Dify From $49.17/mo · Free plan 9.4 Visit 
RAGFlow
ragflow.io
What it is
RAGFlow is an open-source retrieval-augmented generation engine and agent platform for building a context layer for AI agents. Its ingestion pipeline processes multiple data formats into semantic representations for retrieval. Search combines vector search and BM25 with custom scoring and re-ranking, while visual workflows connect retrieval, tools, and MCPs for agent orchestration. Users can connect online, local, and OpenAI-compatible model providers for knowledge bases, chats, search, and agents. Documented connectors include Notion, Google Drive, S3, Microsoft Teams, REST API, and Sitemap. RAGFlow provides HTTP and Python APIs, and a chat assistant can be embedded in another webpage using an iframe. It offers cloud and self-hosted deployment; Docker deployment has a stated minimum of 4 CPU cores, 16 GB RAM, and 50 GB disk. The free plan includes five apps, one team member, 0.1 GB of dataset storage, and 500 monthly credits, but no API key. Starter costs $29 a month and includes an API key.
Spec sheet
- What it does
- RAGFlow is an open-source retrieval-augmented-generation engine and agent platform designed to provide grounded answers with citations.Read 15 Oct 2026 · ragflow.io
- Purpose
- RAGFlow describes itself as an open-source RAG engine and integrated agent platform for building a context layer for AI agents.Read 29 Sep 2026 · ragflow.io
- Intended users
- The site describes the platform as built for enterprise and lists solutions for financial services, legal and compliance, manufacturing, and education.Read 29 Sep 2026 · ragflow.io
- Security
- By default, RAGFlow validates MCP server URLs and rejects hosts that resolve to loopback, private, link-local, reserved, or other non-public addresses.Read 29 Sep 2026 · ragflow.io
- License
- The public repository is labeled Apache-2.0 licensed.Read 15 Oct 2026 · github.com
- Agent orchestration
- Visual workflows combine retrieval, tools and MCP services for agent construction.Read 15 Oct 2026 · ragflow.io
- Agent workflows
- Its visual workflows integrate RAG, tools, and MCPs for agent orchestration.Read 29 Sep 2026 · ragflow.io
- API and embedding
- RAGFlow provides HTTP and Python APIs and supports embedding a Chat assistant in a third-party webpage with an iframe.Read 29 Sep 2026 · ragflow.io
- API migration
- RAGFlow 1.0 moves its public REST backend from Python to Go and documents endpoint and parameter changes.Read 15 Oct 2026 · ragflow.io
- Architecture limitation
- The official Go image targets Linux AMD64; ARM64 requires a matching dependency image and native libraries.Read 15 Oct 2026 · ragflow.io
- Chat channels
- Supported chat-channel integrations include Discord, DingTalk, Telegram, WeCom and Feishu/Lark.Read 15 Oct 2026 · ragflow.io
- Chunking control
- Users can inspect chunking results and intervene in parsing through configurable chunk templates.Read 15 Oct 2026 · ragflow.io
- Company founded
- LinkedIn lists InfiniFlow as founded in 2023.Read 15 Oct 2026 · linkedin.com
- Company headquarters
- LinkedIn lists InfiniFlow headquarters in Shanghai, China.Read 15 Oct 2026 · linkedin.com
- Company legal name
- Crunchbase lists the legal name as InfiniFlow Inc.Read 15 Oct 2026 · crunchbase.com
- Company size
- LinkedIn lists InfiniFlow as having 11–50 employees.Read 15 Oct 2026 · linkedin.com
- Data connectors
- Documented data sources include Notion, Google Drive, S3, Microsoft Teams, REST API, and Sitemap.Read 29 Sep 2026 · ragflow.io
- Data processing
- Its built-in ingestion pipeline cleanses and processes multi-format data into semantic representations for retrieval.Read 29 Sep 2026 · ragflow.io
- Deep document understanding
- RAGFlow supports parsing complex documents such as scanned PDFs, tables, images and slide decks.Read 15 Oct 2026 · ragflow.io
- Deployment complexity
- Independent analysis says Docker deployment also runs Elasticsearch or Infinity, MinIO, MySQL and Redis, increasing operational complexity.Read 15 Oct 2026 · datacamp.com
- Developer interfaces
- Independent documentation describes web UI, REST, Python and JavaScript APIs, MCP and agent workflows.Read 15 Oct 2026 · andrew.ooo
- Document ingestion
- Its built-in ingestion pipeline cleans and processes multi-format data into semantic representations for retrieval.Read 15 Oct 2026 · ragflow.io
- Enterprise support
- The Enterprise plan lists dedicated support and a custom SLA.Read 29 Sep 2026 · ragflow.io
- External tools
- Agents can connect to external MCP servers over Streamable HTTP or SSE; stdio servers require a gateway or another service exposing a supported endpoint.Read 29 Sep 2026 · ragflow.io
- Hardware limitation
- An independent review warns that deployments with less than 16 GB RAM can suffer Elasticsearch out-of-memory kills and silent ingestion failures.Read 15 Oct 2026 · aifoss.dev
- Hybrid search
