RemarkableCloud

Managed LibreChat VPS hosting

LibreChat, live in minutes.
On a server that is yours alone.

A private ChatGPT-style interface for every major model provider. One clean UI, your API keys, your conversation history on your server.

  • 500% SLA
  • 30-day money-back
  • Free Daily Snapshots
  • Firewall & IDS

What it is

LibreChat is the private, self-hosted ChatGPT alternative: one clean chat interface that speaks to OpenAI, Anthropic, Google, and local models through your own API keys. Conversations, prompts, and search history live in your database, not on someone else's analytics dashboard.

Minimum RAM

4 GB

Fits on SC-4GB; SC-8GB is the comfortable pick with room to stack.

What we install

Our playbook deploys the official Docker Compose stack (LibreChat, MongoDB, Meilisearch) with HTTPS issued and forced, registration locked to you, and the env prepared for your API keys. Add keys, invite your people, done.

Every plan includes

Instant hostname with TLS, database created and wired, daily snapshots, firewall and IDS. Add Fully Managed anytime and our engineers run the whole server for you.

Pick your server

Choose a plan for LibreChat.

LibreChat needs at least 4 GB of RAM. Every plan is your own private VPS, and the same server runs as many apps as fit.

SC-4GB

$16 /mo
  • 2 vCPU
  • 4 GB RAM
  • 100 GB NVMe
  • 10 TB transfer
  • Full Root Access
  • Non-Oversold Cores
  • 100% NVMe Storage
  • Network Firewall/IDS
  • Free Daily Snapshots
  • DDoS-Protected Network
  • Dual Backups (Optional)
  • Fully Managed (Optional)
Order SC-4GB

30-day money-back

SC-6GB

$24 /mo
  • 3 vCPU
  • 6 GB RAM
  • 150 GB NVMe
  • 15 TB transfer
  • Full Root Access
  • Non-Oversold Cores
  • 100% NVMe Storage
  • Network Firewall/IDS
  • Free Daily Snapshots
  • DDoS-Protected Network
  • Dual Backups (Optional)
  • Fully Managed (Optional)
Order SC-6GB

30-day money-back

SC-8GB

$32 /mo
  • 4 vCPU
  • 8 GB RAM
  • 200 GB NVMe
  • 20 TB transfer
  • Full Root Access
  • Non-Oversold Cores
  • 100% NVMe Storage
  • Network Firewall/IDS
  • Free Daily Snapshots
  • DDoS-Protected Network
  • Dual Backups (Optional)
  • Fully Managed (Optional)
Order SC-8GB

30-day money-back

SC-16GB

$64 /mo
  • 6 vCPU
  • 16 GB RAM
  • 400 GB NVMe
  • 40 TB transfer
  • Full Root Access
  • Non-Oversold Cores
  • 100% NVMe Storage
  • Network Firewall/IDS
  • Free Daily Snapshots
  • DDoS-Protected Network
  • Dual Backups (Optional)
  • Fully Managed (Optional)
Order SC-16GB

30-day money-back

LibreChat installs itself on first boot with TLS, a hostname, and its database wired. Management and Dual Backups are optional addons in the cart.

Prefer to self-host? The exact LibreChat image we deploy is public and free to pull, with a full production guide.

Why here

Why run LibreChat on RemarkableCloud.

Your own private VPS

Not a container on a shared box. A real virtual server with dedicated resources and your own IP, and nobody else on it.

Stack apps, one price

Add as many apps as fit on your server from the client area, in one click each. No per-app charge, ever.

A 500% SLA that pays

1 hour down = 5 hours credited back, automatically, from the first minute. While others credit after thresholds, we credit from minute one.

Non-oversold hardware

Enterprise dedicated infrastructure, 100% NVMe, resources never sold twice. Your LibreChat performs the same on the worst day as the best.

Humans since 2001

Real engineers answer, at any hour. Twenty-five years of running production servers, and no chatbot wall between you and them.

Free migration, done by us

Moving an existing LibreChat site? We migrate it, verify it, and hand it back running, at no cost. Your old host stays live until you approve.

Built for

What people run on a LibreChat VPS here.

Every model, one chat

OpenAI, Anthropic, Google and local models behind a single familiar interface with per-user keys.

A team AI portal

Accounts, presets and search over history, so the company's AI usage lives in one governed place.

Cost-controlled API usage

Bring your own keys and watch spend by provider instead of paying per-seat markups.

Conversation search that works

Meilisearch under the hood makes months of chats actually findable.

The details

LibreChat here, in plain words.

Why self-host a ChatGPT-style interface?

Control and cost. Your team gets one interface for every model with conversation history you own, and API-priced usage often costs less than per-seat AI subscriptions once more than a couple of people are involved. BYO keys means each provider bills you directly at API rates.

Which AI models does LibreChat support?

OpenAI, Anthropic, Google, Azure OpenAI, and any OpenAI-compatible endpoint, which includes a LiteLLM gateway or a local Ollama on the same server. Switching models mid-conversation is built in.

How much RAM does LibreChat need?

