# Open-LLM-VTuber/Open-LLM-VTuber

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms

Repository: https://github.com/Open-LLM-VTuber/Open-LLM-VTuber
Canonical: https://ross.abutalabs.com/products/open-llm-vtuber
Homepage: https://open-llm-vtuber.github.io/
Language: Python
License: NOASSERTION
License Family: other
Topics: ai-vtuber, ai-waifu, ai, neuro-sama, chatbots, live2d, live2d-web, llm, ollama, ai-companion
Last push: 2026-05-15T07:18:04+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 82, release rhythm 44, longevity 72
- inputs: {"age_days": 1013, "days_push": 110, "days_rel": 372, "gap_med": 9.5, "n_releases_24m": 17}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 13473, forks 1599 (observed 2026-08-28T04:11:03.388958+00:00)

## What it is
Open-LLM-VTuber is a cross-platform AI companion application that enables real-time voice conversations with LLMs, featuring a Live2D avatar, voice interruption, vision perception, and MCP tool calling. It runs fully offline with local models or via cloud APIs, and offers web and Electron desktop clients including a transparent desktop-pet mode.

## Use cases
- run a local AI vtuber like neuro-sama
- chat with an AI waifu using voice
- build an AI companion with Live2D avatar
- have hands-free voice conversations with local LLMs
- create an AI desktop pet that talks to me
- connect an AI companion to my livestream chat
- run an offline voice assistant with long-term memory

## When to choose
- you want a fully local, privacy-preserving voice AI companion with an animated avatar
- you need cross-platform support (Windows, macOS, Linux) including Apple Silicon and non-NVIDIA GPUs
- you want rich interaction features like voice interruption, vision, MCP tools, and livestream integration
- you want pluggable backends for LLMs, ASR, and TTS

## When to avoid
- you need a production-grade, stable product - the project is still in early active development
- you only need a headless chatbot or API without a visual avatar
- you require a permissive open-source license (license is non-standard)
- you want to contribute features right now - v2 rewrite is in planning and v1 feature PRs are paused

## Facets
- artifact type: application
- maturity: active
- function: chatbot, speech-recognition, tts, llm-inference, agent-framework, mcp, chat-interface
- domain: artificial-intelligence, large-language-models, chatbots, entertainment, self-hosted
- platform: windows, cross-platform, python
- tags: ai-vtuber, live2d, ai-companion, voice-interaction, desktop-pet, vtuber, offline, neuro-sama, livestreaming, natural-language-processing, macos, linux, docker, electron, web-server

## Member repositories
- Open-LLM-VTuber/Open-LLM-VTuber (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:03.388958+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:13:16.166595+00:00, confidence not recorded.
  - readme: https://github.com/Open-LLM-VTuber/Open-LLM-VTuber (fetched 2026-08-28T04:11:03.388958+00:00, sha 04bf1d41a165)
  - homepage: https://open-llm-vtuber.github.io/ (fetched 2026-08-29T08:08:13.336264+00:00, sha 12969de3662f)
  - site_page: http://docs.llmvtuber.com/docs/intro (fetched 2026-08-29T08:08:13.345365+00:00, sha 1ffb3f805ac8)
  - site_page: http://docs.llmvtuber.com/docs/quick-start (fetched 2026-08-29T08:08:13.347760+00:00, sha d52e7c03733e)
- Data as of 2026-08-30T08:39:29.467469+00:00.