An LLM-driven autonomous penetration testing agent. Plan to Act to Observe to Reflect to Report. Read-only recon, 8 tools, multi-provider LLM, professional pentest reports.

ai-agent ai-security anthropic claude cybersecurity infosec llm mcp model-context-protocol nvd ollama openai owasp penetration-testing pentest reconnaissance redteam security-tools sigma-rules vulnerability-scanner
1 Open Issue Need Help Last updated: Jul 1, 2026

Open Issues Need Help

View All on GitHub
documentation good first issue

An LLM-driven autonomous penetration testing agent. Plan to Act to Observe to Reflect to Report. Read-only recon, 8 tools, multi-provider LLM, professional pentest reports.

Python
#ai-agent#ai-security#anthropic#claude#cybersecurity#infosec#llm#mcp#model-context-protocol#nvd#ollama#openai#owasp#penetration-testing#pentest#reconnaissance#redteam#security-tools#sigma-rules#vulnerability-scanner