Odysseus is a self-hosted AI workspace that combines chat and agents with research, document editing, email, notes, tasks, and calendar in one web app. It runs on your own machine against model endpoints you choose, local or API-based, with no telemetry and optional external integrations.
Agents plan, call tools, and work through tasks using built-in tools (bash, files, web search, memory) plus any connected Model Context Protocol (MCP) server, with each tool toggled individually. The assistant keeps persistent memory across conversations and can write, refine, and reuse its own skills.
A Cookbook section recommends models for the available hardware and downloads, serves, and manages local models across machines from a catalog of 270+ models. Other sections run multi-step web research that produces a cited report, send one prompt to several models for blind side-by-side comparison, and provide an image gallery with generation, background removal, and inpainting.
The workspace side includes a writing-first document editor with AI edits and suggestions, an IMAP and SMTP email client with triage, tagging, summaries, and draft replies, and notes, to-dos, and scheduled agent tasks with CalDAV calendar sync. It deploys with Docker Compose or as a native install, with authentication and two-factor login.
“MY trillion $Dollar Project is finally OUT!”
Features
- Chat and agents: local or API models with tools, MCP servers, files, shell, skills, and memory
- Cookbook: hardware-aware model recommendations, downloads, and serving across 270+ cataloged models
- Deep research: multi-step web research that reads sources and writes a cited report
- Compare: blind side-by-side testing of several models on one prompt, with synthesis
- Documents: a writing-first editor with AI edits and suggestions for Markdown, HTML, and CSV
- Email: IMAP and SMTP inbox with triage, tags, summaries, reminders, and reply drafts
- Notes, tasks, and calendar: reminders, to-dos, scheduled agent tasks, and CalDAV sync
- Persistent memory and skills: the assistant recalls context across conversations and reuses skills it writes
- Image gallery: image generation, editing, background removal, and inpainting
- Extras: themes, uploads, web search, presets, sessions, and two-factor authentication
