Interface translations plus language-aware prompts across chat, agents, and research flows.
Yours for the voyage.
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.
Started as an AI chat. Became a workspace. Each piece runs locally against whatever endpoints you point it at.
Multi-turn chat plus autonomous agents that plan, call tools, and work through tasks.
Built-in tools (bash, files, web, memory) plus any MCP server you connect. Toggle per tool.
Hardware-aware model recommendations and one-click serving across 270+ catalogued models.
AI summaries, style-matched draft replies, auto-tagging and spam triage over IMAP/SMTP.
Multi-step research runs that gather, read, and synthesize sources into a written report.
Send one prompt to several models at once and compare their answers side-by-side.
Persistent memory the assistant builds up and recalls across all your conversations.
The assistant writes, refines, and reuses its own skills — getting more capable over time.
Runs on your machine against your own endpoints. No telemetry, with optional external integrations when you choose them.
This fork focuses on maintainable architecture, practical workflows, and a product style that feels alive instead of corporate boilerplate.
Interface translations plus language-aware prompts across chat, agents, and research flows.
The codebase was reorganized into domain packages to simplify ownership, testing, and refactors.
Works with local models and private infrastructure while preserving optional integrations.
Atenea started from one bold prompt and kept evolving with real-world use.
> idk what to make come up with something oh make an AI chat but make it good and make it look nice
Each panel expands and plays its preview when you hover or tap it. Swipe on mobile to move through them.
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.
It's open source and free. No sales team, no demo request, no Trojan horse.