Guides
Setup guides
Install and configure Liminal on your stack. Desktop app, CLI, OpenRouter, Ollama, and env vars. Every guide links to the installer and technical docs.
Install Liminal on your machine
Liminal ships as a native desktop app for Windows, macOS, and Linux, plus a one-command CLI installer for developers. Every guide below assumes Community Edition: free under FSL-1.1-MIT, no Vireon account required, bring-your-own API key or optional Pro managed inference.
Most people start with the desktop download on the Get started page, then pick OpenRouter or a local Ollama model using the configuration guides.
Pick your model provider
OpenRouter is the default recommendation: one API key, hundreds of models, and strong prompt-cache pricing on supported routes. You can also point Liminal at OpenAI, Anthropic, xAI, or a fully local OpenAI-compatible server when privacy or air-gap requirements matter.
7 in-depth pages. Each includes step-by-step detail, FAQs, and links back to Liminal AI install and docs.
OpenRouter + Liminal
Point Liminal AI at OpenRouter for DeepSeek, Claude, GPT, and more. API key, model slugs, and harness env vars in five minutes.
Read →Install Liminal on Windows
Install the Liminal AI coding agent on Windows 10/11 with PowerShell. Node.js 22+, API key, and first run in minutes.
Read →Install Liminal on macOS
Install Liminal AI on macOS with one curl command. Apple Silicon and Intel supported. Node 22+ required.
Read →Install Liminal on Linux
Install Liminal AI on Ubuntu, Debian, Fedora, and other Linux distros. One script, local agent, any LLM.
Read →Ollama + Liminal
Run Liminal AI against Ollama on your machine. No cloud inference. OpenAI-compatible local endpoint setup.
Read →Environment & API keys
Configure AGENT_API_KEY, models, and harness toggles for Liminal AI. Quick reference for .env setup.
Read →Docker + Liminal
Run Liminal AI in Docker for reproducible dev environments. Image patterns, API keys via env, and mounting your workspace.
Read →