Open-LLM-VTuber/

Open-LLM-VTuber

GitHub Website

Open-LLM-VTuber is a cross-platform, offline-capable voice-interactive AI companion with Live2D avatars, supporting multiple LLM/ASR/TTS backends and both web and desktop clients.

13kstars

1.5kforks

142issues

2023since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

open-webui/

open-webui

▲ 729/wk

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

148k21kPython

mem0ai/

mem0

▲ 565/wk

Universal memory layer for AI Agents

63k7.3kPython

chatchat-space/

Langchain-Chatchat

▲ 24/wk

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

39k6.3kPythonquiet

ollama/

ollama

▲ 640/wk

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

178k17kGo

chatboxai/

chatbox

Powerful AI Client

41k4.2kTypeScriptgiant

NousResearch/

hermes-agent

▲ 3.5k/wk

The agent that grows with you

225k44kPython

CompareOpen-LLM-VTuber vs open-webui Open-LLM-VTuber vs mem0 Open-LLM-VTuber vs Langchain-Chatchat

Reviewgenerated from repository data · Aug 5, 2026

What it is

Open-LLM-VTuber is a voice-interactive AI companion that supports real-time voice conversations and a Live2D avatar. It runs offline on Windows, macOS, and Linux, with both web and desktop client modes, including a transparent background desktop pet mode.

How it works

The project integrates various LLM inferences, ASR, and TTS options to enable offline operation and flexible backend choices. It provides visual perception features (camera, screen capture), voice interruption, chat log persistence, and a Live2D-based avatar system. It supports multiple module configurations and allows importing custom Live2D models and adjusting the persona through prompts.

Getting started

Please refer to the Quick Start in the documentation for installation: "Please refer to the Quick Start section in our documentation for installation."

Recent releases

Latest releases include:

v1.2.1 Release (2025-08-26): 1.2.1 contains important fixes to the frontend. Please update to the latest version if you are using 1.2.0.
v1.2.0 Release (2025-08-03): 1.2.0 includes Letta-based long-term memory, MCP support, Live2D Cubism 5 support, Chinese frontend support, and frontend improvements.
v1.1.0 Release (2025-02-19): Major features include group chat functionality, Silero-VAD, and CosyVoice2 TTS.
v1.0.1 Release (2025-02-04): Backend and frontend rewrite with over 240+ new commits.
v0.5.2 Release (2024-12-21): Default ASR provider updated back to FunASR.

Traction

Stars: 13093 Forks: 1533 Open issues: 142

Behind the repo

This project operates under the Open-LLM-VTuber organization and includes community documentation, Zulip/Known issue discussions, and a development roadmap for v2.0. It encourages participation via its Zulip chat and GitHub discussion.

Caveats

License: none listed Created: 2023-11-24 Last push: 2026-05-15 Language: Python

SharePost on X LinkedIn