Back to guide

Install Odysseus AI on Windows

Last updated: June 3, 2026

Three approaches, pick one. Docker Desktop is the most reliable. For the latest instructions, check the official repository .

Method 1: Docker Desktop

Recommended

Docker handles all dependencies and works consistently across Windows versions. Requires Windows 10/11 with WSL2 support.

1. Install Docker Desktop

Download from docker.com. During setup, enable the WSL2 backend. Restart after installation.

2. Clone and start Odysseus

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

cd odysseus

cp .env.example .env

docker compose up -d

3. Open in browser

Navigate to http://localhost:7000.

For NVIDIA GPU support:

# Install NVIDIA Container Toolkit first

# Then use the GPU compose override

docker compose -f docker-compose.yml -f docker-compose.gpu.yml up -d

Method 2: WSL2 + Native Install

Run Odysseus directly inside a WSL2 Linux environment. Better compatibility than native Windows, with direct hardware access.

1. Install WSL2

# Run in PowerShell as Administrator

wsl --install

# Restart, then set up your Ubuntu user

2. Inside WSL2, install dependencies and clone

sudo apt update && sudo apt install python3.11 python3.11-venv git

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

cd odysseus

python3.11 -m venv venv

source venv/bin/activate

pip install -r requirements.txt

cp .env.example .env

python main.py

Advantage: native Linux environment with full compatibility. NVIDIA GPU passthrough works through WSL2's built-in CUDA support.

Method 3: Native Windows

Experimental

Running directly on Windows without Docker or WSL. Some dependencies don't install cleanly. Community members have created forks to fix Windows-specific issues.

# Install Python 3.11 from python.org

# Install Git for Windows

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

cd odysseus

python -m venv venv

venv\Scripts\activate

pip install -r requirements.txt

copy .env.example .env

python main.py

Expect path issues and missing native dependencies. Check the GitHub Issues tab for Windows-specific fixes.

Known Windows Issues

Docker Desktop uses too much RAM

Create %UserProfile%\.wslconfig to limit memory:

[wsl2]

memory=8GB

swap=4GB

GPU passthrough: NVIDIA only

Docker on Windows only supports NVIDIA GPU passthrough via the NVIDIA Container Toolkit. AMD GPUs are not supported in Docker on Windows. AMD users should consider WSL2 with ROCm or cloud API backends.

File permission errors in mounted volumes

Windows and Linux handle file permissions differently. If you see permission errors, try storing your project files inside the WSL2 filesystem (\\wsl$\Ubuntu\home\...) instead of on the Windows drive.

Ollama on Windows + Odysseus in Docker

Install Ollama natively on Windows. It runs on localhost:11434. From inside Docker, reach it via host.docker.internal:11434. Set this as your Ollama endpoint in the Odysseus settings.

NVIDIA GPU Setup on Windows

To use your NVIDIA GPU with Odysseus in Docker on Windows:

  1. 1.Install the latest NVIDIA GPU drivers from nvidia.com
  2. 2.Ensure Docker Desktop is using the WSL2 backend (Settings > General > Use the WSL 2 based engine)
  3. 3.Install NVIDIA Container Toolkit inside WSL2
  4. 4.Restart Docker Desktop
  5. 5.Start Odysseus with the GPU compose file

# Verify GPU is visible inside Docker

docker run --rm --gpus all nvidia/cuda:12.0-base nvidia-smi

# Start Odysseus with GPU support

docker compose -f docker-compose.yml -f docker-compose.gpu.yml up -d

FAQ

Can I run Odysseus AI on Windows without WSL?

Docker Desktop for Windows is the recommended approach and handles WSL2 internally. For a fully native Windows install without Docker, expect compatibility issues. Some Python dependencies don't install cleanly on Windows. Community forks exist to address this, but Docker remains the most reliable path.

Does Odysseus AI support AMD GPUs on Windows?

Not through Docker on Windows. NVIDIA is the only GPU vendor supported via Docker GPU passthrough on Windows. AMD GPUs work on Linux with ROCm. If you have an AMD GPU, consider running Odysseus in WSL2 with ROCm or using cloud API backends instead.

How much RAM does Docker Desktop need for Odysseus?

Docker Desktop with WSL2 defaults to using up to 50% of your system RAM. For Odysseus, allocate at least 8GB to WSL2. Create a .wslconfig file in your user profile to set memory limits and prevent Docker from consuming too much RAM.

Can I use Ollama on Windows alongside Odysseus in Docker?

Yes. Install Ollama natively on Windows, which runs on localhost:11434. Then configure Odysseus in Docker to connect to host.docker.internal:11434 to reach the Ollama instance on your host machine.

Related Guides