Fork improved for maintainability and daily usage

Yours for the voyage.

Build your private AI command center,
not just another chat tab.

Atenea is a self-hosted AI workspace with chat, agents, memory, research, docs, email, calendar, and image tools. Bilingual (EN/ES), local-first, and designed to run on your own infra.

Bilingual UI + prompts Domain-based architecture Local-first + Docker-ready
Works with your stack

Connect models and tools you already use

Ollama vLLM llama.cpp OpenRouter OpenAI GitHub Copilot MCP ChromaDB IMAP/SMTP CalDAV Docker
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.

About Atenea

Built to be useful every day

This fork focuses on maintainable architecture, practical workflows, and a product style that feels alive instead of corporate boilerplate.

EN/ES
Bilingual workspace and AI behavior

Interface translations plus language-aware prompts across chat, agents, and research flows.

Domain-first
More maintainable code architecture

The codebase was reorganized into domain packages to simplify ownership, testing, and refactors.

Docker + Local
Ready for real self-hosted usage

Works with local models and private infrastructure while preserving optional integrations.

Atenea started from one bold prompt and kept evolving with real-world use.

user@atenea: ~
> 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.
The vision

Self-hosted AI should feel premium, not compromised.

Atenea exists to close the gap between "cool local model" and "daily driver workspace." Instead of a single chat box, you get an integrated system for chats, workflows, memory, research, and assistant tooling — without giving up control of your data.

This fork pushes further with a cleaner architecture, bilingual UX, and practical improvements focused on maintainability, performance, and long-term evolution.

Get started

Atenea is yours.

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

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