- The product combines vector search, BM25, custom scoring and reranking for retrieval.Read 15 Oct 2026 · ragflow.io
- Knowledge compilation
- The platform organizes documents into structured knowledge artifacts through knowledge compilation.Read 15 Oct 2026 · ragflow.io
- Limit: learning curve
- An independent review says the workflow builder and retrieval settings take time to learn.Read 15 Oct 2026 · datacamp.com
- Limit: overkill for simple text
- An independent review says DeepDoc can add latency and RAM without retrieval benefit for clean Markdown, code documentation and copyable PDFs.Read 15 Oct 2026 · aifoss.dev
- MCP integration
- RAGFlow can act as an MCP server through /api/v1/mcp and can also connect external MCP servers to its agents.Read 15 Oct 2026 · ragflow.io
- Model integrations
- Documented model providers include OpenAI, Anthropic, Azure OpenAI, Bedrock, Cohere, Gemini, DeepSeek, Ollama, Xinference, LocalAI, Mistral, NVIDIA and OpenAI-compatible endpoints.Read 15 Oct 2026 · ragflow.com.cn
- Model support
- RAGFlow lets users connect online, local, and OpenAI-compatible model providers for knowledge bases, chats, search, and agents.Read 29 Sep 2026 · ragflow.io
- Notable release
- The official blog lists RAGFlow 0.27, featuring knowledge compilation and agentic retrieval, dated August 24, 2026.Read 15 Oct 2026 · ragflow.io
- Platform caveat
- RAGFlow says it tests ARM64 platforms but does not maintain RAGFlow Docker images for ARM; users can build an image themselves on linux/arm64 or darwin/arm64.Read 29 Sep 2026 · ragflow.io
- Praise: document quality
- Independent reviewers repeatedly praise DeepDoc for handling scanned PDFs, tables and complex layouts better than lighter alternatives.Read 15 Oct 2026 · datacamp.com
- Praise: integrated platform
- Independent reviewers praise having parsing, retrieval, citations and workflows in one deployable product instead of assembling separate libraries.Read 15 Oct 2026 · datacamp.com
- Privacy roles
- RAGFlow says it typically acts as a controller for personal data it collects for its own purposes and as a processor or service provider for customer data uploaded to its cloud services.Read 29 Sep 2026 · ragflow.io
- Public API
- The REST API uses bearer API keys and includes document ingestion, chat completion, dataset search and OpenAI-compatible endpoints.Read 15 Oct 2026 · ragflow.io
- Rating on G2
- 0.0 out of 5 from 0 reviews; G2 says there are not enough reviews to provide buying insight.Read 15 Oct 2026 · g2.com
- Repository scale
- The GitHub repository displayed about 92,300 stars, 11,000 forks and 939 open issues when checked.Read 15 Oct 2026 · github.com
- Search
- Its search combines vector search, BM25, custom scoring, and advanced re-ranking.Read 29 Sep 2026 · ragflow.io
- Self-hosting
- RAGFlow is deployed with Docker Compose and can be run on user-controlled infrastructure.Read 15 Oct 2026 · datacamp.com
- System requirements
- The documented starting configuration is four x86 CPU cores, 16 GB RAM and 50 GB free disk.Read 15 Oct 2026 · ragflow.io
Plans and prices
Free Free 5 Apps · 1 team members · 0.1 GB dataset storage · 500 credits / month · API key not available Read 29 Sep 2026 · ragflow.io
Free Free $0 month 5 apps · 1 team member · 0.1 GB dataset storage · 500 credits/month · API key unavailable Read 15 Oct 2026 · ragflow.io
Starter $29 a month $29 month; page also shows $59 month 50 apps · 5 team members · 5 GB dataset storage · 5,000 credits/month · API key available Read 15 Oct 2026 · ragflow.io
Pro $129 a month $129 month; page also shows $259 month Unlimited apps · 20 team members · 50 GB dataset storage · 20,000 credits/month · API key available Read 15 Oct 2026 · ragflow.io
Enterprise Priced on request Contact us BYOC deployment · on-premises deployment · dedicated support · custom SLA Read 15 Oct 2026 · ragflow.io
Strong points and limits
Strong points
- Combines vector search with BM25 and re-ranking.
- Visual workflows integrate RAG, tools, and MCPs.
- Offers HTTP and Python APIs.
- Self-hosted Docker deployment is documented.
Limits
- Free plan has no API key.
- Free plan limits storage to 0.1 GB.
- Docker minimum is 4 CPU cores and 16 GB RAM.
Who it suits
RAGFlow suits teams building retrieval and agent workflows, particularly those needing model-provider choices, documented connectors, or self-hosting. Its listed solutions include financial services, legal and compliance, manufacturing, and education.
Verdict
RAGFlow pairs ingestion, search, and agent workflow tools with cloud and self-hosted options. The free tier is limited to five apps and 500 monthly credits, while Starter costs $29 a month.
Where Specifiction places it
- Retrieval-Augmented Generation Tools#3 of 268.8
Alternatives to RAGFlowAll alternatives →
Dify From $49.17/mo · Free plan 9.4 Visit 
AnythingLLM From $50/mo · Free plan 9.3 Visit 
Azure AI Speech Free plan 8.5 Visit