RedAmon

Overview

Open-source, self-hosted AI penetration testing framework. It maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens pull requests that fix what it finds. It supports MCP both ways: plug in any MCP server as a tool, or drive RedAmon from Claude Code or your own agent.

Best for

Best for
Security teams wanting an open-source, agent-driven pentesting framework with human oversight

Use cases

• Map an organization's attack surface into a graph for analysis
• Run autonomous penetration tests with human approval checkpoints
• Integrate MCP servers as tools or orchestrate RedAmon from an external agent

Notes

Open-source, self-hosted AI penetration testing framework. It maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens pull requests that fix what it finds. It supports MCP both ways: plug in any MCP server as a tool, or drive RedAmon from Claude Code or your own agent.

2,918 stars on GitHub. Last updated 2026-10-03. Licensed MIT.

Use cases

• Map an organization’s attack surface into a graph for analysis
• Run autonomous penetration tests with human approval checkpoints
• Integrate MCP servers as tools or orchestrate RedAmon from an external agent

Pros

• Self-hosted and open-source with full control over infrastructure
• Human approval gates reduce risk during autonomous exploitation
• Bidirectional MCP support enables flexible agent integration

Cons

• Requires self-hosting, setup, and ongoing maintenance
• Python-only codebase may limit adoption in non-Python shops
• Community project with no commercial support or SLA

Indexed from awesome-langchain and enriched against its public facts.