OpenHeavy

A multi-agent AI chat application, simulation of grok heavy.

Example of working

(1 agents working, 1 agent finish work)

(final response)

🚀 Quick Start

Prerequisites

• Python 3.8+
• pip package manager
• Access to OpenAI-compatible API (NVIDIA API configured by default)
• SearXNG search service running on localhost:8888 (for web search functionality)

Installation

1. Clone and navigate to the project:

   git clone https://github.com/valerka1292/OpenHeavy.git
   cd OpenHeavy

2. Install dependencies:

   make install
   # or manually:
   pip install -r requirements.txt

3. Configure environment:

   cp .env.example .env
   # Edit .env with your API keys and settings

   Required settings in .env:

   # LLM API Configuration
   BASE_URL=https://integrate.api.nvidia.com/v1
   MODEL=qwen/qwen3-235b-a22b
   
   # Required API Keys
   API_KEY=your_actual_api_key_here
   FLASK_SECRET_KEY=your_secret_key_here

   Optional settings:

   # Search API (for web search functionality)
   SEARCH_API_URL=http://localhost:8888/search
   
   # Flask settings
   FLASK_PORT=5000
   FLASK_DEBUG=false
   
   # Logging
   LOG_LEVEL=INFO
   LOG_FORMAT=json

4. Run the application:

   make run
   # or manually:
   python src/main.py

5. Open your browser: Navigate to http://localhost:5000