I got tired of keeping a Telegram tab open all day just to talk to my local agent, so I built a monitor-resident avatar that fronts it instead — a video-call-style face that performs the replies instead of me reading a wall of text.
A few things that might interest this crowd:
No runtime GPU for the avatar. Instead of live-animating a face, the agent's reply carries inline emotion-beat tags — [working], [confirm] deploy?, [happy] — and a player selects and blends between ~30 pre-rendered clips. The GPU stays 100% on the model. Code and logs render as chat cards instead of being read aloud, and [confirm] pops a human-in-the-loop approve/cancel that blocks the agent until you answer.
It hooks into a real agent as a connector. The agent's gateway dials out to a local WebSocket the app hosts, so from the agent's side the avatar is just "another channel," indistinguishable from a messenger. Adapters for Hermes and OpenClaw are included, plus a demo mode that runs with zero setup.
Local voice both ways. Edge TTS out (swappable to Qwen3-TTS / MeloTTS / Piper), Silero VAD + faster-whisper in.
Open-core, MIT. The engine is fully usable on its own: drop in a folder of clips named by emotion, point it at your agent. Avatars are pure-data bundles — no code runs when you install one — so you can build your own. The repo ships the engine only; there's no bundled character.
The engine just plays video clips — it doesn't care what produced the pixels. So the avatar can be photoreal, 2D anime, a 3D render, pixel art, anything. You can even use a Live2D or VRM model: pre-render its expressions into clips and it becomes a Ghost Vessel preset. A Live2D shell can't do the reverse — it can't take live-action footage. Clips are a superset. The trade-off is that you give up real-time rig interactivity (no dragging the head around) and you pay a one-time render step.
Repo + 45s demo: https://github.com/ghdtjrtka/ghost-vessel
The part I'd most like feedback on is the emotion-beat output format — the contract that turns model text into a UI performance. Has anyone here tried similar output contracts to drive an interface from LLM output? Curious what broke on your setup, and whether smaller local models keep the tags straight.
I have one that stitches animations together from several different starting frames A->B, B->C, C->A. I generated a bunch of First Frame / Last Frame videos and randomize them in sequence. It uses MuseTalk for lip sync when it's talking. It looks much more natural.
Mine is a cartoon scientist in a lab. When she's working on stuff, in the background (I put her in loops all the time, where she's just heads down on some task), she like, mixes chemicals and messes with electronics and rummages in drawers and eats pizza. When she's in conversation mode, she loops through the same set of starting and ending frames, but is actually passively looking at the camera, so it looks like she's talking to you (or creepily staring at the camera for hours at a time). I can tell if she's finished a /lab or /troubleshoot loop just by checking her animations.