# ragflow

Open-source Retrieval-Augmented Generation engine that combines deep document understanding with agent capabilities.

## Agent Decision Summary
- Risk level: low
- Source confidence: high
- Recommended workflows: Memory or RAG workflow
- Permission surface: memory
- Agent JSON: https://www.openagent.bot/memory-systems/ragflow.agent.json

## Summary
RAGFlow is an open-source RAG engine that goes beyond simple vector search by combining deep document understanding, layout analysis, and agent-based orchestration. It processes complex documents (PDFs, images, tables) with layout-aware parsing, then uses agent capabilities to route, filter, and augment retrieval results — creating a production-ready context layer for LLM applications.


## Guide
### What it is
RAGFlow is an open-source RAG engine that combines deep document understanding with agent capabilities. It processes complex documents with layout-aware parsing and uses agent orchestration for production-quality retrieval.

### Why it matters
RAGFlow is the most popular open-source RAG engine (81K+ stars) specifically because it handles the hardest part of RAG: extracting quality content from complex documents.


### FAQ
- What types of documents can RAGFlow process?
  - RAGFlow processes PDFs, images, Office documents, and other complex formats with layout-aware parsing that preserves tables, headers, and multi-column structure.
- Does RAGFlow include agent capabilities?
  - Yes, RAGFlow combines RAG with agent orchestration for intelligent routing, filtering, and result augmentation.
- Is RAGFlow open source?
  - Yes, it is open source under the Apache-2.0 license with 81K+ GitHub stars.
- Can RAGFlow be self-hosted?
  - Yes, RAGFlow is designed for self-hosted deployment with Docker support.
## What It Does
RAGFlow is an open-source RAG engine that combines deep document understanding with agent capabilities. It processes complex documents with layout-aware parsing and uses agent orchestration for production-quality retrieval.

## How To Evaluate
Evaluate ragflow by starting from the official sources, checking its repo interface surface, and running one narrow workflow before expanding scope. Recorded integrations include memory systems.

## Why It Matters
Most RAG systems fail on complex documents with tables, images, and unusual layouts. RAGFlow's deep document understanding pipeline solves this, making it the leading open-source RAG engine with 81K+ GitHub stars. Its combination of layout-aware parsing and agent orchestration sets a new standard for production RAG quality.


## Best For
- Teams building RAG systems that need to handle complex documents with tables, images, and multi-column layouts
- Organizations deploying document Q&A over PDFs, contracts, reports, and technical documentation
- Engineers who want an all-in-one RAG solution with document processing, retrieval, and agent orchestration

## Not For
- Simple vector search use cases where basic chunking and embedding are sufficient
- Teams that prefer to assemble RAG pipelines from individual components rather than using an integrated platform

## What It Actually Does
- Rag: ragflow surfaces rag as a core capability in its published project metadata and source links.
  - Why it matters: This gives readers a starting point for evaluating whether the project fits their workflow before visiting the source repository or docs.
- Workflow: ragflow surfaces workflow as a core capability in its published project metadata and source links.
  - Why it matters: This gives readers a starting point for evaluating whether the project fits their workflow before visiting the source repository or docs.
- Memory: ragflow surfaces memory as a core capability in its published project metadata and source links.
  - Why it matters: This gives readers a starting point for evaluating whether the project fits their workflow before visiting the source repository or docs.

## Typical Use Cases
- Personal memory: Use it as a candidate for personal memory when the project facts, license, and official links match your deployment requirements.

## How It Compares
- When to choose ragflow: Compare it with nearby memory systems by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need.

## Fit Matrix
- Memory or RAG workflow: strong. ragflow has multiple signals for memory or rag workflow, including matching tags, capabilities, category, or positioning. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
- Browser automation: partial. ragflow has at least one signal for browser automation, but should be checked against a real task before adoption. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Coding agent workflow: partial. ragflow has at least one signal for coding agent workflow, but should be checked against a real task before adoption. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Evaluation and observability: partial. ragflow has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Reusable skill workflow: partial. ragflow has at least one signal for reusable skill workflow, but should be checked against a real task before adoption. Required check: Run one skill end to end and check whether it produces evidence or structured output.
- Connector or protocol layer: weak. ragflow is not primarily positioned for connector or protocol layer in the current metadata. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.

## Evidence
- verified: ragflow is listed as open source. Source: License metadata: Apache-2.0
- verified: ragflow has a recorded GitHub repository: infiniflow/ragflow. Source: Resource facts and GitHub source link.
- inferred: ragflow supports these recorded deployment modes: cloud. Source: OpenAgent decision signal metadata.
- inferred: ragflow is tagged with rag, workflow, memory capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/infiniflow/ragflow
- Open Homepage: https://ragflow.io
- Inspect repository: https://github.com/infiniflow/ragflow/blob/main/README.md

## Facts
- Category: memory-systems
- Resource type: memory_system
- Open source: yes
- License: Apache-2.0
- Last verified: 2026-06-03
- GitHub repo: infiniflow/ragflow
- GitHub stars: 81809

## Capabilities
- rag
- workflow
- memory

## Structured Use Case Tags
- personal-memory

## Getting Started
- Review the repository: https://github.com/infiniflow/ragflow
- Homepage: https://ragflow.io
- Review the repository: https://github.com/infiniflow/ragflow/blob/main/README.md

## Links
- GitHub: https://github.com/infiniflow/ragflow
- Homepage: https://ragflow.io
- Source: https://github.com/infiniflow/ragflow/blob/main/README.md

## Structured Outputs
- JSON: https://www.openagent.bot/memory-systems/ragflow.json
- Markdown: https://www.openagent.bot/memory-systems/ragflow.md
- Agent JSON: https://www.openagent.bot/memory-systems/ragflow.agent.json
- Canonical: https://www.openagent.bot/memory-systems/ragflow