This project addresses the challenge of comprehensive subdomain enumeration and reconnaissance by integrating passive sources, active probing, and advanced security checks into a single tool. It offers an AI-powered analysis layer using local LLMs for vulnerability detection and reporting, targeting security researchers, penetration testers, and bug bounty hunters seeking a private, cost-effective, and feature-rich solution.

How It Works

God's Eye combines over 20 passive subdomain sources with DNS brute-forcing and HTTP probing to map a target's attack surface. Its core innovation lies in its integration with Ollama, enabling local, private AI analysis. This allows for intelligent vulnerability detection, CVE matching, JavaScript code review, and the generation of executive reports without relying on external APIs or incurring costs. The AI component uses a multi-agent orchestration system for specialized analysis of findings.

Quick Start & Requirements

• Installation: Clone the repository (git clone https://github.com/Vyntral/god-eye.git), navigate into the directory (cd god-eye), and build the binary (go build -o god-eye ./cmd/god-eye).
• Basic Usage: ./god-eye -d target.com
• AI-Powered Usage: Requires Ollama installation (curl https://ollama.ai/install.sh | sh), pulling models (ollama pull deepseek-r1:1.5b && ollama pull qwen2.5-coder:7b), starting the Ollama server (ollama serve &), and then running the tool (./god-eye -d target.com --enable-ai).
• Prerequisites: Go 1.21 or higher. Ollama and specific LLM models are required for AI features.
• Resource Footprint: AI models require significant disk space (approx. 9GB) and memory during operation.
• Links: Repository: https://github.com/Vyntral/god-eye.git

Highlighted Details

• Integrates 20 passive sources, DNS brute-forcing, and HTTP probing.
• Features 100% private, zero-cost AI analysis via local Ollama LLMs.
• Performs comprehensive security checks, including WAF detection, TLS appliance fingerprinting, and subdomain takeover detection (110+ fingerprints).
• AI capabilities include real-time CVE detection, JavaScript secret extraction, and multi-agent specialized analysis.
• Offers stealth modes for evasion during authorized testing.

Maintenance & Community

The project is authored by Vyntral and associated with the Orizon organization. No specific community channels (e.g., Discord, Slack) or roadmap links are provided in the README.

Licensing & Compatibility

The project is licensed under the MIT License with additional terms, detailed in the LICENSE file. Users should review these terms for specific compatibility notes regarding commercial use or closed-source linking, as they may impose restrictions beyond the standard MIT license.

Limitations & Caveats

The AI features necessitate the installation and configuration of Ollama and downloading large language models, which can be time-consuming and resource-intensive. The tool is strictly intended for authorized security testing, with a prominent legal disclaimer emphasizing user responsibility and compliance with applicable laws (e.g., CFAA, Computer Misuse Act). The "additional terms" to the MIT license require careful review for any potential usage restrictions.