Yours for the voyage.

Your own AI workspace,
running on your hardware.

Odysseus is a self-hosted interface for talking to language models — chat, autonomous agents, tools, model serving, email, research, and more. Local-first, privacy-first, and no telemetry. Just you and your models.

(if you want to add an API that's cool too — I'm not here to tell you how to live your life…)

Everything, self-hosted

One app, a lot of capabilities

Started as an AI chat. Became a workspace. Each piece runs locally against whatever endpoints you point it at.

Chat & Agents

Multi-turn chat plus autonomous agents that plan, call tools, and work through tasks.

Tools & MCP

Built-in tools (bash, files, web, memory) plus any MCP server you connect. Toggle per tool.

Cookbook

Hardware-aware model recommendations and one-click serving across 270+ catalogued models.

Email Assistant

AI summaries, style-matched draft replies, auto-tagging and spam triage over IMAP/SMTP.

Deep Research

Multi-step research runs that gather, read, and synthesize sources into a written report.

Compare

Send one prompt to several models at once and compare their answers side-by-side.

Memory

Persistent memory the assistant builds up and recalls across all your conversations.

Skills self-evolving

The assistant writes, refines, and reuses its own skills — getting more capable over time.

Private by default

Runs on your machine against your own endpoints. No telemetry, with optional external integrations when you choose them.

Loved by enterprises

What our customers are saying

Generic Coder Guy

"Odysseus helped us ship more ships while shipping ships. Truly best-in-class shipping."

★★★★★
Generic Coder Guy
Sr. Engineer, ShipShip Inc.
A real woman

"I'm a real person. This is a real testimonial. By a real woman."

★★★★★
Generic Corporate Woman
VP of Verticals, Things LLC

"AHHHHHHHHHHHHHHHHHHHHHHHHHHHHH"

☆☆☆☆☆
Polyphemus
Cyclops, Cave Solutions (on leave)

"Anyway, as I was saying — best-in-class."

★★★★★
Chad Corporate
Chief Executive Officer

Odysseus was created by a carefully crafted one-shot AI prompt:

user@odysseus: ~
> idk what to make come up with something oh make an AI chat but make it good and make it look nice
See it in action

Hover or tap to take a closer look

Each panel expands and plays its preview when you hover or tap it. Swipe on mobile to move through them.

[ Chat & Agents ]
Chat & AgentsTalk to any local model, or give it tools and let the agent run.
[ Cookbook ]
CookbookDownload, serve, and manage local models across your machines.
[ Deep Research ]
Deep ResearchAsk once: it searches, reads sources, and writes back a cited report.
[ Compare ]
CompareSend one prompt to many models at once and watch them answer side by side.
[ Documents ]
DocumentsA document editor that puts you first — work on what you want, with AI help when you want it.
[ Notes & Tasks ]
Notes & TasksCapture notes and to-dos, or let scheduled agents work and brief you after.
[ Image Gallery ]
Image GalleryGenerate, edit, remove backgrounds, and inpaint in your own gallery.
[ Themes ]
ThemesRestyle and make it yours — edit your own, or ask the agent to make one.
How it actually started

Uncompromised local LLM experience.

I started working on the Odysseus project because running local AI felt fun and powerful. But the options at the time to engage with LLMs felt like taking steps back. The idea that you could just self-host AI and not pay for a subscription wasn't there. All the tools and functions that make it all magic were missing.

So I started building Odysseus bit by bit — and the more I gave it to work with, the better it served me. Turns out the more your model knows about you, the more useful it gets. Which is the other reason to self-host: you get all that context without handing your private data to someone else's cloud.

Get started

Odysseus is yours.

It's open source and free. No sales team, no demo request, no Trojan horse.

$ git clone https://github.com/pewdiepie-archdaemon/odysseus.git && cd odysseus
View on GitHub
Self-hosted Bring your own models Local-first MCP-ready No telemetry