New in v1.1.0The mobile app is out of Beta and included in every edition — iOS and Android, signed in to your own instance.Read the announcement

Platform Platform overviewSee it in actionAI SearchAI AssistantAI Connectors & MCPIntegrationsQuality LoopAdministration & SecurityMobile app
Solutions IT & Platform teamsCompliance & Data ProtectionDevelopersAgencies & Partners
Sovereignty
References
Pricing
Resources Trust CenterEU AI ActSecurity & disclosureFree toolsOpen source & open coreDocumentation ↗API reference ↗GitHub ↗ReferencesBlogChangelog
Company AboutPartnersContact
Search See it live Book a demo
Solutions · IT & platform teams

A self-hosted AI platform your team runs — not one more SaaS dependency.

Stand it up on your own infrastructure in minutes, connect the sources you already have, and keep cost to one predictable annual invoice. Transparent per-seat pricing, no phone-home, no lock-in.

Self-host guide →
Deploy in minutes, not months

Three commands. Your own server.

The install is a published, open-source CLI — read it on npm before you run it. RAGSuite stands up on your own infrastructure in minutes, not a year-long integration project. Native by default, Docker if you prefer, and open core means no lock-in — your data stays yours, exportable anytime.

admin@your-server: ~
Plays once on scroll · static under reduced-motion
Integrate

Your sources, your models, your stack.

Crawl and upload, connect Gmail and an open MCP, and run OpenAI, Anthropic, Mistral, Gemini or fully local Ollama — on FastAPI, PostgreSQL, Redis and a vector store you operate.

your-domain.de / connectors
SharePoint
Slack
Confluence
Google Drive
Notion
Gmail
Crawl & upload
MCP server
MCP client
Predictable

One invoice. Per seat. In EUR.

The Enterprise Edition is €25 per user a month, billed annually, and lower per seat at volume. The same rate as your team grows, no metering surprises, and every rate published to the top of the ladder — the cost your finance team can sign off without a sales call. Community is free with unlimited users.

Search result on your servers
"Which clauses limit our liability under the new contract?"
Liability is capped at the total fees paid in the prior 12 months 1, and the cap does not apply in cases of gross negligence 2.
1 vertrag-2026.pdf · S. 12
2 agb.example.eu/haftung
No data left the building · 4 sources checked
What your team gets

Operable from day one.

Install with one CLI

npm install -g @ragsuite/ragsuite, then ragsuite init and ragsuite start — live on your own server, no year-long integration project.

minutes

REST API & webhooks

Keys you create, reveal and revoke; endpoints for search and retrieve; webhooks for events.

API-first

System health & 2FA

Live health for Gateway, PostgreSQL, Redis and the vector store; 2FA and session management.

Community

RBAC & SSO

SAML/OIDC and role-based access across organisation, teams and users when you scale.

Enterprise

See it running on a setup like yours · take the tour →

Stand it up in minutes, on your own server. No data left the building.
How RAGSuite deploys
FAQ

For IT teams, answered

What does it take to run?

A Linux, macOS or WSL2 host with Node 18+, plus PostgreSQL and Redis. The open-source CLI brings the whole stack — FastAPI, PostgreSQL, Redis and a vector store — up on infrastructure you control, natively by default or under Docker if you prefer.

Can we keep everything on-premise?

Yes. With local models via Ollama and offline licence keys, RAGSuite needs no outbound internet at all.

How is cost structured?

Two editions: Community is free with unlimited users; the Enterprise Edition is €25/user/month, billed annually, and lower per seat at volume. No metering surprises, and every rate published to the top of the ladder. See pricing.

Which models can we use?

OpenAI, Anthropic, Mistral, Gemini, or fully local via Ollama — your keys, your data, never used to train another model.

Reference
“For a Mittelstand client in Saxony, “where does the data go?” is the first question. With RAGSuite the answer is: nowhere.”
Susann Thelemann · level.pro · Dresden
Read the case study →
1–5
crawl depth
Local
LLMs via Ollama
0
data egress
Citations
on every result

All references →

Mihaela Angelova, Delivery & Onboarding
Mihaela Angelova
Delivery & Onboarding

Self-host an AI platform your ops team trusts.

Native or Docker, API-first, versions pinned, backup/DR documented. We’ll help you stand it up.

Founding-customer programme open now — own your AI, on your own infrastructure.
Read the docs →