Skip to content

Releases: OuOSama/YAE-AI

🎉 First YAE-AI Release! 2025

29 Nov 08:02
@OuOSama OuOSama
v1.0.0
de329bf

Choose a tag to compare

View all tags
🎉 First YAE-AI Release! 2025 Latest
Latest

🦊 YAE-AI v1.0.0 - Initial Release

Your AI VTuber companion is finally here! ✨

🎉 What's New

This is the first official release of YAE-AI — a self-hosted AI VTuber framework that lets you run powerful language models locally with Docker and UV package manager.

✨ Core Features

  • 🐳 Docker-powered vLLM hosting — Run your models in isolated containers with ease
  • ⚡ UV package manager integration — Lightning-fast Python dependency management
  • 🎯 Character roleplay system — Built-in support for immersive VTuber personalities
  • 🔄 Multi-provider support — Easily switch between local vLLMs, ChatGPT, Claude, and Gemini
  • 🎨 Fully customizable — Adapt system prompts and configurations to match your vision

📦 What's Included

yae-ai/
├── src/
│   ├── utils/save.py      # Hugging Face model downloader
│   └── main.py            # Main application entry point
├── docker-compose.yml     # vLLM container configuration
├── pyproject.toml         # UV dependencies and project metadata
└── README.md              # Comprehensive documentation

🚀 Quick Start

# Clone the repository
git clone https://github.com/OuOSama/YAE-AI.git yae-ai
cd yae-ai

Install dependencies


uv sync


Download the model


uv run src/utils/save.py


Start vLLM containers


docker compose up -d

That's it! Your AI is now running on http://localhost:8000 🎯

💡 Usage Example

from openai import OpenAI

client = OpenAI(

api_key="mykey",

base_url="http://localhost:8000/v1"

)


response = client.chat.completions.create(

model="/model",

messages=[

{

"role": "system",

"content": "You are a charming VTuber AI assistant..."

},

{

"role": "user",

"content": "Tell me something interesting!"

}

],

temperature=0.7

)


print(response.choices[0].message.content)

🛠️ Requirements

Tool Version Purpose
Python 3.10+ Core runtime
UV Latest Package management
Docker Latest Container orchestration
Git Latest Repository cloning

📖 Documentation

Full documentation is available in the README.md, including:

  • Detailed installation guide
  • Advanced configuration options
  • Character prompt examples
  • Troubleshooting tips
  • Contributing guidelines

🐛 Known Issues

  • Model downloads can take significant time depending on internet speed
  • Docker requires at least 8GB RAM for optimal performance
  • Some models may require GPU support (configure in docker-compose.yml)

🌟 What's Next?

Check out our roadmap for upcoming features:

  • Voice synthesis integration (TTS)
  • WebUI for easier configuration
  • Multi-language support
  • Fine-tuning scripts
  • Live2D integration
  • Streaming platform integrations

💜 Community & Support

🙏 Acknowledgments

Special thanks to:

  • vLLM Team for the incredible inference engine
  • Astral for creating UV
  • The VTuber community for endless inspiration
  • All early testers and contributors ✨

📄 License

This project is licensed under the MIT License — see LICENSE for details.

<div align="center">

Built with 💜 by OuOSama

Stay based, stay creative ✨

Download Release | View Documentation | Report Issues

</div>

📝 Release Notes

Added

  • Initial project structure with UV package manager
  • Docker Compose configuration for vLLM hosting
  • Model download utility from Hugging Face
  • OpenAI-compatible API client example
  • Comprehensive README documentation
  • MIT License

Security

  • Local-first architecture keeps your data private
  • No external API calls required for model inference
  • Self-hosted deployment gives you full control

Full Changelog: https://github.com/OuOSama/YAE-AI/commits/v1.0.0

# 🦊 YAE-AI v1.0.0 - Initial Release

Your AI VTuber companion is finally here! ✨

🎉 What's New

This is the first official release of YAE-AI — a self-hosted AI VTuber framework that lets you run powerful language models locally with Docker and UV package manager.

✨ Core Features

  • 🐳 Docker-powered vLLM hosting — Run your models in isolated containers with ease
  • ⚡ UV package manager integration — Lightning-fast Python dependency management
  • 🎯 Character roleplay system — Built-in support for immersive VTuber personalities
  • 🔄 Multi-provider support — Easily switch between local vLLMs, ChatGPT, Claude, and Gemini
  • 🎨 Fully customizable — Adapt system prompts and configurations to match your vision

📦 What's Included

yae-ai/
├── src/
│   ├── utils/save.py      # Hugging Face model downloader
│   └── main.py            # Main application entry point
├── docker-compose.yml     # vLLM container configuration
├── pyproject.toml         # UV dependencies and project metadata
└── README.md              # Comprehensive documentation

🚀 Quick Start

# Clone the repository
git clone https://github.com/OuOSama/YAE-AI.git yae-ai
cd yae-ai

# Install dependencies
uv sync

# Download the model
uv run src/utils/save.py

# Start vLLM containers
docker compose up -d

That's it! Your AI is now running on http://localhost:8000 🎯

💡 Usage Example

from openai import OpenAI

client = OpenAI(
    api_key="mykey",
    base_url="http://localhost:8000/v1"
)

response = client.chat.completions.create(
    model="/model",
    messages=[
        {
            "role": "system",
            "content": "You are a charming VTuber AI assistant..."
        },
        {
            "role": "user",
            "content": "Tell me something interesting!"
        }
    ],
    temperature=0.7
)

print(response.choices[0].message.content)

🛠️ Requirements

Tool Version Purpose
Python 3.10+ Core runtime
UV Latest Package management
Docker Latest Container orchestration
Git Latest Repository cloning

📖 Documentation

Full documentation is available in the [README.md](https://github.com/OuOSama/YAE-AI/blob/main/README.md), including:

  • Detailed installation guide
  • Advanced configuration options
  • Character prompt examples
  • Troubleshooting tips
  • Contributing guidelines

🐛 Known Issues

  • Model downloads can take significant time depending on internet speed
  • Docker requires at least 8GB RAM for optimal performance
  • Some models may require GPU support (configure in docker-compose.yml)

🌟 What's Next?

Check out our [roadmap](https://github.com/OuOSama/YAE-AI#-roadmap) for upcoming features:

  • Voice synthesis integration (TTS)
  • WebUI for easier configuration
  • Multi-language support
  • Fine-tuning scripts
  • Live2D integration
  • Streaming platform integrations

💜 Community & Support

🙏 Acknowledgments

Special thanks to:

📄 License

This project is licensed under the MIT License — see [LICENSE](LICENSE) for details.

**Built with 💜 by [...

Read more
Assets 2
Loading