#3636th of 37 in AssistantsFor image, video and design, video and animation, voice, speech and music

open-llm-vtuber

Voice-chat AI companion with a Live2D avatar and desktop pet mode

Stars
14.3k
License
custom license
Last commit
May 2026
Last release
Aug 2025
Language
Python
Stars, last 30 weeks+8,117
27 Mar 2026: 6,231 stars3 Apr 2026: 6,317 stars10 Apr 2026: 6,684 stars17 Apr 2026: 6,773 stars24 Apr 2026: 6,859 stars1 May 2026: 7,212 stars8 May 2026: 7,439 stars15 May 2026: 7,562 stars22 May 2026: 7,692 stars29 May 2026: 7,766 stars5 Jun 2026: 9,896 stars12 Jun 2026: 11,027 stars19 Jun 2026: 11,480 stars26 Jun 2026: 11,760 stars3 Jul 2026: 12,147 stars10 Jul 2026: 12,314 stars17 Jul 2026: 12,476 stars24 Jul 2026: 12,603 stars31 Jul 2026: 12,880 stars7 Aug 2026: 13,024 stars14 Aug 2026: 13,135 stars21 Aug 2026: 13,297 stars28 Aug 2026: 13,397 stars4 Sept 2026: 13,531 stars11 Sept 2026: 13,629 stars18 Sept 2026: 13,749 stars25 Sept 2026: 13,857 stars2 Oct 2026: 13,928 stars9 Oct 2026: 14,000 stars16 Oct 2026: 14,134 stars23 Oct 2026: 14,348 stars

6,231 on 27 Mar 202614,348 on 23 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Open-LLM-VTuber is a Python server with web and desktop clients for real-time voice conversations with a Live2D character. It plugs in LLM, speech recognition and text-to-speech backends through a config file, and can run fully offline with local models. It also supports camera and screen input, voice interruption, and a transparent desktop pet mode.

Who it is for: Self-hosters wanting a local voice AI companion with a Live2D avatar

Strengths

  • Many swappable backends: Ollama, OpenAI-compatible, Claude, Gemini, vLLM, GGUF for LLMs
  • ASR and TTS options include sherpa-onnx, Faster-Whisper, Edge TTS, GPTSoVITS, Fish Audio
  • Runs fully offline on Windows, macOS and Linux, with CPU or cloud API fallback
  • Pluggable Agent interface and custom Live2D models for characters

Weaknesses

  • Long-term memory feature is temporarily removed
  • v1 is in maintenance; a full v2 rewrite is planned and v1 feature requests are refused
  • Remote access needs https via reverse proxy, or the browser microphone will not start
  • License is NOASSERTION; bundled Live2D sample models carry separate terms for commercial use

What it needs

  • GPU optional
  • Docker
  • Needs uv, ffmpeg
  • Models: Ollama, OpenAI-compatible, Gemini, Claude, Mistral

Quick answers

Is open-llm-vtuber open source?

Its code is public on GitHub under its own license terms; read them before you use it at work.

Can you run open-llm-vtuber with Docker?

Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.

Does open-llm-vtuber need a GPU?

No. It runs on a CPU and can use a GPU when you have one.

Also in Assistants

See all 37
Also in Assistants
RankProjectScore
1career-opsJob-search agent that scores listings, tailors CVs and drafts applications76.9k starsMIT95 out of 100
2ai-job-searchClaude Code workflow that searches job boards and drafts tailored CVs and cover letters64.2k starsMIT95 out of 100
3openhumanRust agent harness with desktop app, built-in memory and embeddable library42.3k starsGPL-3.093 out of 100
#4OpenClawPersonal AI assistant reachable through Discord, Slack, Telegram, WhatsApp and more392.9k starsMIT92 out of 100
#5airiAI VTuber companion with VRM and Live2D avatars, voice, and game-playing Live demo ↗ (opens in a new tab)50.6k starsMIT91 out of 100