OpenRAG
OpenRAG is a free, AGPL-3.0 modular framework for building document-grounded retrieval-augmented generation systems.
What OpenRAG is
OpenRAG is a free, AGPL-3.0 modular framework for building document-grounded retrieval-augmented generation systems. Its search combines semantic retrieval, BM25 keyword matching, and multilingual reranking; answers cite a source document and page, with links to the cited location. It processes 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/viewer roles, and 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 perimeter. Deployment prerequisites are Docker, Docker Compose, and at least 16 GB 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.
Good
- Free AGPL-3.0 self-hosted edition has no features held back.
- Answers cite documents and pages with source links.
- Search combines semantic retrieval, BM25, and reranking.
- Partition roles and token or OpenID Connect authentication are supported.
Watch out
- Deployment requires Docker, Docker Compose, and at least 16 GB RAM.
- CSV, ODT, and HTML support are coming soon.
- Encryption in transit and at rest is coming soon.
- Tool calling, agentic RAG, and MCP are coming soon.
Who it suits
OpenRAG may suit teams building document-grounded assistants, legal search, or multimodal enterprise question answering. It is aimed at deployers able to provide the listed infrastructure and manage their own deployment.
Verdict
OpenRAG offers document citations, hybrid search, and self-hosting with access controls. Its listed deployment requirements and features marked as coming soon are important considerations before adopting it.
Plans and prices
From OpenRAG's own pricing page, checked 3 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| OpenRAG (AGPL-3.0 self-hosted) | Free | AGPL-3.0 · deploy on your own infrastructure · no feature held back |
| Managed OpenRAG service | Priced on request | Usage-based or fixed-fee billing depending on deployment mode · short, renewable commitment periods · Price schedules established during scoping, according to deployment mode and volume. |
The facts
Each one read from OpenRAG's own pages, with the date it was checked.
What it does
- Access control
- Partitions isolate knowledge bases; partition roles include owner, editor and viewer, and API tokens are stored as SHA-256 hashes.checked 3 Oct 2026
- Access controls
- It supports partition isolation, owner/editor/viewer roles, and token or single sign-on authentication through OpenID Connect providers.checked 2 Oct 2026
- Answers
- Answers cite the source document and page, with a link that opens the cited page.checked 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.checked 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.checked 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.checked 3 Oct 2026
- Deployment and data
- OpenRAG runs on infrastructure controlled by the deployer, keeping documents, embeddings, and queries within that perimeter.checked 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.checked 2 Oct 2026
- Document handling
- It supports multimodal parsing including PDF layout awareness, OCR, image captioning, and audio transcription.checked 2 Oct 2026
- Document processing
- It supports multimodal parsing with audio transcription, image captioning, OCR and PDF layout awareness.checked 3 Oct 2026
- Integrations
- The product documents compatibility with OpenAI API clients and names Open WebUI, LangChain, n8n and Twake.ai as integrations.checked 3 Oct 2026
- Interfaces
- The product includes an admin console, a chat interface, and an OpenAI-compatible API.checked 2 Oct 2026
- License
- OpenRAG is licensed under AGPL-3.0.checked 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.checked 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.checked 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.checked 2 Oct 2026
- Product
- OpenRAG is a modular framework for building document-grounded retrieval-augmented generation systems.checked 3 Oct 2026
- Purpose
- OpenRAG is a modular framework for building document-grounded retrieval-augmented generation systems.checked 2 Oct 2026
- Scaling
- Ray distributes ingestion, chunking and embedding across worker nodes for horizontal scaling.checked 3 Oct 2026
- Search
- Retrieval combines semantic search with BM25 keyword matching and multilingual reranking.checked 3 Oct 2026
- Search and scale
- It supports hybrid search, reranking, and distributed processing with Ray worker nodes.checked 2 Oct 2026
- Security
- The site describes fail-closed scopes, verified outbound connections, redacted secrets, non-root containers, rate limiting and security headers.checked 3 Oct 2026
- Support
- The product site directs technical questions to GitHub issues and links to documentation and a contact form.checked 3 Oct 2026
The company
- Founded
- 2000checked 28 Sep 2026
Alternatives to OpenRAG
- 1
Vellum
Free planOpen sourceAndroidiOSWebAPI8.7From $30 a month - 2
Scanopy
Free planOpen sourceWebAPILinuxmacOS8.3Free plan - 3
Flowise
Free planWebAPILinuxmacOS7.2From $35 a month - 4
LlamaIndex
Free planWebAPILinuxSelf-hosted7.1From $50 a month - 5
Vercel
Free planWebAPI7.0$20 usage-based - 6
LangChain
Free planAPISelf-hosted6.8$39 usage-based