Install Odysseus with Docker
The official recommended method — works on Windows, macOS, and Linux.
Quick answer
Requirements: Docker Desktop (Windows/Mac) or Docker Engine (Linux).
Expected result: http://localhost:7000 shows the Odysseus login. Compose also starts ChromaDB, SearXNG, and ntfy on loopback.
First password: docker compose logs odysseus
Official tip: clone -b main for the curated branch. Bare git clone defaults to dev (newest, less stable).
Install commands
terminal
git clone -b main https://github.com/pewdiepie-archdaemon/odysseus.git
cd odysseus
cp .env.example .env
docker compose up -d --build
# Open http://localhost:7000
# Admin password: docker compose logs odysseusConnect Ollama from Docker
When Odysseus runs inside Docker, localhost refers to the container — not your host machine.
terminal
# Odysseus in Docker + Ollama on host:
# 1. Install Ollama on your machine (not in container)
# 2. Pull a model: ollama pull llama3.2
# 3. Let Ollama listen beyond loopback if needed:
# OLLAMA_HOST=0.0.0.0:11434 ollama serve
# 4. In Odysseus Settings, add endpoint:
# Windows/Mac: http://host.docker.internal:11434/v1
# Linux: http://172.17.0.1:11434/v1 (or host network mode)NVIDIA GPU (official overlay)
For Cookbook GPU serving inside Docker on Linux or WSL2. Apple Silicon Docker cannot use Metal — use ./start-macos.sh instead.
terminal
# From the Odysseus repo root (Linux / WSL2):
# 1. Diagnose / install NVIDIA Container Toolkit (optional helpers):
scripts/check-docker-gpu.sh --print-install-commands
# scripts/check-docker-gpu.sh --install-nvidia-toolkit
# 2. Enable the official overlay in .env (after passthrough works):
# COMPOSE_FILE=docker-compose.yml:docker/gpu.nvidia.yml
# Or run:
scripts/check-docker-gpu.sh --enable-nvidia-overlay
# 3. Recreate:
docker compose down
docker compose up -d --build
# Verify GPU inside the container:
docker compose exec odysseus nvidia-smi -L
# Stack UIs that need a single file: use docker-compose.gpu-nvidia.yml instead.FAQ