Project J.A.I.son

Core server for building AI Companion applications.

About This Project • Key Features • Applications • Install From Scratch • Operations • How To Use • Developer Guide • Community • Credits • License

About This Project

This project is for a fully customizable AI persona usable for streaming or private companionship. Feel free to download and use how you wish.

This software uses libraries from the FFmpeg project under the LGPLv2.1

Key Features

• Realtime promptable AI personality with text and speech input
• Support for MCP
• REST API and websocket server for building applications on top of this server
• Options to run fully local

Official Applications

• Discord bot integration
• VTube Studio with emotions
• Twitch Chat and Events content provider

Feel free to build and share your own! See the Developer Guide for more info.

Install From Scratch

Note To simplify setup across platforms, setup now uses conda. Conda is not necessary to run this project.

Setup and install dependencies

Create and enter a virtual environment with Python ^3.10 and pip 24.0.

For example, using conda:

conda create -n jaison-core python=3.10 pip=24.0 -y
conda activate jaison-core

---

Install PyTorch 2.7.1 with the right integration. Example below for computers with RTX graphics card.

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128

For NVidia cards, ensure you have the latest drivers and CUDA toolkit

Dealing with duplicate libiomp5md.dll.

It might not be necessary, but in case you encounter this error when running:

1. Go to environment directory (where conda stores installed packages)
2. Search for libiomp5md.dll
3. Delete the version under package torch

---

Install dependencies.

# Inside project root where this README is located
pip install -r requirements.txt
pip install --no-deps -r requirements.no_deps.txt
python -m spacy download en_core_web_sm
python install.py
python -m unidic download

If on Windows, please enable Developer Mode

---

Install FFmpeg

For Ubuntu/Debian users

sudo apt install ffmpeg

For MacOS users

brew install ffmpeg

For Windows users

Download executables and place them in the root folder:

• Download latest ffmpeg-git-essentials.7z
• Extract and copy all contents from bin/ to root of this project.

---

Configuration

FOR A FREE, 3RD PARTY T2T INTEGRATION: Use openai type but configure for use with Groq.

Add keys and other sensitive information for services you intend to use in .env (make a new file and copy the contents of .env-template).

For immediate setup using the example configuration, just provide the OpenAI API key.

Overall configuration can be done in configs/ and an example with all configurable options is located in configs/example.yaml. See Development guide for details on configuration.

How To Use

While using the virtual environment with the installation.

python ./src/main.py --help

Example usage: python ./src/main.py --config=example

Developer Guide

See the specification for building applciations for Project J.A.I.son, creating custom integrations, and configuration tips below:

• REST API spec
• Development guide
• Contributing guidelines

Community

Join the community!

• Discord
• Youtube
• Twitch

Thank you to all the contributors!

Become a contributor as well

License

MIT