Skip to content
SPECIFICTION
Get listed

OpenRAG

open-rag.ai

Free plan WebAPISelf-hosted
Visit open-rag.ai
Spec score 8.3 #5 of 49 in LLM Application Development Frameworks

What it is

OpenRAG is a modular framework for building systems that answer questions using documents as their grounding. Its retrieval combines semantic search with BM25 keyword matching and multilingual reranking; answers cite a source document and page, with links to the cited location. Document processing covers listed text, office, email, audio, video, and image formats, with PDF layout awareness, OCR, image captioning, and audio transcription. The product includes an admin console, chat interface, and OpenAI-compatible API, and can connect to user-provided models or a hosted provider. Partition isolation, owner, editor, and viewer roles, plus token or OpenID Connect authentication, are among its access controls. It can run on infrastructure controlled by the deployer, keeping documents, embeddings, and queries within that environment. The self-hosted AGPL-3.0 edition is listed at free. Deployment prerequisites are Docker, Docker Compose, and at least 16 GB of RAM; a CPU-only profile is optional. CSV, ODT, and HTML support, tool calling, agentic RAG, MCP, and encryption in transit and at rest are listed as coming soon.

Spec sheet

Purpose
OpenRAG is a modular framework for building document-grounded retrieval-augmented generation systems.Read 2 Oct 2026 · open-rag.ai
Product
OpenRAG is a modular framework for building document-grounded retrieval-augmented generation systems.Read 3 Oct 2026 · open-rag.ai
Audience
The site describes use for AI assistants, legal search and multimodal enterprise question answering, and says public administrations and private companies use it.Read 3 Oct 2026 · open-rag.ai
Integrations
The product documents compatibility with OpenAI API clients and names Open WebUI, LangChain, n8n and Twake.ai as integrations.Read 3 Oct 2026 · open-rag.ai
Security
The site describes fail-closed scopes, verified outbound connections, redacted secrets, non-root containers, rate limiting and security headers.Read 3 Oct 2026 · open-rag.ai
Support
The product site directs technical questions to GitHub issues and links to documentation and a contact form.Read 3 Oct 2026 · open-rag.ai
License
OpenRAG is licensed under AGPL-3.0.Read 2 Oct 2026 · open-rag.ai
Founded
2000Read 28 Sep 2026 · open-rag.ai
Access control
Partitions isolate knowledge bases; partition roles include owner, editor and viewer, and API tokens are stored as SHA-256 hashes.Read 3 Oct 2026 · open-rag.ai
Access controls
It supports partition isolation, owner/editor/viewer roles, and token or single sign-on authentication through OpenID Connect providers.Read 2 Oct 2026 · open-rag.ai
Answers
Answers cite the source document and page, with a link that opens the cited page.Read 3 Oct 2026 · open-rag.ai
Commercial offering
The maker says there is no paid edition and no feature held back; it also links to a LINAGORA-managed service.Read 2 Oct 2026 · open-rag.ai
Compliance and hosting
OpenRAG can run on customer infrastructure or hosting qualified SecNumCloud; the site says traceable answers and auditable code provide evidence relevant to GDPR and the AI Act, with obligations remaining with the deployer.Read 3 Oct 2026 · open-rag.ai
Deployment and data
OpenRAG runs on infrastructure controlled by the deployer, keeping documents, embeddings, and queries within that perimeter.Read 2 Oct 2026 · open-rag.ai
Deployment requirements
The maker lists Docker and Docker Compose as prerequisites, with 16 GB RAM minimum and an optional CPU-only profile.Read 2 Oct 2026 · open-rag.ai
Document handling
It supports multimodal parsing including PDF layout awareness, OCR, image captioning, and audio transcription.Read 2 Oct 2026 · open-rag.ai
Document processing
It supports multimodal parsing with audio transcription, image captioning, OCR and PDF layout awareness.Read 3 Oct 2026 · open-rag.ai
Interfaces
The product includes an admin console, a chat interface, and an OpenAI-compatible API.Read 2 Oct 2026 · open-rag.ai
Model choice
The site says users can connect their own models, including Mistral, Qwen, Lucie, Claude and GPT, or use a hosted provider.Read 3 Oct 2026 · open-rag.ai
Notable limit
CSV, ODT and HTML support, format-specific chunkers, tool calling, agentic RAG, MCP, and encryption in transit and at rest are listed as coming soon.Read 3 Oct 2026 · open-rag.ai
Notable limits
The maker lists CSV, ODT, and HTML support, tool calling, agentic RAG, MCP, and encryption in transit and at rest as coming soon.Read 2 Oct 2026 · open-rag.ai
Scaling
Ray distributes ingestion, chunking and embedding across worker nodes for horizontal scaling.Read 3 Oct 2026 · open-rag.ai
Search
Retrieval combines semantic search with BM25 keyword matching and multilingual reranking.Read 3 Oct 2026 · open-rag.ai
Search and scale
It supports hybrid search, reranking, and distributed processing with Ray worker nodes.Read 2 Oct 2026 · open-rag.ai
Supported formats
The listed formats are txt, md, pdf, docx, doc, pptx, eml, wav, mp3, mp4, ogg, flv, wma, aac, png, jpeg, jpg and svg.Read 3 Oct 2026 · open-rag.ai

Plans and prices

OpenRAG (AGPL-3.0 self-hosted) Free AGPL-3.0 · deploy on your own infrastructure · no feature held back Read 3 Oct 2026 · open-rag.ai
Managed OpenRAG service Priced on request Price schedules established during scoping, according to deployment mode and volume. Usage-based or fixed-fee billing depending on deployment mode · short, renewable commitment periods Read 3 Oct 2026 · linagora.ai

Every OpenRAG plan and price →

Strong points and limits

Strong points

  • Answers cite documents and pages
  • Combines semantic and BM25 search
  • Includes an OpenAI-compatible API
  • Self-hosted edition is listed at free

Limits

  • Requires at least 16 GB RAM
  • CSV, ODT, and HTML support is coming soon
  • Encryption in transit and at rest is coming soon
  • Tool calling and agentic RAG are coming soon

Who it suits

OpenRAG suits teams building document-grounded assistants, legal search, or multimodal enterprise question answering. It requires Docker, Docker Compose, and at least 16 GB RAM for deployment.

Verdict

OpenRAG combines cited answers, multimodal document processing, and self-hosted deployment under AGPL-3.0. Check its deployment requirements and the listed coming-soon capabilities against your needs.

Where Specifiction places it

Alternatives to OpenRAGAll alternatives →