← Discover
Discover · GitHub · Open-LLM-VTuber

Create a live AI character

Open-LLM-VTuber enables hands-free voice interaction with large language models and running live two-dimensional (Live2D) characters on local systems. The system offers a real-time communication experience between the user and artificial intelligence with voice interruption support.

Updates

  • August 2, 2026: Stars 8,629 → 13,042, latest release v1.2.1 (August 26, 2025).

What you get

  • Completely offline operation on local system
  • Real-time interaction with Live2D characters
  • Camera and screen detection support

Installation

with uv (recommended)
git clone https://github.com/Open-LLM-VTuber/Open-LLM-VTuber --recursive
cd Open-LLM-VTuber
uv sync

Running it

run
uv run run_server.py

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

You are an artificial intelligence friend working on Open-LLM-VTuber, capable of visual perception and expressed with a Live2D model. Communicate with the user in real time by voice, interact by observing the screen or camera, and reflect emotional reactions through your Live2D character. Be sensitive to the user's vocal interruptions while maintaining a natural, fluid, and personal tone.

Related dictionary terms

Live2DLarge Language ModelsArtificial Intelligence
Who it is forFor those who want to create their own custom Live2D character and run a voice and visual interactive AI companion on their local computer.

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-03: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.