{
  "schema_version": "openagent.resource.v1",
  "id": "res_ragflow",
  "slug": "ragflow",
  "status": "published",
  "identity": {
    "name": "ragflow",
    "one_liner": "Open-source Retrieval-Augmented Generation engine that combines deep document understanding with agent capabilities.",
    "short_description": "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."
  },
  "classification": {
    "resource_type": "memory_system",
    "primary_category": "memory-systems",
    "subcategories": [
      "memory-systems",
      "rag",
      "document-processing",
      "workflow"
    ]
  },
  "positioning": {
    "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"
    ],
    "use_cases": [
      "personal-memory"
    ],
    "target_audience": [
      "developer",
      "agent_builder"
    ],
    "maturity": "active"
  },
  "decision_signals": {
    "deployment_modes": [
      "cloud"
    ],
    "open_source": true,
    "local_first": false,
    "self_hostable": false,
    "has_api": false,
    "has_gui": false,
    "supports_mcp": false,
    "supports_docker": false
  },
  "facts": {
    "license": "Apache-2.0",
    "pricing_model": "open_source",
    "github_stars": 81809,
    "github_forks": 9414,
    "github_repo_full_name": "infiniflow/ragflow",
    "last_verified_at": "2026-06-03"
  },
  "capabilities": {
    "core_capabilities": [
      "rag",
      "workflow",
      "memory"
    ],
    "integrations": [
      "memory systems"
    ],
    "interfaces": [
      "repo"
    ]
  },
  "links": {
    "primary_url": "https://github.com/infiniflow/ragflow",
    "items": [
      {
        "type": "github",
        "label": "GitHub",
        "url": "https://github.com/infiniflow/ragflow"
      },
      {
        "type": "homepage",
        "label": "Homepage",
        "url": "https://ragflow.io"
      },
      {
        "type": "github",
        "label": "Source",
        "url": "https://github.com/infiniflow/ragflow/blob/main/README.md"
      }
    ]
  },
  "media": {
    "thumbnail_url": "https://opengraph.githubassets.com/openagentbot/infiniflow/ragflow",
    "og_image_url": "https://opengraph.githubassets.com/openagentbot/infiniflow/ragflow",
    "thumbnail_brief": {
      "resource_type": "memory_system",
      "visual_motif": "layered cards, archive grid, or stacked memory tiles",
      "background_style": "minimal editorial surface with restrained open-source accent color",
      "title_overlay": "ragflow",
      "subtitle": "Open-source Retrieval-Augmented Generation engine that combines deep document understanding with agent capabilities.",
      "avoid": [
        "noisy poster layout",
        "large marketing slogans",
        "random gradient blobs"
      ]
    }
  },
  "tags": {
    "category": [
      "memory-system",
      "open-source"
    ],
    "capability": [
      "rag",
      "workflow",
      "memory"
    ],
    "constraint": [
      "open-source"
    ],
    "scenario": [
      "personal-memory"
    ]
  },
  "relationships": {},
  "machine_readable": {
    "canonical_url": "https://www.openagent.bot/memory-systems/ragflow",
    "json_url": "https://www.openagent.bot/memory-systems/ragflow.json",
    "markdown_url": "https://www.openagent.bot/memory-systems/ragflow.md"
  },
  "seo": {
    "title": "RAGFlow: Open-Source RAG Engine with Agent Capabilities",
    "description": "RAGFlow is a leading open-source Retrieval-Augmented Generation engine that combines deep document understanding with agent orchestration for production RAG."
  },
  "editorial": {
    "trust_note": "Verified from source links and project metadata.",
    "core_strengths": [
      {
        "title": "Rag",
        "description": "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."
      },
      {
        "title": "Workflow",
        "description": "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."
      },
      {
        "title": "Memory",
        "description": "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."
      }
    ],
    "use_case_notes": [
      {
        "title": "Personal memory",
        "description": "Use it as a candidate for personal memory when the project facts, license, and official links match your deployment requirements."
      }
    ],
    "compare_notes": [
      {
        "title": "When to choose ragflow",
        "summary": "Compare it with nearby memory systems by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need."
      }
    ],
    "getting_started": [
      {
        "label": "Review the repository",
        "url": "https://github.com/infiniflow/ragflow",
        "type": "github"
      },
      {
        "label": "Homepage",
        "url": "https://ragflow.io",
        "type": "homepage"
      },
      {
        "label": "Review the repository",
        "url": "https://github.com/infiniflow/ragflow/blob/main/README.md",
        "type": "github"
      }
    ],
    "seo_article": {
      "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": [
        {
          "question": "What types of documents can RAGFlow process?",
          "answer": "RAGFlow processes PDFs, images, Office documents, and other complex formats with layout-aware parsing that preserves tables, headers, and multi-column structure."
        },
        {
          "question": "Does RAGFlow include agent capabilities?",
          "answer": "Yes, RAGFlow combines RAG with agent orchestration for intelligent routing, filtering, and result augmentation."
        },
        {
          "question": "Is RAGFlow open source?",
          "answer": "Yes, it is open source under the Apache-2.0 license with 81K+ GitHub stars."
        },
        {
          "question": "Can RAGFlow be self-hosted?",
          "answer": "Yes, RAGFlow is designed for self-hosted deployment with Docker support."
        }
      ]
    }
  },
  "timestamps": {
    "created_at": "2026-06-03T00:00:00.000Z",
    "updated_at": "2026-06-03T00:00:00.000Z",
    "published_at": "2026-06-03T00:00:00.000Z"
  }
}