

RAGFlow
β Text source-checked Nov 19, 2026Open-source RAG engine combining retrieval and agent capabilities to create a context layer for LLMs.
Source-checked against the vendor's site Β· rebuilt from the vendor's own pagesProfile updated Link checked Pricing captured How we rate
In short
RAGFlow is an open-source RAG engine using deep document understanding to provide cited answers. It combines vector search, BM25, and agent workflows for LLM integration.
RAGFlow is an open-source retrieval-augmented generation engine based on deep document understanding. RAGFlow provides question-answering capabilities backed by citations from complex formatted data when integrated with LLMs.
RAGFlow combines vector search, BM25, and custom scoring with advanced re-ranking for retrieval. RAGFlow integrates RAG, tools, and MCPs within visual workflows for agent orchestration. RAGFlow uses a built-in ingestion pipeline to process multi-format data into semantic representations for retrieval.
RAGFlow supports local deployment via Docker or by launching from source. RAGFlow Docker images are available for Linux x86-64 and ARM64.
According to RAGFlow: RAGFlow is an open-source retrieval-augmented generation engine based on deep document understanding. Its pages list this strength: Deep document understanding for knowledge extraction from unstructured data with complicated formats. They also state this limitation: The free plan cannot purchase add-on packs.
β The AI Tool Bible editorial team
Pros
- β Deep document understanding for knowledge extraction from unstructured data with complicated formats.
- β Hybrid search combining vector search, BM25, and custom scoring with advanced re-ranking.
- β Visual workflow builder integrating RAG, tools, and MCPs for agent orchestration.
- β Open-source availability with local deployment options.
Cons
- β οΈ The free plan cannot purchase add-on packs.
Pricing (captured )
| Tier | Monthly | Key features |
|---|---|---|
| Free | $0 | β |
| Small team | $59 | β |
| Enterprise | Contact sales |
|
Prices change; we show the grid as captured on Oct 15, 2026. Check current pricing on the vendor's site β
Facts
- Platforms
- linux
- API available
- Yes (not source-checked)
- Free trial
- Yes (not source-checked)
- Open source
- Yes (license: Apache-2.0)
- GitHub stars
- 94,098 (checked Nov 13, 2026) (not source-checked)
- Last GitHub push
- Nov 13, 2026 (not source-checked)
- First commit
- Dec 2023 (not source-checked)
- Model used
- Multi-model (not source-checked)
- Vendor pages
- Changelog
- Docs pages indexed
- 215 pages we found in the docs (not source-checked)
- Hacker News
- 10 stories Β· top 13 points Β· last Nov 16, 2026 Β· checked Nov 19, 2026
- Earliest Wayback capture
- 2024-03-20 (earliest archived capture of the site, not a launch date)
Where this tool sits
Use cases
Recent updates from RAGFlow
Frequently asked
- How much does RAGFlow cost?
- RAGFlow offers a freemium model. The Free plan is $0/month. Starter plans are $29 or $59/month, while Pro plans are $129 or $259/month.
- Can I deploy RAGFlow locally?
- Yes, RAGFlow supports local deployment via Docker or by launching from source. Docker images are available for Linux x86-64 and ARM64 architectures.
- What retrieval methods does RAGFlow use?
- RAGFlow combines vector search, BM25, and custom scoring with advanced re-ranking. It uses a built-in ingestion pipeline to process multi-format data into semantic representations.
- Does RAGFlow support agent workflows?
- Yes, RAGFlow integrates RAG, tools, and MCPs within visual workflows for agent orchestration. It is suitable for use cases like agent workflow orchestration and investment research.
- Which LLMs does RAGFlow support?
- RAGFlow is described as using a multi-model approach. It provides question-answering capabilities backed by citations when integrated with LLMs, though specific model names are not documented.