3D Avatar

Live VRM companion with emotion and gestures

Sidekick AI lives beside your game as a real 3D avatar — animated, expressive, present. The difference between consulting a tool and playing with a teammate.

Add to Steam Wishlist

How It Works

Full 3D VRM avatar

Real 3D model rendered live in a floating window beside your game. Not a portrait, not a sprite, not a static image — a body with bones, expressions, and presence.

Emotion and gestures

The avatar reacts: smiles at clutch plays, winces at deaths, points at things on your screen, leans in during boss fights. Reactions you actually feel because you can see them.

Lip sync to the voice layer

Mouth movement matches the audio. The voice tips you hear come from a face that's actually saying them, not a disembodied speaker.

Companion customization

Pick or tweak the avatar that fits the vibe you want. The companion identity is consistent across sessions instead of resetting every time.

Why presence is a feature, not decoration

The 3D avatar is the most quietly opinionated choice in Sidekick AI. Most AI products treat the visual layer as a logo — a portrait, a chat bubble, maybe a 2D character. Sidekick treats it as a teammate with a body. The difference is presence: the sense that someone is playing with you, not just speaking at you.

Presence is the thing voice alone can't deliver. Voice gives you information. The avatar gives you company. For the moments you fire up Sidekick at 2am to push through a hard boss, company turns out to matter more than information.

How reactions work

Screen vision flags notable moments — a boss kill, a clutch dodge, a death, a rare drop, a critical strike, the start of a new encounter. Those signals travel to the avatar layer alongside the voice line. The avatar's expression, posture, and gesture pick up the moment. You die to Malenia again and the companion sighs. You finally beat her and the avatar throws hands up. None of this is narrated — you just see it.

Reactions are timed to feel like a teammate noticing things, not a cartoon. The avatar doesn't celebrate every kill or wince at every hit. It reacts to moments that genuinely matter, which is usually fewer per session than you'd expect.

Avatar versus portrait — the category difference

Other AI companions in the gaming space lean on 2D portraits, static character art, or stylized chat windows. Those work for chat. They don't deliver the felt experience of having a teammate present in your session. A 3D VRM avatar that animates, expresses, and reacts is a meaningfully different product shape — closer to VTubing than chatbot, closer to a co-op partner than a tool.

That said, if the visual layer isn't what you want, the product is fully usable as voice-only. Hide the avatar window and Sidekick is just a voice in your headset. The 3D layer is opt-in for the players who want it, not a tax for the players who don't.

Frequently Asked Questions

What is a VRM avatar?
VRM is an open standard for 3D humanoid avatars, widely used in VTubing, virtual worlds, and gaming. Sidekick uses VRM because it's the right format for real-time rendered companions — fully rigged, expression-capable, and well-supported. Your avatar isn't a video; it's a live 3D model that animates in response to what's happening.
Where does the avatar live during gameplay?
In a floating, resizable window beside your game window. You can dock it to a corner, drop it on a second monitor, or shrink it to a thumbnail when you want minimum visual footprint. The avatar never overlays gameplay unless you explicitly want it to.
Does the 3D avatar slow down my game?
On any modern gaming PC, no. VRM rendering is light compared to what your game is doing. Sidekick is designed so the avatar window stays smooth even when your game is pushing your GPU.
Why does a 3D avatar matter? Couldn't I just use voice?
You could. Voice alone works fine functionally. The 3D avatar adds presence — the difference between hearing a tip and playing alongside someone. Looking over and seeing a teammate reacting to your plays is a different kind of company than hearing a voice from nowhere. Whether that matters to you is a personal call, and you can shrink the avatar window if it doesn't.
Can I bring my own VRM model?
VRM is an open format, so this is a natural roadmap direction. Initial release ships a set of curated avatars that look right and behave consistently. Bring-your-own-VRM is the kind of customization that's easier to add once the baseline product is dialed in.
What if I stream? Does the avatar need to be off-camera?
Most streamers will want the avatar on camera. Sidekick's 3D companion is built stream-safe by design — appropriate poses, no inappropriate content, gaming-focused personality. Drop the avatar window into OBS as a windowed source and you have an on-screen companion for your viewers.
How does the avatar know when to react?
Same pipeline that drives the coaching voice. Screen vision recognizes notable moments — boss kills, deaths, big crits, rare drops — and the avatar gets reaction signals along with whatever the voice says. Reactions are tuned to be timely, not constant.
Can I turn off the avatar entirely?
Yes. Voice-only mode hides the avatar window completely. You still get the full real-time coaching experience, just without the visual companion. The 3D layer is a feature, not a requirement.

Related Resources

Screen Vision

What the avatar is reacting to — your live gameplay.

Voice Chat

What the avatar is saying — voice in, voice out coaching.

Avatar Gallery

Browse the avatars available in Sidekick AI.

Ready to play smarter?

Sidekick AI uses vision AI to watch your screen and coach you in real-time. Try the free demo on Steam.

Add to Steam Wishlist