Run a local language model with Ollama on a CPU-only VPS
Install Ollama, pull a small quantised model, measure its real speed on your plan and keep the API private to the server.
Read guide →GLWS · KNOWLEDGE BASE
AI and LLMs.
Private models on your own server.
Self-host AI on a Linux VPS: run local models with Ollama, agents such as OpenClaw, Hermes and OpenCode, an MCP server and a LiteLLM gateway, and keep it all secure.
Our plans have no GPU, so local models run on the CPU. That suits small models and private experiments. Agents, gateways and MCP servers mostly call hosted models, so they run well even on small plans.
Start with sizing and Ollama if you want local models, or with the gateway and agent guides if you use hosted ones. Read the security guide before you publish anything.
15 ai and llms guides
Self-host Open WebUI with Ollama using Docker Compose
Run a private ChatGPT-style interface and Ollama in one Compose project, publish it on localhost only and lock down sign-ups.
Read guide →Choose a VPS size for a local AI model
Work out how much memory, disk and CPU a quantised model needs, then test on a small plan and measure before you upgrade.
Read guide →Secure Ollama, Open WebUI and other AI services on a public server
Keep AI services off the open internet: bind to localhost, avoid the Docker firewall bypass, add authentication and verify from outside.
Read guide →Use hosted AI APIs from your VPS without leaking keys or costs
Keep API keys out of code, load them through systemd, set timeouts, retries and spending limits, and rotate a key that leaks.
Read guide →Run a small AI chatbot as a systemd service
Write a short Python service that answers questions through a local Ollama model, run it as a protected systemd service and call it safely.
Read guide →Self-host n8n for automation and AI workflows
Run n8n in Docker on localhost, keep its data in a volume, reach it over a tunnel or Nginx and connect it to a local Ollama model.
Read guide →Run a private vector database with Qdrant or pgvector
Store and search embeddings on your own server with Qdrant in Docker or the pgvector extension, keep it private and test with a tiny dataset.
Read guide →Answer questions about your own documents with a local model
Split text files into chunks, embed them with Ollama, find the closest chunks to a question and answer from them, all on your server.
Read guide →Transcribe audio on a CPU VPS with whisper.cpp
Build whisper.cpp, download a small speech model, convert audio to the right format and measure how long transcription takes on your plan.
Read guide →Run OpenClaw on your VPS
Install OpenClaw as an unprivileged user, run its gateway as a service, keep the control interface private and limit who and what the assistant can reach.
Read guide →Self-host Hermes Agent on a Linux VPS: step by step
Install Hermes Agent, choose a model, connect a messaging gateway, run it as a boot-time service and control who is allowed to use it.
Read guide →Build and securely host your first MCP server
Write a small MCP server in Python with a read-only tool, run it over stdio and over HTTP, and publish it behind HTTPS and token authentication.
Read guide →Create an AI API gateway with LiteLLM
Run the LiteLLM proxy with Docker Compose, keep your provider keys in one place, issue limited virtual keys and put the gateway behind HTTPS.
Read guide →Run an AI coding agent with OpenCode on a VPS
Install OpenCode, connect a model provider, keep it inside a project with permission rules, work from tmux and use headless mode safely.
Read guide →Other topics
Getting started · Linux basics · System administration · Security · Server administration · Kubernetes · Troubleshooting · Monitoring · Networking · Web hosting · Data and storage · Self-hosting
Browse all guides