What problem does it solve? Manual penetration testing requires coordinating dozens of security tools, interpreting their output, and writing reports by hand. Guardian automates this by using AI agents to plan, execute, and analyze security assessments step by step with evidence capture. ## Core Features & Use Cases - AI-Driven Workflows: Multi-agent architecture (Planner, Tool Selector, Analyst, Reporter) coordinates tools like Nmap, Nuclei, httpx, and Gobuster using OpenAI, Claude, Gemini, or OpenRouter. - Built-in and Custom Workflows: Run pre-configured web pentest, network assessment, recon, and autonomous modes, or define custom YAML workflows and Python tool integrations. - Evidence-Based Reporting: Generate Markdown, HTML, or JSON reports from sessions with captured commands and findings. - Use Case: A security engineer runs python -m cli.main workflow run --name web_pentest --target example.com to probe HTTP services, fingerprint technologies, scan for vulnerabilities, and produce a report with AI-analyzed findings. ## Quick Start Ask the AI to run a Guardian web penetration test workflow against an authorized target domain and generate a Markdown report of the findings.
