What is RAGFlow used for?

RAGFlow is an open-source retrieval-augmented generation engine that combines document understanding with agent capabilities to give LLMs grounded context. It is a good fit for question answering over company documents, building knowledge-base assistants and grounding LLM agents in private data.

Is RAGFlow open source?

Yes. RAGFlow is open source under the Apache-2.0 licence. Its source code is on GitHub at infiniflow/ragflow and is written mainly in Go.

Yes. RAGFlow is open source, so the software itself is free to use. A managed cloud version is also available, with paid plans from $59 per month.

Can I self-host RAGFlow?

Yes. RAGFlow can be self-hosted on your own server or infrastructure.

What is RAGFlow an alternative to?

RAGFlow is an open-source alternative to Vectara, Glean, Unstructured and Cohere. Other open-source alternatives to Vectara include Swirl and Supavec.

Is RAGFlow actively maintained?

Yes. The most recent commit to RAGFlow was on 2 October 2026, and the latest release is v1.0.0-rc1, published on 29 September 2026. The project has 92k stars on GitHub.

RAGFlow: open-source alternative to Vectara, Glean

About RAGFlow

RAGFlow is an open-source engine for retrieval-augmented generation (RAG). It combines RAG with agent capabilities to give large language models a context layer built from your own documents, so applications can answer from real data. It is released under the Apache-2.0 license and, per the repository, is currently at a 1.0.0 release candidate.

It extracts knowledge from unstructured documents with complicated formats using deep document understanding, and offers pre-built agent templates. Recent updates mentioned in the README include website ingestion through sitemaps, Google BigQuery data sources with incremental sync, knowledge compilation that generates wikis, graphs, trees and mind maps, and agentic RAG with multiple thinking modes.

You can try the managed cloud service or deploy it locally by following the local deployment guide. The project provides documentation, a roadmap and a Discord community. It suits developers and enterprises building document question answering and knowledge-based assistants who want control over their data pipeline.

Key features

Deep document understanding for unstructured files
Retrieval-augmented generation workflows
Pre-built agent templates
Agentic RAG with adjustable thinking modes
Website ingestion through sitemaps
Knowledge compilation into wikis and graphs
Google BigQuery data source sync

Good fit for

→Question answering over company documents
→Building knowledge-base assistants
→Grounding LLM agents in private data

Built with: Go
Tags: rag; retrieval-augmented-generation; ai-agents; llm; document-understanding; knowledge-base; self-hosted; ai

RAGFlow: questions and answers

What is RAGFlow used for?: RAGFlow is an open-source retrieval-augmented generation engine that combines document understanding with agent capabilities to give LLMs grounded context. It is a good fit for question answering over company documents, building knowledge-base assistants and grounding LLM agents in private data.
Is RAGFlow open source?: Yes. RAGFlow is open source under the Apache-2.0 licence. Its source code is on GitHub at infiniflow/ragflow and is written mainly in Go.
Is RAGFlow free?: Yes. RAGFlow is open source, so the software itself is free to use. A managed cloud version is also available, with paid plans from $59 per month.
Can I self-host RAGFlow?: Yes. RAGFlow can be self-hosted on your own server or infrastructure.
What is RAGFlow an alternative to?: RAGFlow is an open-source alternative to Vectara, Glean, Unstructured and Cohere. Other open-source alternatives to Vectara include Swirl and Supavec.
Is RAGFlow actively maintained?: Yes. The most recent commit to RAGFlow was on 2 October 2026, and the latest release is v1.0.0-rc1, published on 29 September 2026. The project has 92k stars on GitHub.