Install

Get OwlCoda running on macOS, Linux, or Windows-WSL in under 5 minutes.

OwlCoda is currently distributed as source. npm / Homebrew / standalone binary are planned for 1.0.

Prerequisites

• Node.js ≥ 18 (Node 20+ recommended)
• A local OpenAI-compatible inference backend (Ollama / LM Studio / vLLM / any custom router) — required for local-only operation
• macOS, Linux, or Windows (WSL recommended on Windows)

Steps

git clone https://github.com/yeemio/owlcoda.git
cd owlcoda
npm install
npm run build
npm link             # exposes `owlcoda` globally

If npm link fails

This usually means your global npm prefix is not writable.

• Option A — sudo: sudo npm link
• Option B — user-local prefix:

  npm config set prefix ~/.local
  export PATH=~/.local/bin:$PATH    # add this to your shell profile
  cd /path/to/owlcoda && npm link
  

• Option C — skip the link entirely: node /path/to/owlcoda/dist/cli.js …

Verify the install

owlcoda --version
owlcoda doctor

owlcoda doctor checks Node version, the local runtime reachability, and configured models. See Troubleshooting for what to do when a check fails.

Next

Configure your first backend in Configure providers.