Observed arrival · 2026-09-09
latentPresence puts a face on the conversation
An open-source conversational AI that joins video calls as a full-body 3D character, speaking, reacting, remembering, and working with your chosen models.
Field notes
The project describes a VRM character rendered in the browser with three.js, combining lip sync, expressions, voice replies, and optional camera-based mood estimation. It supports a broad mix of local and hosted model runtimes, while memory can be directed to MariaDB, SQLite, or the browser. The page also describes document answers with openable citations and scheduled tasks that are visible and cancellable, although the project identifies itself as early development.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue