RedAmon

RedAmon is an open-source autonomous AI penetration testing platform that maps attack surfaces and executes attacks.

RedAmon is an open-source, self-hosted AI penetration testing platform built for security teams. It maps a target's attack surface into a Neo4j graph database using a parallelized recon engine. A fireteam of autonomous AI specialists then queries that graph in real time to plan, exploit, and pivot. The platform runs entirely inside isolated Docker containers with strict privilege separation, rule of engagement parsing, and human-in-the-loop approval gates for dangerous tools. It supports various automated tools including Nuclei, Nmap, Metasploit, and custom code execution.

RedAmon at a glance

Best for: Software engineer
Runs on: Web, Linux, self-hosted, open source
Pricing: Free and open-source
Released: December 2025
Category: AI coding tool
Website: redamon.org

Key features

Maps attack surfaces into a graph database
Executes autonomous AI pentesting workflows
Enforces human approval gates for dangerous tools
Runs fully isolated inside Docker containers
Parses rules of engagement into constraints
Integrates 26 agent tools and Kali catalog
Maintains append-only audit trails

Use it for

Mapping external domain and port attack surfaces
Executing automated black-box web vulnerability scans
Testing applications for CVEs and configuration flaws
Verifying security controls with isolated sandboxes

Alternatives to RedAmon

ARTEX — Runs autonomous multi-agent penetration testing with a dual-graph architecture.
PentAGI — It autonomously manages penetration testing workflows within a secure Docker sandbox.
HackerOne — Combines AI agents with expert human researchers to prioritize and fix real risks.
CyberStrike — Autonomous AI agents execute recon, web, network, and cloud penetration testing.
Autonomous Pentest Agent — Dual-graph architecture for asset synchronization and multi-step attack planning.
AiSOC — Runs locally without API keys with bundled models and auditable reasoning ledgers.
Daytona — It provisions sandboxes in under 90 milliseconds with full security isolation.
Dsh Infinite Gen 4 — It runs dual-layer prompt injection for deep security auditing and reverse engineering.
CodeAnt AI — It uses agentic testing to prove exploitability with actionable reproduction steps.
VulnClaw — It uses LLM agents to autonomously execute end-to-end security testing loops.
Pentest AI — Eliminates false positives by reproducing every exploit three times.
Reticle — Verifies agent code changes by replaying application flows.

All RedAmon alternatives