Odysseus

Odysseus is a privacy-focused, self-hosted AI workspace that runs entirely on
your own hardware. It provides a full-featured browser UI for chat, document
analysis, deep web research, calendar sync, image generation, speech-to-text,
email, and more — connecting to Ollama, LM Studio, OpenAI, Anthropic, and any
OpenAI-compatible endpoint.

Nothing leaves your machine beyond the LLM API calls you explicitly configure.
Your conversations, documents, uploaded files, and personal settings are stored
in ~/snap/odysseus/common/app/data and persist across snap updates.

LOCAL AI

Run 'odysseus.inference-snap' to detect a Canonical inference snap
(gemma4, gemma3, deepseek-r1, and others) and configure it as the
Ollama-compatible backend in one step — fully offline, no API key required.

QUICK START

After installation, run:

odysseus

Then open http://localhost:7000 in your browser to reach the UI. The default
port can be changed by setting ODYSSEUSPORT in the environment or in your
.env file.

CONFIGURATION

Place a .env file at ~/snap/odysseus/common/.env to set API keys, LLM hosts,
and other options before starting the server. All variables from the upstream
.env.example are supported; for example:

OPENAIAPIKEY=sk-...
LLMHOST=localhost
ODYSSEUSPORT=7000
ODYSSEUSHOST=127.0.0.1

AUTH

Authentication can be enabled by setting AUTH_ENABLED=true in your .env file.

SECURITY NOTE

This tool is capable of executing code, accessing files, and interacting
with external services on your behalf. Due to the nature of autonomous
AI agents, we recommend installing and running this snap inside an LXD
container as best practice. A container provides an extra layer of
confinement, limiting the agent's reach to the container environment
and reducing exposure to your host system and personal data.

lxc launch ubuntu:24.04 my-agent
lxc exec my-agent -- snap install --classic odysseus