R2R Hosting Live In 5 Minutes

R2R hosting gives you a self-hosted RAG engine on your own domain: ingest documents, search them and query them through a REST API and a web dashboard. Deploy R2R 3.6.5 with a pgvector Postgres database, a generated administrator login and HTTPS in minutes. It does not work end to end until you add a model provider key in the Environment editor.

Deploy your R2R

No terminal
No technical skills needed
No lock-in, cancel anytime

What is R2R?

R2R is an advanced AI retrieval system that supports retrieval-augmented generation (RAG). Upstream describes a RESTful API with multimodal content ingestion, hybrid search, knowledge graphs and document management, plus a Deep Research API for multi-step answers. A self-hosted R2R is an alternative to a hosted RAG API, with the code under the MIT licence, so the documents sit in your own database rather than a vendor's.

On xCloud it is R2R 3.6.5 with the 1.0.3 dashboard, pgvector on Postgres 16 and an nginx proxy, all pinned by digest, with everything stored in postgres_data. xCloud generates the secrets and the administrator password. Hatchet, Unstructured, MinIO and graph clustering are not included, and uploaded text is sent to the model provider you configure.

From Sign-Up to a Live R2R In Just 3 Easy Steps

A RAG backend needs the API, a dashboard, a vector database, secrets, a proxy, a domain and a certificate before the first document is ingested. This is the same result without assembling any of it.

Step 01
Sign Up
Create your xCloud account and pick R2R from the OneClick catalog. Choose your domain and enter the administrator email; the password is generated for you.
Step 02
We Deploy It For You
One click. We start the R2R 3.6.5 API, the 1.0.3 dashboard, pgvector on Postgres 16 and an nginx proxy, all pinned by digest, generate the secrets and publish them over HTTPS. The first boot takes a few minutes.
Step 03
Add A Model Key And Ingest
Sign in with the administrator email and generated password. Open Environment, uncomment OPENAI_API_KEY or another provider key, then Save and Redeploy. Only then can you ingest documents and search them.

Retrieval-Augmented Generation API: R2R On Your Own Server

R2R runs here with its dashboard and database, and every request needs a login. The models come from the provider you configure.

REST API For Retrieval
Upstream is built around a RESTful API for search, RAG answers and agents, documented at /docs on your own domain.
Document Ingestion
Ingest content into Postgres, where documents, chunks, vectors, users and uploaded files are stored. Uploads are capped at 1 GB by the proxy.
Hybrid Search
Search combines vector and full-text queries, using pgvector in the bundled Postgres rather than a separate vector database.
Agents And Deep Research
Upstream lists a Deep Research API that does multi-step reasoning over your knowledge base. It needs a configured model provider.
Web Dashboard
Use the R2R dashboard to sign in, manage documents and try retrieval without writing client code.
Login On Every Route
Stock R2R lets anyone call the API as an administrator. This template requires authentication, and only signed-in users can create more accounts.

Everything You Need To Run Your RAG 24/7

Managed hosting for R2R, so the parts that keep it online are not your problem.

R2R 3.6.5 deployed instantly
Images pinned by digest
Administrator login generated
Authentication required on the API
Free SSL certificate
Everything in Postgres on a persistent volume
Server backups and snapshots
30+ server locations
Unused balance refunded

What You Can Do With R2R

Answer questions from your own documents
Ingest manuals or policies and query them with RAG over the documents you supplied.
Give an app a retrieval backend
Call the REST API from your own code for search and RAG instead of writing a vector store layer.
Keep source documents on your server
Store files, chunks and vectors in your own Postgres, with the model provider seeing only what is sent for embedding and answers.
Try agents over a knowledge base
Use the agent endpoints, once a provider key is set, to experiment with multi-step answers.

R2R vs Alternatives

Hosted RAG APIs: As a self-hosted alternative to hosted RAG APIs, R2R keeps documents, chunks and vectors in your own Postgres, behind a login on your domain.
RAGFlow: RAGFlow has its own OneClick page. In an R2R vs RAGFlow comparison, R2R is API-first with a dashboard, so compare ingestion options, interfaces and services each one needs.
AnythingLLM: AnythingLLM has its own OneClick page. It is another self-hosted tool for chatting with your documents, so compare how each handles ingestion and models.
Qdrant: Qdrant has its own OneClick page. R2R stores vectors with pgvector in its own bundled Postgres, so compare that with running a separate vector database.

