RAGFlow

Open-source RAG engine with document ingestion, hybrid search and visual agent workflows.

Infrastructure by InfiniFlow

IndexedApache-2.0★ 92,809

Write a review

Get started

Setup steps are in the repository. Website · Docs · Repository

About

RAGFlow is an open-source retrieval-augmented generation engine. It includes an ingestion pipeline that structures multi-format documents, hybrid search that combines vector search, full-text search and re-ranking, and a visual workflow builder for agents that use retrieval, tools and MCP. The project is Apache-2.0 licensed and can also be used as a cloud service.

Use cases: knowledge-base, agent-orchestration

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category: RAG and data · rag engine
Self-host: Yesraw.githubusercontent.com
Open source: Yesraw.githubusercontent.com
Protocols: mcpragflow.io

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Signals

Stars: 92,809
Forks: 11,100
Open issues: 931
Last commit: Oct 24, 2026 (3 days ago)
Last release: Oct 16, 2026 (12 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/infiniflow/ragflow
Website: ragflow.io
Docs: ragflow.io/docs/dev/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Website Docs README github-graphql