garycaogan/gary-ai-live-avatar
App
Can I trust it?
No red flags in our checks.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change yesterday.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A Python project that runs an AI digital host live: it filters viewer danmaku, queues messages so the avatar answers one at a time, and handles outfit changes, simple gestures, idle topics and an OBS overlay. The avatar itself is generated by Vidu S2 real-time digital human, and…
Who it's for
Developers building AI live-streaming avatars with Vidu S2 and OBS overlays
How to use it
Install
cd ai-live-avatar && python3 -m venv .venv && .venv/bin/pip install -r requirements.txtFrom its README. Check it there before running it.
Ready-made installers, when the project publishes them, are on its latest release.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up garycaogan/gary-ai-live-avatar in my project. Follow its README: https://github.com/garycaogan/gary-ai-live-avatar. Explain each step and check it is safe before running anything.
Star curve
On the radar
Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.
Records
- Best place on RepoAlerts: #44, on 21 Oct 2026
Get alerts for repos like this
We'll email you when something in Creative tools starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/garycaogan/gary-ai-live-avatar?ref=badge)Similar repos
- cyber-xiaoya/cyber-xiaoya-live
A component-based digital human live-streaming system using Vidu s2 for rendering. It runs a local FastAPI bridge that routes viewer danmaku, LLM replies and local TTS audio to Vidu, with a browser st
- openspline/openspline
Python and Node SDK that adds a realtime lip-synced avatar video to a voice AI agent. Generates synchronized video and speech from a portrait and audio, on OpenSpline Cloud or a self-hosted NVIDIA GPU
- rhfbgfgfdg999999/3d-printer-live
Browser-based visualization that shows viewers' avatars being 3D printed layer by layer during a live stream. Comments, likes and gifts from Douyin, Kuaishou or TikTok rooms queue prints, and a local
- livliv-dev/stage
A TypeScript studio for giving AI characters a personality and running them as chatbots or live-streamed VTubers. It supports long-term memory, real-time voice chat, Neuro SDK integration, webcam face
- jacke-pp/open-yoki
A self-hosted AI live-stream host that runs on one server. It speaks with a cloned voice and a real-time digital avatar, replies to chat comments, keeps memory of regular viewers, writes diary entries
- tequed232/DSH-L2D
A Live2D character runtime for DeepSeek Harness that drives a model's gaze, expressions and motions from semantic behavior intents. It includes an action queue with priorities, a model capability prof