Simple Pricing. Everything Included.

Dedicated Cloud VPS sizes, pre-configured for R2R hosting. Pick the one that fits, and resize any time.

Cloud VPS 6 GB

Cloud VPS 16 GB

Already Have a Server? Bring Your Own

Connect any VPS — DigitalOcean, Vultr, Linode, AWS, Hetzner or bare metal — and deploy R2R on it through the same panel, for a per-server management fee instead of a Cloud VPS rental.

Free

Start your journey without cost.

$0forever

1 server
10 sites

Start free

Starter

Professional

The same platform, discounted at 6–10 servers.

$4per server / month

6–10 servers
Unlimited sites
All features included
Bring any VPS provider

Get started

Agency

The same platform, discounted at 11+ servers.

$3per server / month

11+ servers
Unlimited sites
All features included
Bring any VPS provider

Get started

Priced per connected server, so your rate adjusts automatically as you add or remove servers. You pay your own provider for the server itself.

Self-managed hosting

Ready To Run Your Own RAG Engine?

R2R on xCloud runs on a dedicated Cloud VPS that we provision, patch, monitor and restore. Your documents, your database, your domain.

Fast Provisioning
Deploy faster using an xCloud Managed Server built with optimized stacks and high-speed SSDs.
Enterprise-grade security
Protect your infrastructure with a free SSL certificate and more advanced security features at no additional cost.
Intuitive Control Panel
From Server creation to application deployment, everything can be managed from our intuitive control panel.

Hear what people are saying about us

See why agencies, developers, startups, and growing businesses choose xCloud to power their projects.

xCloud works really well, I am surprised by its performance being this the release version, I have tried many paid platforms such as runcloud, cloudpages or serveravatar, as well as free platforms such as CyberPanel, CloudPanel or Hestia Control Panel and direct competitors such as SpinupWP and FlyWP. Of all those that I have tried, the platform that works best for WordPress is SpinupWP and I believe that xCloud can reach and surpass that development, its roadmap is promising. Congratulations to the xCloud team, I hope they become the leading platform in the segment, it has all the potential to achieve it!

Brian Geovanny

I've been with runcloud for the last 3 years. However, after trying xcloud for the last month, I'm switching over. They are on a roll with their setup.

Kevin Pineda

I'm moving my servers to xCloud, a cloud control panel by M Asif Rahman and the WPDeveloper team. Their roadmap looks interesting and no, there are no team mates nor API limits with xCloud! #xCloud #wordpress #hosting

Leo Koo

How Cloud Nine Web Elevated Client Experience While Streamlining Hosting Operations using xCloud

Ed Ellingham

xCloud is like having an expert server team on call — without the big agency costs. It's given me back my time and given my clients peace of mind. Highly recommended for freelancers and small teams who want reliable performance and security.

Dumitru Butucel

xCloud isn't just a solution. It's like one of that friend who got your back when you screw things up pretty bad.

Waqar Ahmed

Trust me when I say, once people explore the potential of xCloud they gonna switch from other panels, just keep delivering the best tech, lots of love for the team 😍😍

Rahul Singh

So far my experience has been smooth like silk. I didn't imagine that configuring and managing a VPS would be so easy. As of today, I have deployed 8 sites. The support is good, and they treat users with respect, even if they ask stupid questions (myself included). For the future, I hope for greater flexibility in scheduled backups and more comprehensive and consistent documentation. I'm sure that within a few months, xCloud will become the leader in its segment. This community is amazing, and the Staff here is super helpful.

Massimo Villa

Came from cloudways then to runcloud then to xcloud. Looks like I'm staying here.

Gerson El

I've recently taken all of my Vultr-hosted sites and gotten rid of cPanel for them to substitute it with xCloud. I have to say, I'm really impressed with xCloud so far! The interface is definitely the standout feature for me.

Tony Lewis

I came from Cloudways and won't go back. Highly impressed with xCloud. Glad I gave them a chance.

