Freedom251 › LLM Application Development Frameworks
OpenRAG
What OpenRAG is
OpenRAG is a free, AGPL-3.0 framework for building systems that answer questions using documents as their grounding. Its search combines semantic retrieval with BM25 keyword matching and multilingual reranking. Answers cite a document and page, with links that open at the cited location. It handles 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. Access controls include isolated partitions, owner, editor and viewer roles, and token or OpenID Connect authentication. OpenRAG can run on infrastructure controlled by the deployer, keeping documents, embeddings and queries within that perimeter. Deployment requires Docker, Docker Compose and at least 16 GB RAM; a CPU-only profile is optional. 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. The maker says the self-hosted edition has no features held back.
Who it suits
It suits teams building document-grounded assistants, legal search or multimodal enterprise question answering, including organizations that want to control deployment infrastructure. Be prepared to meet the listed Docker and memory prerequisites.
What it does well
- Free self-hosted edition under AGPL-3.0.
- Answers link to cited document pages.
- Supports hybrid search and reranking.
- Can keep data within deployer-controlled infrastructure.
What to know first
- Requires Docker and Docker Compose.
- Minimum listed memory is 16 GB.
- CSV, ODT and HTML support are coming soon.
- Encryption in transit and at rest is coming soon.
Limits
The free self-hosted edition has no features held back. CSV, ODT, and HTML support, tool calling, agentic RAG, MCP, and encryption in transit and at rest are listed as coming soon.
Plans
| Plan | Billed and limits | Price |
|---|---|---|
| OpenRAG (AGPL-3.0 self-hosted) | AGPL-3.0 · deploy on your own infrastructure · no feature held back | Free |
| Managed OpenRAG service | 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 | On request |
As open-rag.ai lists them, read 3 Oct 2026. The maker's own page has the final word.
Getting started
- Visit the OpenRAG website.
- Prepare Docker and Docker Compose on the infrastructure where you will deploy it.
- Provide at least 16 GB RAM, or use the optional CPU-only profile.
- Deploy the free AGPL-3.0 edition on your own infrastructure.
- Connect your own model or use a hosted provider.
- Use the admin console, chat interface, or OpenAI-compatible API.
Verdict
OpenRAG combines document retrieval, source-linked answers and self-managed deployment in a free framework. Its listed deployment prerequisites and features marked as coming soon are important considerations before adoption.
Questions
How much does self-hosted OpenRAG cost?
The AGPL-3.0 self-hosted plan is free.
Is there a free plan?
Yes. The self-hosted edition is free and has no features held back.
What platforms are available?
OpenRAG is available through web, API, and self-hosted deployment.
Is OpenRAG open source?
Yes. The self-hosted edition is licensed under AGPL-3.0.
Which models can it use?
Users can connect models including Mistral, Qwen, Lucie, Claude, and GPT, or use a hosted provider.
What does the managed service cost?
No fixed price is listed. Pricing is set during scoping and can be usage-based or fixed-fee depending on deployment mode.
Facts from OpenRAG's own pages
- Access control
- Partitions isolate knowledge bases; partition roles include owner, editor and viewer, and API tokens are stored as SHA-256 hashes. · open-rag.ai, 3 Oct 2026
- Access controls
- It supports partition isolation, owner/editor/viewer roles, and token or single sign-on authentication through OpenID Connect providers. · open-rag.ai, 2 Oct 2026
- Answers
- Answers cite the source document and page, with a link that opens the cited page. · open-rag.ai, 3 Oct 2026
- Audience
- The site describes use for AI assistants, legal search and multimodal enterprise question answering, and says public administrations and private companies use it. · open-rag.ai, 3 Oct 2026
- Commercial offering
- The maker says there is no paid edition and no feature held back; it also links to a LINAGORA-managed service. · open-rag.ai, 2 Oct 2026
- 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. · open-rag.ai, 3 Oct 2026
- Deployment and data
- OpenRAG runs on infrastructure controlled by the deployer, keeping documents, embeddings, and queries within that perimeter. · open-rag.ai, 2 Oct 2026
- Deployment requirements
- The maker lists Docker and Docker Compose as prerequisites, with 16 GB RAM minimum and an optional CPU-only profile. · open-rag.ai, 2 Oct 2026
- Document handling
- It supports multimodal parsing including PDF layout awareness, OCR, image captioning, and audio transcription. · open-rag.ai, 2 Oct 2026
- Document processing
- It supports multimodal parsing with audio transcription, image captioning, OCR and PDF layout awareness. · open-rag.ai, 3 Oct 2026
- Founded
- 2000 · open-rag.ai, 28 Sept 2026
- Integrations
- The product documents compatibility with OpenAI API clients and names Open WebUI, LangChain, n8n and Twake.ai as integrations. · open-rag.ai, 3 Oct 2026
- Interfaces
- The product includes an admin console, a chat interface, and an OpenAI-compatible API. · open-rag.ai, 2 Oct 2026
- License
- OpenRAG is licensed under AGPL-3.0. · open-rag.ai, 2 Oct 2026
- Model choice
- The site says users can connect their own models, including Mistral, Qwen, Lucie, Claude and GPT, or use a hosted provider. · open-rag.ai, 3 Oct 2026
- 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. · open-rag.ai, 3 Oct 2026
- 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. · open-rag.ai, 2 Oct 2026
- Product
- OpenRAG is a modular framework for building document-grounded retrieval-augmented generation systems. · open-rag.ai, 3 Oct 2026
- Purpose
- OpenRAG is a modular framework for building document-grounded retrieval-augmented generation systems. · open-rag.ai, 2 Oct 2026
- Scaling
- Ray distributes ingestion, chunking and embedding across worker nodes for horizontal scaling. · open-rag.ai, 3 Oct 2026
- Search
- Retrieval combines semantic search with BM25 keyword matching and multilingual reranking. · open-rag.ai, 3 Oct 2026
- Search and scale
- It supports hybrid search, reranking, and distributed processing with Ray worker nodes. · open-rag.ai, 2 Oct 2026
- Security
- The site describes fail-closed scopes, verified outbound connections, redacted secrets, non-root containers, rate limiting and security headers. · open-rag.ai, 3 Oct 2026
- Support
- The product site directs technical questions to GitHub issues and links to documentation and a contact form. · open-rag.ai, 3 Oct 2026