Artificial Intelligence

LibreChat

Private multi-LLM chat — OpenAI, Anthropic, Google and local models on your own server.

Official documentation

About LibreChat

LibreChat is an open-source chat interface that unifies multiple AI providers behind a single, polished UI. Deployed on your VPS, it gives your team a private alternative to ChatGPT: conversations, API keys and history stay in your own MongoDB — no data sent to third parties.

It supports multi-user management with admin roles, per-user API key storage, built-in RAG for document-based conversations, and a flexible `librechat.yaml` for custom endpoints (Ollama, Groq, Mistral). One server, every model, your data.

What gets installed

Ready when the VPS starts

Compatible OS
Ubuntu 24.04
Application
LibreChat
Tech stack
DockerNode.jsMongoDB 8
Minimum RAM
2 GB (4 GB recommended)
Minimum CPU
2 vCPU
Default port
3080
Access
root over SSH

Key features

  • Unified interface for OpenAI, Anthropic, Google Gemini and local Ollama models
  • Multi-user management with admin roles and access control
  • Conversation history persisted in your own MongoDB
  • Built-in RAG: chat with your PDF documents and knowledge bases
  • Per-user or shared API keys at server level
  • Extensible via librechat.yaml: custom endpoints, plugins, tool integrations

When to use this solution?

Team AI assistant

Deploy a shared ChatGPT alternative for your team. One API key per provider, internal accounts you control, all history in your MongoDB.

Multi-model comparison

Test GPT-4, Claude, Gemma and Mistral side by side in the same interface before integrating one into your product.

Zero-cloud RAG

Combine LibreChat with a local Ollama on the same VPS: your documents, your models, no data leaving the server.

Guide

Deploy LibreChat on your VPS

  1. Order your VPS

    From your ServOrbit dashboard, order a Cloud VPS with at least 2 vCPU and 4 GB RAM (8 GB if you add a local Ollama model). Choose Ubuntu 24.04.

  2. Deploy LibreChat

    In your client area, click Install on the LibreChat card. The automated provisioning deploys LibreChat, MongoDB and all dependencies via Docker Compose.

  3. Create your admin account

    Open the app URL in your browser. The first user to register automatically becomes administrator — no setup wizard needed.

  4. Connect your first AI provider

    Go to Settings → API Keys, enter your OpenAI, Anthropic or Google key, and start chatting. For a fully local setup, point a custom endpoint to your Ollama instance.

  5. Attach a domain (optional)

    Attach a domain from your client area to get HTTPS automatically. Without a domain, access via ssh -L 3080:127.0.0.1:3080 root@your-vps then http://localhost:3080.

  6. Invite your team

    As admin, go to Admin Panel → Users to invite team members. You control which AI providers and models each user can access.

Frequently asked questions

Questions about LibreChat

← Back to Artificial IntelligenceAll applications
LibreChat is a self-hosted, open-source chat interface that lets you use OpenAI, Anthropic, Google, and local Ollama models from a single UI — like ChatGPT, but on your own server.

Embed the deploy button

Maintaining a project that uses LibreChat? This button lets your readers deploy it on a VPS in one click, without reading Docker documentation.

Deploy LibreChat on ServOrbit
Markdown
[![Deploy LibreChat on ServOrbit](https://servorbit.com/brand/deploy/button.svg)](https://servorbit.com/vps-cloud?template=librechat&utm_source=deploy-badge&utm_medium=referral&utm_campaign=librechat)
HTML
<a href="https://servorbit.com/vps-cloud?template=librechat&utm_source=deploy-badge&utm_medium=referral&utm_campaign=librechat"><img src="https://servorbit.com/brand/deploy/button.svg" alt="Deploy LibreChat on ServOrbit" height="40"></a>

The button points to a VPS order with the template preselected. The image is served from servorbit.com — nothing to host on your side.

Complementary solutions

Artificial Intelligence

Open WebUI

Web interface to interact with your local or remote LLMs. Your data stays on your infrastructure — no third party involved.

Artificial Intelligence

AnythingLLM

Open-source AI workspace with built-in RAG, AI agents, and multi-model chat. Connect your own documents, use any LLM — hosted privately on your VPS.

Artificial Intelligence

Dify

Build LLM applications visually: chatbots, RAG agents, pipelines — without writing any backend code.

Need help?

Browse our help center and FAQ, or reach our team — callback, WhatsApp or email.

Message us on WhatsAppopens in a new tab
or write to us