 98
  • Longevity 71
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: 11.0
  • age_days: 995
  • days_rel: 14
  • days_push: 7
  • n_releases_24m: 39

Full methodology

Adoption not part of the score

89328 stars · 10511 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that combines deep document understanding with agent orchestration to provide a context layer for LLMs. It offers ingestion pipelines for multi-format data, hybrid retrieval (vector, full-text, tensor), and visual agent workflows, deployable via Docker.

Use cases

  • build a chatbot that answers questions from my own documents with citations
  • parse and index PDFs and complex documents for RAG
  • set up a self-hosted RAG engine with hybrid vector and BM25 search
  • build AI agents that retrieve knowledge from enterprise datasets
  • extract structured data from legal or financial documents
  • create a knowledge base Q&A system for my company
  • orchestrate multi-agent workflows with retrieval and web search
  • add a context layer to LLM applications

When to choose

  • you need a full-featured, self-hosted RAG platform with document parsing, retrieval, and agent orchestration in one product
  • you want grounded answers with citations from complex formatted documents
  • you need hybrid search (vector, full-text, tensor) with re-ranking
  • you want visual workflow-based agent building with MCP and tool integration

When to avoid

  • you only need a lightweight embedding or vector search library to embed in your own code
  • you cannot run Docker with at least 4 CPU cores and 16 GB RAM
  • you need ARM Docker images, which are not officially maintained
  • you want a minimal headless API without a built-in UI and agent platform

Facets

application · maturity active

rag search-engine etl agent-framework llm-inference chatbot web-scraping ocr pdf self-hosted artificial-intelligence large-language-models self-hosted developer-tools self-hosted python go rag-engine document-understanding hybrid-search agentic-rag knowledge-compilation vector-search bm25 mcp enterprise question-answering retrieval-augmented-generation ai-agents search natural-language-processing docker linux web-server

4 sources

Member repositories

RepositoryRoleHealth v2
infiniflow/ragflowmain93

For agents

markdown · JSON · MCP: product_card(name="infiniflow/ragflow")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem