# odysseus-dev/odysseus

Self-hosted AI workspace.

Repository: https://github.com/odysseus-dev/odysseus
Canonical: https://ross.abutalabs.com/products/odysseus
Homepage: https://odysseus-dev.github.io/odysseus
Language: Python
License: AGPL-3.0
License Family: copyleft
Last push: 2026-08-25T12:18:44+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 6
- inputs: {"age_days": 94, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 86318, forks 670 (observed 2026-08-28T04:12:23.052677+00:00)

## What it is
Odysseus is a self-hosted, privacy-first AI workspace that combines chat, autonomous agents, tools/MCP integration, model serving, and deep research in a single web application. It also bundles productivity features like an AI-assisted document editor, IMAP/SMTP email triage, notes, tasks, calendar with CalDAV sync, and persistent memory.

## Use cases
- self-host an AI chat interface for local and API language models
- run autonomous AI agents with tools, shell access, and MCP servers
- get hardware-aware recommendations for which local models to download and serve
- automate multi-step web research and generate cited reports
- triage my email inbox with AI summaries and draft replies
- compare multiple LLMs side by side on the same prompt
- manage notes, todos, and calendar with AI-assisted scheduling
- keep an AI assistant with persistent memory fully private on my own hardware

## When to choose
- you want a single self-hosted app combining chat, agents, research, email, and notes instead of separate tools
- privacy matters: no telemetry, everything runs on your hardware against your own endpoints
- you want to run and compare local models with hardware-aware recommendations
- you need agent capabilities with MCP, shell, files, and web tools in one workspace

## When to avoid
- you only need a lightweight chat UI without workspace features like email or calendar
- you cannot run Docker or manage a self-hosted deployment with auth and security hardening
- you need a managed cloud service with vendor support
- you require multi-user enterprise collaboration features at scale

## Facets
- artifact type: application
- maturity: active
- function: chatbot, agent-framework, rag, mcp, llm-inference, email, web-scraping, self-hosted, chat-interface
- domain: artificial-intelligence, large-language-models, self-hosted, developer-tools, privacy
- platform: self-hosted, windows, python
- tags: ai-workspace, local-first, local-models, deep-research, model-comparison, caldav, imap-smtp, no-telemetry, ai-agents, docker, linux, macos, web-server

## Member repositories
- odysseus-dev/odysseus (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:23.052677+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:13:53.552888+00:00, confidence not recorded.
  - readme: https://github.com/odysseus-dev/odysseus (fetched 2026-08-28T04:12:23.052677+00:00, sha 9caaeb8dd94e)
  - homepage: https://odysseus-dev.github.io/odysseus (fetched 2026-08-28T17:39:10.849112+00:00, sha fac4e1762544)
- Data as of 2026-08-30T08:39:29.467469+00:00.