An open-source AI companion you can see and talk to
Load a VRM avatar, connect any LLM, and talk by voice with a character that speaks, listens, and remembers, all on your own machine.
Bring your own brain
Plug in any model. Use your own keys.
The best way to bring an AI to life.
A real 3D body, not a chat box.
Drop in any VRM model and watch it come to life. Replies appear as 3D speech bubbles that follow your companion's head as it moves, breathes, and looks around.
She steps into your room.
Place her on your real floor through the camera and she stands there in your space, holding her ground as you move around her. Drag her anywhere, pinch to resize, and keep the chat open the whole time, in Android Chrome or any WebXR-capable headset browser.
She actually remembers.
Local AI embeddings weave your conversations into a web of memories she can recall by meaning, not keywords. Affection, trust, and mood shift over time across eight relationship stages — from Stranger to Soulmate.
You own every part of it.
Run a frontier model or keep it fully offline with Ollama and LM Studio. Mix and match your chat, voice input, and text-to-speech providers — all on your own API keys, with nothing routed through us.
Utsuwa means vessel. You decide what fills it.
Fresh from the blog
Guides, deep dives, and release notes from the project.
Ready to meet your companion?
Try it right in your browser, or download the desktop app. Free and open source.