Apps / LibreChat
Managed LibreChat hosting.
One server, no app limits.
A private ChatGPT-style interface for every major model provider. One clean UI, your API keys, your conversation history on your server.
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.
What managed covers
Server updates, daily snapshots, dual offsite backups that include your conversation database, monitoring, firewall, mail gateway for its notification mail, and humans on call.
The app is $0. The managed server is the only bill, and everything above is part of it.
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.
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 GBOne API gateway for 100+ LLM providers: unified OpenAI-format calls, spend tracking, rate limits, and failover, self-hosted.
Ollama
+16 GBRun 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 GBThe MySQL fork with a community heart. Same managed treatment: tuning, backups, monitoring.
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.
Sizing an app stack? The VPS sizing calculator recommends a plan from your apps and traffic, with the math shown.
Shared CPU servers
The right home for LibreChat and most stacks: 3.0+ GHz vCPU, from $10/mo.
See Shared CPU →Dedicated CPU servers
For CPU-hungry stacks and busy databases: cores that are physically yours.
See Dedicated CPU →All plans and pricing
Every plan, both families, one honest price with everything included.
See pricing →Your server runs. You sleep.
Fully managed hosting from people who have been doing this since 2001.