A persistent-state agent manager, with heavy tooling, research and learning, built from several local models working as one. All on your own machine.
Luna isn’t one model. A chat model does the thinking and talking, and smaller ones beside it see, hear, speak, recall by meaning and judge what’s relevant (what she runs on). Around them sits state that carries on between sessions: facts she writes, corrects and forgets, notes on past conversations, lessons from her own mistakes, moods, routines, and who’s in the house. On top of that sit her tools (files, commands, email, web research, your network and smart home, scheduled jobs, MCP servers), and she looks things up and learns from how her turns went.
The persona is a layer, not the point. Her default face is a cat-girl with a voice, moods and an animated portrait, and presets set her up as a calm assistant, a companion or a streamer. Under every face it’s the same agent.



Why reinvent the wheel when you can just use the existing OpenVoiceOS, building upon and contributing back to that, which has a decade of work behind it stemming from Mycroft and thus an actual community around it?