RAGFlow
A retrieval-augmented generation engine that parses complex documents, such as PDFs, tables and scans, into a knowledge base for grounded AI answers and agents.
What is RAGFlow?
RAGFlow focuses on the hard first step of RAG: understanding documents. Its DeepDoc component analyzes layout, runs OCR and recognizes tables, so answers can cite the right passage in a messy PDF or scan. On top of the knowledge base it offers chat with citations, an agent builder with templates, and features that turn documents into wikis, graphs and mind maps. It can ingest websites through sitemaps and connects to many model providers.
Good fit if
- Your source material is complex PDFs, scans or spreadsheets, and plain text splitting gives poor answers.
- You want answers that show the passages they come from.
- You need a self-hosted RAG service with a web UI for non-developers.
Look elsewhere if
- You want a lighter document chat app: AnythingLLM or Kotaemon.
- You need visual LLM app building beyond RAG: Dify.
Before you adopt it
RAGFlow is Apache-2.0, but the web/src/ee directory holds enterprise features, so some of the interface is a paid part. The authors recommend at least 4 CPU cores, 16 GB of RAM and 50 GB of disk for a Docker deployment, and more for local models.
Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction
RAGFlow health: is it still maintained?
93 of 100, actively developed
Read from GitHub on 1 November 2026. How the score works
RAGFlow license: is it open source?
RAGFlow uses Apache-2.0, an open-source license approved by the OSI. Some features sit under a separate paid license inside the same repository.
- December 2023First published on GitHub.
- TodayApache-2.0, with paid parts: directory web/src/ee/.
How to run RAGFlow yourself
- Docker
- Dockerfile or compose file in the repository
- Compose file
- docker/docker-compose.yml: 1 service
- Setup effort
- 1 of 5, judged from the compose file
- Kubernetes
- No Helm chart in the repository
- Desktop and mobile
- Builds for macOS, Windows, Linux, including ARM in GitHub releases
- Interface languages
- 15 languages
Install instructions: ragflow.io or the README on GitHub.
Alternatives to RAGFlow
- AnythingLLMStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first… 94 health · MIT · 67.8k stars
- DocsGPTPrivate AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research,… 84 health · MIT · 18.4k stars
- Hermes AgentThe agent that grows with you 76 health · MIT · 259k stars
- LobeHubLobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and… 73 health · LobeHub Community License · 83.7k stars
- MaxKBMaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。 82 health · GPL-3.0 · 23.1k stars
Questions about RAGFlow
Is RAGFlow open source?
Yes. RAGFlow is published under Apache-2.0, an OSI-approved open-source license. Some features are kept under a separate paid license in the same repository.
Is RAGFlow still maintained?
Its health score is 93 of 100 (actively developed). It had 2,740 commits in the last 90 days, the latest on 31 October 2026, and its latest release came out on 30 October 2026.
How do I run RAGFlow?
You can run it with Docker, as an app for macOS, Windows, Linux, including ARM. The README on GitHub has the exact steps.
What are the alternatives to RAGFlow?
Close alternatives in the AI chat & local LLMs category include AnythingLLM, DocsGPT, Hermes Agent.