Jared McDowell

I like xCloud better than RunCloud, but one thing I'll point out is that some years ago RunCloud was hungry for business, the support was outstanding, and the community was active and helped each other. Maybe it was sold, there was a change in management, or they stopped being hungry, but the quality of the RunCloud offering declined and it hasn't been moving forward quickly. My point is that currently the xCloud team has the edge and it is theirs to keep or lose

David McCan

How Kevin Heinrichs Cut Hosting Costs by 84% While Running WooCommerce & Node.js Sites Efficiently

Kevin Heinrichs

I had 150 sites on cloudways and am in the process of moving them to xcloud. Much faster and better priced.

Dan Spinoza

Dear xCloud Team, I have been using xCloud for some time now and am genuinely impressed with its capabilities and the flexibility it offers by allowing users to bring their own VPS for management. It's a fantastic service, and my experience so far has been very positive. Successful migrated 5 sites on a single server. Xcloud migration tool worked great. There were few hiccups with security plugin like MalCare but disabling the plugin prior to migration worked just fine.

Rahil Maknojia

Came from runcloud. Tried xcloud and never came back.

Karl Fanega

How Advanced Web Strategies Saved Over $2,000 & Recovered 56 Hours per Month Managing 70+ Client Websites

Gary Moody

xCloud gave me what no other hosting platform could: the flexibility of a VPS with the convenience of managed WordPress. As a solo founder running an entire business on one server, that combination is an important unfair advantage.

Jorge de los Reyes Martínez

I use Server Avatar and xCloud and I'll sooner use xCloud than Server Avatar personally.

Jay Pagano

How Newman Web Solutions Ensured Perfect Uptime and Seamless Scaling For 120+ WordPress Sites with xCloud

Lori Newman

I too have moved over to xCloud. It's pretty sweet. One click n8n and uptime Kuma apps

John Aperture

I went from Cloudways to xCloud. No intention on switching in the foreseeable future.

Blaine Moore

Frequently Asked Questions

Feel free to contact us with any questions or concerns you may have.

Does R2R work right after install?

No. Ingestion and search need a model provider. Open Environment, uncomment OPENAI_API_KEY or another provider key, fill it in, then Save and Redeploy the site. The defaults are OpenAI text-embedding-3-small, gpt-4.1 and gpt-4.1-mini, so an OpenAI key works first.

Which LLM providers does R2R use?

The template defaults to OpenAI models, and you can set another provider key in the Environment editor, then redeploy so R2R reads it. Documents you upload are stored in Postgres and sent to the configured provider for embeddings and answers.

Can you self-host R2R with Docker?

Yes. Upstream deploys with Docker, and this template is R2R Docker hosting without the setup: the API, dashboard, pgvector Postgres and nginx proxy pinned by digest, one data volume and HTTPS on your own domain.

How much RAM does R2R need?

The manifest asks for 2048 MB of RAM, 2 CPU cores and 20 GB of disk. The 6 GB plan covers that, and document volume, embedding batches and database size are what grow it over time.

Does R2R support hybrid search and knowledge graphs?

Upstream lists hybrid search and knowledge graphs. This template does not include the graph clustering service, Hatchet, Unstructured or MinIO, so graph community building is unavailable and ingestion runs inside the R2R process itself, so large jobs share its memory.

Is my R2R API protected?

Yes. Stock R2R lets anyone call the API as an administrator, so this template sets require_authentication to true. Every dashboard page and API call needs a login, and only signed-in users can create more accounts.

Is R2R open source?

Yes. R2R is published under the MIT licence, so the engine is free to use. You pay for the Cloud VPS that hosts it, which makes this an R2R cloud of your own, plus whatever your chosen model provider charges for tokens.

Does R2R send emails?

No. No mail provider is configured, so account emails such as verification and password reset are written to the container logs only, never delivered. Change the administrator password from the dashboard instead of editing the environment.

How do I back up R2R?

All state lives in the postgres_data volume. Stop the stack and archive it, or run pg_dump against the Postgres container for an online copy. Keep off-server copies, and test a restore into a spare install.

Backup and restore Docker apps

How do I upgrade R2R?

The install stays on its pinned 3.6.5 images until you adopt a newer template version. Back up postgres_data first and read the upstream release notes. Nothing upgrades automatically, and database passwords apply only to a fresh volume.

Can I cancel anytime?

Yes. There is no lock-in — cancel any time. Hosting is billed monthly and charged for what you actually use, so when you delete the server the unused balance is refunded to your account, less up to 10% in payment-processing fees.