GDPR-compliant RAG chatbot
you actually own

A RAG chatbot that processes documents and generates answers while meeting EU GDPR requirements: data residency controls, deletion cascades across all storage layers, audit logging, consent management, and the ability to run entirely on EU infrastructure without US data transfers. With Strict EU mode enabled (the default), non-compliant providers are blocked before data leaves your server.

EuroRAG builds GDPR compliance into the architecture: Article 17 erasure across vector stores, per-provider data residency tracking, audit logging, and Strict EU Mode that blocks non-compliant providers. Other tools treat compliance as a deployment-time choice. EuroRAG is also a boilerplate (source code you customize), whereas AnythingLLM is a ready-to-use application and LangChain is a library for building pipelines from scratch.

Nothing changes with your deployment. Your version of EuroRAG continues to work exactly as it does today. It's yours permanently. You just won't receive new features, compatibility patches, or security updates until you renew. Renewal is the same price whether you renew the day after expiry or two years later. No late fees, no penalty for gaps.

EuroRAG gives you the technical infrastructure for GDPR compliance: data residency tracking, deletion cascades across all storage layers, audit logs, consent management, and the ability to run everything locally or on EU servers. However, GDPR compliance also involves organizational measures (privacy policies, DPAs, etc.) that depend on your specific use case. We provide the tools; you'll still need legal review for your deployment.

Any model that runs on Ollama (Mistral, Llama 3, Qwen, Gemma, etc.) for fully local inference. Any OpenAI-compatible API for cloud: EU-hosted options include Mistral, Scaleway, OVHcloud, IONOS, and Gcore (all EU-headquartered, no US CLOUD Act exposure). OpenAI, Groq, and Together AI also work but are blocked by default under Strict EU mode. Or self-hosted inference servers like vLLM or LocalAI. Switch providers by changing environment variables - no code changes needed. The included infrastructure guide helps you pick the right setup for your budget and privacy requirements.

PDF, DOCX, PPTX, XLSX, CSV, HTML, TXT, and Markdown. Document processing is powered by IBM Docling, which handles table-aware extraction (preserves table structure from PDFs and spreadsheets) and OCR for scanned documents. All processing happens on your server. Document content is never sent to external services.

Data source connectors for automated syncing from folders, web crawlers, Nextcloud, and databases are included in the Professional tier. The Starter tier supports document upload through the API and UI, which covers most use cases for getting started. If you need automated ingestion from external sources, the Professional tier adds these connectors along with admin tools.

Probably not. EuroRAG is source code, a boilerplate for developers and agencies building RAG products. You need to be comfortable with Python, Docker, and basic server administration. If you want a ready-to-use app, AnythingLLM might be a better fit.

React is powerful, but it means your team needs JavaScript expertise, a Node.js build pipeline, and a separate frontend deployment. EuroRAG uses Jinja2 templates + HTMX, which means the same Python developer who writes the API can also modify the UI. For a boilerplate you're meant to customize, this is a significant advantage.

They're different products for different goals. ChatRAG ($199 Starter / $269 Complete) and StartKit.AI ($199–399, one-time perpetual license) are built on Next.js/Node.js and designed for building chatbot SaaS businesses with Stripe billing and cloud infrastructure. EuroRAG is for building private, self-hosted knowledge bases on your own server with GDPR compliance built into the architecture. If you need SaaS monetization and cloud deployment, look at ChatRAG. If you need data sovereignty and a Python stack, EuroRAG is the fit.

Yes, except for LLM inference. The application itself (FastAPI, hybrid search, ChromaDB, document processing, even the embedding model) runs comfortably on a 2 vCPU / 4GB EU VPS (Hetzner CX22, ~€7/mo). Chat inference is the only heavy part, and you have two options: an EU-hosted API like Mistral or Scaleway (pay per token, typically €3–10/mo at small-team usage), or your own GPU server running Ollama if you want zero external calls. Realistic all-in for a production deployment on EU infrastructure: €8–16/mo. The included deployment guide walks through each setup with exact steps and current prices.

Yes. EuroRAG works with any language your chosen LLM supports, and ships with configuration guidance for multilingual embedding models like BGE-M3 and Qwen3-Embedding that handle EU languages well. Since there's no hardcoded English dependency in the pipeline, you can run it entirely in German, French, or any other language.

The Starter and Professional tiers are available now. The Enterprise tier launches Fall 2026. Join our newsletter below to get notified the moment it ships. We send occasional updates about new features, security patches, and deployment guides.

Since the product is complete source code, it can't be returned after download, so we don't offer refunds. By purchasing EuroRAG, you request immediate access to the private repository and acknowledge that you lose your 14-day right of withdrawal under EU Directive 2011/83/EU Article 16(m) once repository access is granted. If you have questions before purchasing or want to see specific code examples, get in touch. We're happy to help you decide if EuroRAG is the right fit.

Yes. Under your single license you may build and deploy an unlimited number of applications for your clients, with no per-client or per-project fee, provided you never provide the Software source code to any third party, including your clients. Your clients receive the deployed application only, and never receive the Software source code as a development starting point. This license does not transfer to your clients.

At checkout you provide your GitHub username, and you're invited to the private repository automatically, typically within a minute of payment. Clone, configure your .env, and docker compose up. Prefer not to use GitHub? We'll send a download instead; just reply to your purchase email.

The full repository is private, but we're happy to share specific examples: how the deletion cascade works, what a connector implementation looks like, how the template override system is structured. Get in touch with what you'd like to see. The architecture documentation shipped with the product is generated and verified against the actual code, so what's described is what you get.

Checkout handles this automatically. EU businesses with a valid VAT ID are reverse-charged (no VAT added; you account for it locally). You'll receive a compliant invoice by email after purchase. We're an EU (Lithuanian) entity, so cross-border EU purchases are straightforward for your accounting.