1. Inspects your machine
Detects macOS, Windows, or Linux, available memory, accelerators, Ollama, and reachable local services.
One skill. Your local AI stack.
Give your coding agent the Hangar skill.
It will inspect your computer, connect the local AI services you actually have, set up a local LLM, and verify Hangar at localhost:8003.
Paste this into Codex, Claude Code, or another coding agent
Set up Hangar on this machine by following this skill: https://github.com/alibad/hangar/blob/main/.claude/skills/hangar-setup/SKILL.md Clone the repository if needed, detect what is actually installed, configure only verified local services, make sure a local text model is available, and prove the console works at http://localhost:8003.
Hangar is open source. The skill measures before it configures and never assumes a service exists.
2. Configures Hangar
Creates a profile for this computer and wires only the models and capabilities it can prove are available.
3. Proves it works
Runs the tests, starts the console, checks the host profile, and verifies the local model service responds.
Prefer to install it yourself?Show the manual steps
Install the basics
Install Git, Node.js 22+, and Ollama, then clone Hangar.
Clone and install
git clone https://github.com/alibad/hangar.git
cd hangar
npm installAdd a local model and start
Qwen3 8B is a sensible first local text model. The setup skill can choose a better fit after checking your hardware.
Model and console
ollama pull qwen3:8b
node scripts/detect-host.mjs
npm run devYour models stay on your machine
This public site is only the setup guide. The working console and its machine APIs run locally; the public Human Quest domains cannot reach them.