redamon
View on GitHubOpen-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what it finds. MCP both ways: plug in any MCP server as a tool, or drive RedAmon from Claude Code or your own agent.
Self-hosted AI penetration-testing framework that maps attack surfaces into a Neo4j graph, autonomously runs reconnaissance and exploitation with human approval gates, and can triage findings, generate fixes, and open GitHub pull requests. Supports MCP tools and clients.
Use Cases
Map an authorized target's attack surfaceRun AI-assisted penetration tests in a Kali sandboxValidate vulnerability exploitabilityTriage and deduplicate security findingsGenerate code fixes and open GitHub pull requests
Built With
- Language
- Python
- Frameworks
- LangChain · LangGraph · Neo4j · Metasploit
Tags
autonomous-agent · multi-agent · penetration-testing · red-team · attack-surface · security · MCP · human-approval · vulnerability-remediation · code-fixes