Want ChatGPT, but trained on your own docs?
Want to host it yourself, with no limits or spying?
AnythingLLM gives you that:
→ Self-hosted RAG (Retrieval-Augmented Generation) with OpenAI or Local LLMs
→ Drop in PDFs, Docs, Markdown, Notion pages, websites
→ Slick UI, document management, even team features
In this guide, you’ll learn how to:
Run AnythingLLM on your own Linux server
Use Docker to keep it isolated
Load up your docs
Monitor your LLM uptime like a pro
A Linux server (Ubuntu/Debian) 👉 We recommend Hetzner Cloud — great pricing & performance
Docker + Docker Compose
OpenAI API key or Local LLM (e.g. Ollama)
Docs you want to load
5–10 minutes
git clone https://github.com/Mintplex-Labs/anything-llm.git
cd anything-llm
Copy the example file:
cp .env.example .env
Open .env
and update:
OPENAI_API_KEY=your-openai-key
Or set Ollama / Local LLM variables
Choose vector DB (Supabase is default)
Build and start:
docker compose up -d --build
Cool! Now visit:
http://your-server-ip:3001
Set up your admin account and log in.
You can now:
Upload PDFs
Paste text
Connect Notion or URLs
Create multiple workspaces
Once ingested, you can chat with the content via the UI.
If you don’t want OpenAI, install Ollama on the same or another server:
curl -fsSL https://ollama.com/install.sh | sh
ollama run llama3
Then point AnythingLLM to your local endpoint in .env
.
Your AI knowledge base is now running — but is it reliable?
If it goes down, your productivity (or users) go with it.
Make sure it stays up with Garmingo Status:
✅ Monitor your IP or domain
✅ Set alerts (Slack, Email, Telegram, Discord, etc.)
✅ Multi-location uptime checks
✅ Public or private status pages
✅ SLA tracking + monthly reports
✅ One-time payment → Lifetime Deal!
🎁 Grab it on AppSumo here — under $50, no subscription.
🧠 AnythingLLM gives you private ChatGPT with your docs
🐳 Self-host it with Docker
📊 Monitor it with Garmingo Status
💸 No monthly fees — forever
👉 Get Lifetime Access to Garmingo on AppSumo
👉 Or test it free
Got an idea? Let us know