Open-LLM-VTuberAI companion with voice conversations, visual input, and Live2D avatars, supporting local and hosted language and speech models.
AI companion with voice conversations, visual input, and Live2D avatars, supporting local and hosted language and speech models.
Open-LLM-VTuber combines voice conversations, visual input and a Live2D character in a web interface or desktop client. Users can customize the character and choose speech recognition, language-model and speech-synthesis backends, including local models for offline operation. It runs on Windows, macOS and Linux, retains chat logs, and offers a transparent desktop-pet mode.
Open-LLM-VTuber official README · Reviewed 2026-10-29
- 01 / Feature noteVoice and visual interaction
The companion accepts spoken conversation and visual input from cameras, screen recordings or screenshots.
Feature source ↗ - 02 / Feature noteDesktop pet mode
The desktop client supports a transparent, always-on-top character with mouse click-through.
Feature source ↗
GitHub stars
14,572
Detected license
Unknown
i
Not reported by GitHub.
Verify against official terms.
Repository created
2023-11-24
Repository push
2026-05-15
2023-11-24GitHub release
2025-08-26 · v1.2.1Repository push
2026-05-15
GitHub stars
Unknown
i
Cached history uses a different month window; chart withheld until aligned.
Latest attempt: ok · Checked 2026-10-15T18:22:24.727650+00:00 · Last successful fetch 2026-10-15T18:22:24.727650+00:00 · Provider source
Hacker News stories
Unknown
i
OpenSSF Scorecard
Unknown
i
No result returned.
Checked 2026-10-27T03:01:39Z · Latest attempt: not found · Provider source
GitHub release
Published 2025-08-26
i
Checked 2026-11-04T04:26:56Z · Last successful fetch 2026-11-04T04:26:56Z · Value fetched 2026-11-04T04:26:56Z · Provider source
Unknown