4 GB is the honest floor: the stack runs MongoDB and Meilisearch beside the app. It shares a server politely, and the cart meter sizes the Cube from your full stack.

Can I let my whole team use it?

Yes: registration control, per-user conversations, and shared presets are core features. One server, one set of API keys, one bill from each provider you enable.

Everything around LibreChat, in one honest list.

Everything unmarked ships with every plan. The starred items are optional paid addons, priced plainly, added in the cart or anytime later.

Daily snapshots (kept 24h, plus on-demand)
Free SSL certificates
Instant hostname, your domain one wizard away
DDoS protection
Firewall fed by live threat data
Intrusion detection (IDS)
Centralized log analysis
Root SSH access
Free migration, done by us
Uptime monitoring, public status
500% SLA, automatic credits
30-day money-back guarantee
24/7 human support
Proactive monitoring, 24/7 *
Scheduled security patching *
OS updates and hardening *
Server optimization and tuning *
Outbound mail relay (MailChannels) *
Inbound antispam filtering *
Dual offsite backups (PBS + S3) *
Weekly backup verification *
Human-assisted restores *

* Optional paid addon: part of Fully Managed or Dual Backups. One price per plan, addons priced plainly, no surprise renewals.

Stack it

LibreChat runs well with.

Same server, no extra bill. These are the companions our team installs next to LibreChat most often.

LiteLLM

+1 GB

One API gateway for 100+ LLM providers: unified OpenAI-format calls, spend tracking, rate limits, and failover, self-hosted.

Ollama

+16 GB

Run open LLMs on your own server. Honest requirement: real models want real RAM, and the meter will route you to the right plan.

MariaDB

+1 GB

The MySQL fork with a community heart. Same managed treatment: tuning, backups, monitoring.

How it works

Seven systems working so you do not.

Every managed server runs the same stack underneath. Pick a system to see what it actually does.

Issues end before you hear about them.

Every minute, we check more than 200 parameters of your server and its services: web server, database, mail, disk, memory, and the network path to it. The moment anything drifts out of range, our support staff is alerted, investigates, and fixes it.

This is internal monitoring, deeper than any public uptime check: it watches the inside of your server, not just whether it answers. Most incidents are found and fixed by our staff before anyone outside ever notices them.

  • 200+ parameters checked every minute
  • Alerts reach engineers, not ticket queues
  • Inside-the-server checks, not just ping
  • Humans respond in minutes, any hour
Your VPS web db mail disk + 200 more parameters every minute out of range Staff alerted investigates and fixes it fixed, often before you notice

What customers say

More reviews: Trustpilot
“Excellent webhosting company. I really love all their products and services. Thank you so much.”
Fernando Garibay via Trustpilot
“The tech support is excellent, and they offer very competitive pricing. They also migrate my cPanel VPS to a DirectAdmin VPS without noticeable downtime.”
Carlos Reyes via Trustpilot
“I've been hosting several websites with them, and I can honestly say their support is outstanding. They are incredibly patient, knowledgeable, and genuinely committed to solving problems, even the most difficult and unusual ones.”
Juan Gabriel “Juangui” Verano via Trustpilot

Frequently asked questions

Do I need API keys for LibreChat?

Yes, from each provider you want to offer (OpenAI, Anthropic, Google, or a local Ollama needs none). Model usage bills with the provider; the app and the hosting playbook are $0 on our side.

Is my chat history private?

It lives in the MongoDB on your server, covered by our dual offsite backups, readable by nobody else. Prompts sent to commercial models still reach that provider's API, so pair with Ollama when a conversation must never leave the machine.

LibreChat or Open WebUI?

Open WebUI leans local-first around Ollama; LibreChat leans multi-provider with team features. Both are in our catalog at $0, and 8 GB runs either beside Ollama comfortably for small models.

Which providers does it support?

The major APIs (OpenAI, Anthropic, Google, Azure and more) plus local endpoints, each enabled with your keys in the configuration. Users can be limited to the providers you choose.

Can I connect it to local models?

Yes, point it at an Ollama or any OpenAI-compatible local endpoint, including one running on the same server, and local models appear beside the commercial ones.

Is this LibreChat on a VPS or on shared hosting?

A VPS. LibreChat runs on your own private virtual server with dedicated, non-oversold resources and its own IP. You get real isolation and performance, with the setup, TLS and hardening handled for you.

Can I run other apps on the same server?

Yes. Add any other catalog app to this server from your client area, one click each, no per-app charge. How much fits is a question of RAM, and resizing is minutes.

Do you migrate my existing LibreChat?

Yes, migration help is free. Open a ticket with access to the current setup and we move it, verify it, and hand it back running. Nothing switches until you approve.

Can I upgrade or downgrade the plan later?

Anytime. Plans resize from the client area in minutes, annual billing keeps its flat 17% discount at every size, and there is never a fee to change tiers.

Sizing an app stack? The VPS sizing calculator recommends a plan from your apps and traffic, with the math shown.

Your server runs. You sleep.

Fully managed hosting from people who have been doing this since 2001.