redamon

Overview of redamon

What it is

RedAmon is an open-source, self-hosted AI penetration testing framework. It maps an 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.

Key features

• Maps attack surface into a living Neo4j knowledge graph.
• Autonomous exploitation from a Kali sandbox with human approval gates.
• Opens pull requests with code fixes via the CodeFix agent.
• MCP both ways: plug in any MCP server as a tool, or drive RedAmon from Claude Code or your own agent.
• Dynamic multi-tool parallel recon pipeline that coordinates tools in real time.
• AI triage (CypherFix) correlates findings, deduplicates, and ranks by exploitability.
• Solves 101 / 104 (97.1%) of the XBOW web-security benchmark fully black-box.

Use cases

Authorized security testing, educational purposes, and research only. Bug bounty coverage audit (397 classes of web bug-bounty findings). Automated vulnerability assessment and fix generation.

Getting started

bash git clone https://github.com/samugit83/redamon.git cd redamon # Without GVM (lighter, faster startup): ./redamon.sh install # With GVM / OpenVAS (full stack, ~30 min first run): ./redamon.sh install --gvm After installation, create an admin account when prompted, then open http://localhost:3000 and sign in.

License and pricing

License: MIT. Open source, free to use.

Based on the project's public README and repository metadata.