Odysseus AI GuideInstall

Install Odysseus on Windows

No Docker. Python 3.11+ and Git required.

Professor Patterns · Prefer Docker?

Shortcut

Official one-liner — skip manual steps if this works:

terminal
git clone https://github.com/pewdiepie-archdaemon/odysseus.git
cd odysseus
powershell -ExecutionPolicy Bypass -File .\launch-windows.ps1

Manual steps

  1. 1. Clone the repo

    Open PowerShell in an empty folder. Use the official repo; if it fails on Windows, use the fork from the video (0:30).

    terminal
    git clone https://github.com/pewdiepie-archdaemon/odysseus.git
    cd odysseus

    Fork fallback: github.com/amish-github/odysseus

  2. 2. Create venv & install packages

    Requires Python 3.11+.

    terminal
    py -3.11 -m venv venv
    venv\Scripts\Activate.ps1
    pip install -r requirements.txt
  3. 3. Run setup & start the server

    Copy the admin password printed in the terminal before continuing.

    terminal
    python setup.py
    python -m uvicorn app:app --host 127.0.0.1 --port 7000

    Port 7000 in use? Change to --port 8000.

  4. 4. Log in

    Open http://localhost:7000 — username admin, password from step 3.

  5. 5. Install Ollama & pull a model

    Download from ollama.com. Start with a small model (under ~5 GB).

    terminal
    ollama pull qwen3.5:0.8b

    Models appear in Odysseus automatically when Ollama is running (Settings → gear icon).

  6. 6. Chat

    Select your model in the dropdown, send a message, confirm you get a reply.

FAQ

Common questions