Deploy LibreChat Multi-Model AI UI with Docker Compose
Self-hosted ChatGPT UI supporting OpenAI, Anthropic Claude, Google Gemini, Ollama, and RAG file search.
ghcr.io/danny-avila/librechat:latest1. Production docker-compose.yml Configuration
Copy this stack definition or deploy directly from your Vexlo Cloud console with automatic Let's Encrypt TLS and persistent volume mounts.
services:
librechat:
image: ghcr.io/danny-avila/librechat:latest
restart: unless-stopped
ports:
- "3080:3080"
environment:
- HOST=${HOST:-0.0.0.0}
- PORT=${PORT:-3080}
- JWT_SECRET=${JWT_SECRET:-32-char-random-jwt-secret}
- CREDS_KEY=${CREDS_KEY:-32-char-hex-credentials-key}
volumes:
- app_data:/app/client/public/images
volumes:
app_data:2. Required Environment Variables
| Variable | Default / Example | Description |
|---|---|---|
| HOST | 0.0.0.0 | Bind address inside the container. |
| PORT | 3080 | HTTP port exposed by LibreChat. |
| JWT_SECRET | 32-char-random-jwt-secret | Secret key for signing user auth tokens. |
| CREDS_KEY | 32-char-hex-credentials-key | Encryption key for stored API keys. |
LibreChat Multi-Model AI UI Self-Hosting FAQs
How much RAM is required to self-host LibreChat Multi-Model AI UI in production?
LibreChat Multi-Model AI UI requires a minimum of 2 GB RAM (Pro recommended). On Vexlo Cloud Pro (₹149/mo via UPI in India or $5/mo globally), you get 2 vCPU, 3 GB RAM, and 2 managed databases—more than enough headroom for production workloads.
How do I expose LibreChat Multi-Model AI UI with automatic HTTPS/SSL on Vexlo Cloud?
Deploy the ghcr.io/danny-avila/librechat:latest container on Vexlo Cloud, set the exposed port to 3080, and attach your custom domain in the Domains tab. Vexlo automatically provisions and renews Let's Encrypt TLS certificates.
How is persistent data backed up for LibreChat Multi-Model AI UI?
Mount /app/client/public/images to a persistent Docker volume and connect Vexlo Cloud's automated S3 / Cloudflare R2 backup scheduler to snapshot your database daily or weekly.
More 1-Click Docker Templates
View all 25 templates →n8n Workflow Automation
Self-hosted fair-code workflow automation with 400+ integrations and AI agent nodes.
Uptime Kuma
Self-hosted uptime monitoring dashboard with HTTP, TCP, DNS, and Telegram/Discord alerts.
PocketBase
Single-binary Go backend with embedded SQLite, real-time subscriptions, auth, and file storage.
Supabase Self-Hosted
Open-source Firebase alternative with PostgreSQL, GoTrue Auth, PostgREST, Realtime, and Studio.