Drana-Infinity is a locally hosted advanced AI assistant designed and developed by IHA089.
It’s built specifically for cybersecurity, ethical hacking, and bug bounty research — empowering researchers to analyze, automate, and understand real-world vulnerabilities.
Drana-Infinity runs entirely offline and integrates directly with Ollama using a custom locally hosted AI model — IHA089/drana-infinity-v1.
It allows you to chat, execute commands, upload files, and organize research — all within a secure, private environment.
To ensure smooth performance when running Drana-Infinity and your local AI model, your system should meet the following:
| Category | Minimum | Recommended |
|---|---|---|
| CPU | 8-core processor | 12-core or higher |
| RAM | 16 GB | 32 GB or higher |
| GPU (optional) | NVIDIA GPU with ≥ 8 GB VRAM | RTX 3060 Ti / 4070 or higher |
| Storage | 15 GB free | SSD with 30 GB+ free |
| OS | Linux | Kali Linux |
| Python | 3.10+ | Latest 3.x stable version |
💡 Works on CPU-only systems (slower responses). GPU recommended for real-time AI streaming.
Follow these steps carefully 👇
git clone https://github.com/IHA089/drana-infinity.git
cd drana-infinitypython3 -m venv venv
# Activate the environment
source venv/bin/activatepip install -r requirements.txtDownload and install Ollama from the official website:
ollama run IHA089/drana-infinity-v1Verify that it’s available:
ollama listollama servepython3 drana_infinity.py