AI-Powered
Penetration Testing

The autonomous security agent that thinks like an attacker. Multi-agent AI with persistent memory, 20+ LLM providers, and 18 built-in pentest tools.

0
Pentest Tools
0
LLM Providers
0
Knowledge Packs
0
AI Agents

Latest Release v0.2.4 · MIT License · Cross-Platform

Built by P Ganesh Krishna Reddy

Security researcher and full-stack developer passionate about offensive security and AI.

P Ganesh Krishna Reddy

P Ganesh Krishna Reddy

Security Researcher · Full-Stack Developer · AI Enthusiast

Building autonomous security testing tools to help ethical hackers and security researchers work smarter. Focused on AI-powered offensive security, multi-agent architectures, and making pentesting accessible to everyone.

Three steps to autonomous pentesting

Point it at a target and let the AI do the rest.

1

Target

Give PentestCode a target and an objective. It understands natural language.

2

Orchestrate

AI agents plan the attack, dispatch specialists, and coordinate in parallel.

3

Report

Get a complete report with evidence, attack paths, and remediation advice.

Built for security professionals

Everything you need for thorough, autonomous penetration testing.

🤖

AI Powered

Claude, GPT-4, Gemini and 20+ providers make intelligent security decisions.

Learn more →
🧠

Persistent Memory

Remembers hosts, services, credentials, and attack paths across sessions.

Learn more →
📚

Knowledge Packs

19 curated packs covering every attack surface and pentest methodology.

Learn more →
🔧

Tool Integrations

Built-in parsers for nmap, nuclei, sqlmap, bloodhound, gobuster, and more.

Learn more →
🗺️

Attack Planning

Cost-based path finding through relationship graphs with graph algorithms.

Learn more →

Autonomous Agents

13 specialized agents working in parallel for faster, deeper testing.

Learn more →

Multi-agent orchestration

A strategist-coordinator dispatches specialist agents in parallel.

Input
You → Natural Language Command
AI Core
PentestCode Orchestrator
Planning
Strategist → Task Decomposition
🔍 Recon
📡 Scanner
⚔️ Exploiter
🔑 Identity
📊 Reporter
🌐 WebApp
Output
Results → Report & Attack Paths

See it in action

Watch PentestCode autonomously test a target.

pentestcode — bash

Why PentestCode wins

See how it compares to traditional approaches.

Feature PentestCode Manual Testing Other AI Tools
Speed ★★★★★ ★★ ★★★
Automation ✓ Full ✗ None ✓ Partial
Multi-Agent ✓ 13 agents
Persistent Memory ✓ Full state
AI Planning ✓ Graph-based ✓ Basic
LLM Providers 20+ N/A 1-3
Cost Free (MIT) High (labor) $$

Proven results

4.3x
Faster than single agents
87%
Fewer provider overloads
75%
Token reduction
100%
Open source

Trusted by security professionals

"PentestCode saved me hours on my last engagement. The multi-agent architecture found things I would have missed."

SR
Security Researcher
Independent Consultant

"The persistent memory is a game-changer. I can pause a session, come back days later, and pick up exactly where I left off."

BB
Bug Bounty Hunter
Top 100 on HackerOne

"Finally, an AI tool that actually understands offensive security. The knowledge packs are incredibly well-researched."

DS
DevSecOps Engineer
Fortune 500 Company

Works with your stack

What's coming next

✓ Completed
Multi-Agent Architecture
13 specialized agents with parallel execution
✓ Completed
Persistent Engagement State
Full memory of hosts, services, and attack paths
🚧 In Progress
Cloud Provider Integration
AWS, Azure, GCP scanning and enumeration
📅 Planned
Browser Automation Agent
Automated web app testing with headless browser
📅 Planned
Team Collaboration
Multi-user engagements with shared state
📅 Planned
VS Code Extension
Run PentestCode directly from your editor
📅 Planned
Plugin Marketplace
Community-built tools and knowledge packs

Frequently asked questions

What LLM providers are supported?+
PentestCode supports 20+ providers including Anthropic (Claude), OpenAI (GPT-4), Google (Gemini), Mistral, Ollama, DeepSeek, xAI, OpenRouter, LM Studio, and more.
Is PentestCode free to use?+
Yes. PentestCode is fully open-source under the MIT license. You only need to pay for your LLM provider API usage.
What platforms are supported?+
PentestCode runs on Linux (x64, ARM64), macOS (Intel, Apple Silicon), and Windows (x64). Pre-built binaries are available for all platforms.
How does the multi-agent architecture work?+
A coordinator agent breaks the engagement into tasks and dispatches 13 specialist agents (recon, scanner, exploiter, etc.) in parallel. Each agent has its own tools and knowledge.
Can I use it for bug bounties?+
Absolutely. PentestCode is designed for ethical hacking, bug bounty programs, CTF competitions, and authorized penetration testing.

Get PentestCode

Available for all major platforms.

Platform Architecture Download Size
Linux x64 pentestcode-linux-x64.tar.gz 47.5 MB
Linux ARM64 pentestcode-linux-arm64.tar.gz 47.1 MB
macOS ARM64 (Apple Silicon) pentestcode-darwin-arm64.zip 32.2 MB
macOS x64 (Intel) pentestcode-darwin-x64.zip 34.7 MB
Windows x64 pentestcode-windows-x64.exe 129.6 MB

Ready to automate your penetration testing?

Join security researchers who trust PentestCode for autonomous AI-powered testing.

Download PentestCode View on GitHub