Autonomous Pentest Agent

Autonomous Pentest Agent is an autonomous penetration testing system driven by multiple LLM agents with a Go backend and Next.js frontend.

Autonomous Pentest Agent is an autonomous penetration testing system driven by multiple LLM agents, featuring a Go backend and a Next.js frontend. It runs tasks using a dual-graph architecture consisting of an asset graph for global truth and an exploration graph for task execution. Planners manage a shared todolist for stable attack chains, and workers exchange execution process information to prevent duplicate effort. Users can synchronize assets from ScopeSentry, configure LLM providers, and manage human-in-the-loop approvals. The system supports PostgreSQL for data storage and provides a web interface for dashboards, task lists, and vulnerability testing.

Autonomous Pentest Agent at a glance

Best for: Software engineer
Runs on: Web, Docker, Linux, macOS, Windows, CLI, API, self-hosted, open source
Pricing: Free
Released: October 2026
Category: AI coding tool
Website: github.com/kutukam/autonomous-pentest-agent

Key features

Dual-graph architecture for assets and exploration
Multi-step attack planning with shared todolist
Asset synchronization with ScopeSentry
Human-in-the-loop approval workflows
Worker process-level information exchange
Vulnerability re-testing and verification
Traffic recording and proxy management

Use it for

Synchronize and explore company assets
Execute automated penetration testing tasks
Verify vulnerabilities with re-testing agents
Manage approvals for sensitive operations

Alternatives to Autonomous Pentest Agent

ARTEX — Runs autonomous multi-agent penetration testing with a dual-graph architecture.
PentestGPT — Runs autonomous multi-stage pipelines or interactive multi-LLM workflows for security tests.
PentAGI — It autonomously manages penetration testing workflows within a secure Docker sandbox.
Pentest AI — Eliminates false positives by reproducing every exploit three times.
Artex Global — Autonomous multi-agent penetration testing with multilingual output support.
ARTEX main — It uses an independent dual-graph architecture and an automated discovery engine.
ARTEX — Manages autonomous penetration testing tasks and tracks vulnerability progress.
VulnClaw — It uses LLM agents to autonomously execute end-to-end security testing loops.
PentesterFlow — Pentest agent that runs on local models and writes findings
CyberStrike — Autonomous AI agents execute recon, web, network, and cloud penetration testing.
CodeAnt AI — It uses agentic testing to prove exploitability with actionable reproduction steps.
Polylane — It autonomously investigates production errors and submits ready-to-merge PR fixes.

All Autonomous Pentest Agent alternatives