WinterAI is a personal AI chatbot powered by Gemini LLM for Telegram, designed to be a calm and intelligent companion that representing reserved personality.
While WinterAI provides a smooth chatting experience, there are some current limitations:
- Static Prompting – Personality and responses rely on predefined system prompts (not fully adaptive).
- No Long-Term Memory – Conversations reset after sessions (unless manually integrated with a database).
- API Dependency – Requires a valid LLM API key and stable internet connection to function.
- Limited Privacy – Data is processed through third-party LLM APIs (depending on your provider).
- Single-Personality Mode – Currently limited to one persona (calm, intelligent, emotionally reserved).
-
Clone the repository
git clone <your-repo-url> cd <your-repo-directory>
-
Install dependencies
pip install -r requirements.txt
-
Set up environment variables
- Copy the example environment file:
cp .env.example .env - Edit
.envand add your actual API keys:TELEGRAM_API_KEY: Get from @BotFather on TelegramGEMINI_API_KEY: Get from Google AI Studio
- Copy the example environment file:
-
Run the bot
python WinterAI.py
- Never commit your
.envfile to version control - The
.envfile is automatically ignored by.gitignore - Use the provided
.env.exampleas a template for setting up your environment
- AI-powered responses using Google Gemini
- Knowledge base integration
- Safety settings for content filtering
- Persistent conversation handling