awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com

automated penetration testing agent

Ranking updated Jun 30, 2026

For an autonomous framework for penetration testing, the first results are greydgl/pentestgpt, jasonxtn/argus and redsiege/eyewitness (EyeWitness is a web reconnaissance and screenshot tool for identifying infrastructure and server headers, but it lacks AI-driven vulnerability detection, exploit generation, and modular agent architecture, so it is not an AI-assisted penetration testing framework). autorecon/autorecon and s0md3v/photon round out the shortlist. Compare the match explanations and check the project documentation against your requirements.

We curate open-source GitHub repositories matching “ai agents for penetration testing”. Results are ranked by relevance to your query — pick filters below to narrow, or refine with AI.

automated penetration testing agent

Find the best repos with AI.We'll search the best matching repositories with AI.
  • greydgl/pentestgptGreyDGL avatar

    GreyDGL/PentestGPT

    11,697View on GitHub↗

    PentestGPT is an autonomous security testing framework that leverages large language models to plan, execute, and coordinate end-to-end penetration testing engagements. By functioning as an autonomous agent, the system automates the entire testing lifecycle, from initial reconnaissance and vulnerability analysis to the generation of custom exploits and the execution of post-exploitation tasks. The platform distinguishes itself through a multi-agent orchestration system that coordinates specialized AI agents to collaborate on complex, multi-stage attack chains. It integrates multimodal context

    PentestGPT is an autonomous security testing framework that uses LLMs and a multi-agent system to automate reconnaissance, vulnerability analysis, exploit generation, and post-exploitation, fitting the search for an AI-assisted penetration testing tool with command-line and modular architecture.

    PythonInfrastructure Reconnaissance
    View on GitHub↗11,697
  • jasonxtn/argusjasonxtn avatar

    jasonxtn/Argus

    3,254View on GitHub↗

    Argus is a modular network reconnaissance framework designed for gathering network intelligence, mapping infrastructure, and assessing security postures through automated discovery tasks. It operates as a containerized security toolset that allows for the consistent execution of specialized information-gathering modules across different operating systems. The system functions as an infrastructure audit tool and a web application security scanner, performing tasks such as DNS lookups, port scanning, and the inspection of HTTP headers to detect vulnerabilities. It also serves as a threat intell

    Argus is a modular network reconnaissance framework for infrastructure mapping and vulnerability scanning, but it lacks AI agents, automated exploit generation, and report generation, making it a component of penetration testing rather than the full AI-assisted framework you are looking for.

    PythonInfrastructure ReconnaissanceReconnaissance Workflow Automation
    View on GitHub↗3,254
  • redsiege/eyewitnessRedSiege avatar

    RedSiege/EyeWitness

    5,763View on GitHub↗

    EyeWitness is a web reconnaissance framework used to identify infrastructure and software versions across multiple websites through automated headless browser scans. It functions as an HTTP website screenshotter and a security reporting tool that captures visual snapshots and server headers from a list of web targets. The system distinguishes itself by combining visual documentation with security analysis. It generates searchable HTML reports that categorize website screenshots and metadata by content system or device type, while simultaneously performing server header analysis to determine u

    EyeWitness is a web reconnaissance and screenshot tool for identifying infrastructure and server headers, but it lacks AI-driven vulnerability detection, exploit generation, and modular agent architecture, so it is not an AI-assisted penetration testing framework.

    PythonInfrastructure Reconnaissance
    View on GitHub↗5,763
  • autorecon/autoreconAutoRecon avatar

    AutoRecon/AutoRecon

    5,905View on GitHub↗

    AutoRecon is an automated network reconnaissance tool that performs concurrent port scanning and service enumeration across multiple targets. It operates as a multi-target port scanner, probing IP addresses, CIDR ranges, or hostnames in parallel, and automatically dispatches service-specific enumeration tools after port detection to gather detailed information about each open service. The tool distinguishes itself through a plugin-based scanning system that allows extending or replacing default port and service scans via a flexible plugin architecture. It provides real-time pattern-based outp

    AutoRecon is an automated reconnaissance and port-scanning tool with a plugin system, but it does not use AI agents and focuses only on the initial discovery phase, lacking the AI-driven vulnerability detection or exploitation capabilities this search targets.

    PythonReconnaissance Workflow Automation
    View on GitHub↗5,905
  • s0md3v/photons0md3v avatar

    s0md3v/Photon

    12,953View on GitHub↗

    Photon is a command-line web crawler designed for security reconnaissance and information gathering. It systematically traverses websites to discover URLs, map domain infrastructure, and identify associated subdomains by retrieving DNS records. The tool distinguishes itself through its ability to perform deep content analysis, including the extraction of sensitive data such as API keys and authentication tokens using user-defined regular expressions. It supports offline inspection by cloning crawled web content to the local filesystem, allowing for structural analysis without additional netwo

    Photon is a web crawler and information-gathering tool for reconnaissance, but it does not incorporate AI agents or automate penetration testing tasks beyond crawling, so it's a building block rather than the AI-assisted framework this search targets.

    PythonInfrastructure Reconnaissance
    View on GitHub↗12,953
  • owasp/nettackerOWASP avatar

    OWASP/Nettacker

    5,258View on GitHub↗

    Nettacker is an automated penetration testing framework designed to orchestrate reconnaissance, port scanning, and vulnerability detection. It functions as a network reconnaissance tool and vulnerability scanner that identifies open ports, fingerprints services, and checks systems against databases of known security flaws. The framework distinguishes itself by combining a web application crawler for discovering hidden paths via fuzzing with a vulnerability management system that persists scan results in a database to track historical assessments. It also includes specialized capabilities for

    Nettacker is an automated penetration testing framework for reconnaissance and vulnerability scanning, but it does not incorporate AI agents or exploit generation, so it is a traditional pentesting tool rather than an AI-assisted framework.

    PythonReconnaissance Workflow AutomationNetwork Reconnaissance Tools
    View on GitHub↗5,258
  • manisso/fsocietyManisso avatar

    Manisso/fsociety

    12,136View on GitHub↗

    fsociety is a penetration testing framework and security tool orchestrator designed to conduct full security audits. It functions as a wrapper that integrates external security binaries into a unified, menu-driven interface, providing a centralized system for command-line parameter mapping and execution. The project distinguishes itself by organizing specialized utilities into domain-specific collections for structured navigation. It automates the transition between different phases of an audit by chaining reconnaissance and exploitation tools through sequential workflow automation. The fram

    This repository is a versatile penetration testing framework that orchestrates existing security tools for reconnaissance and exploitation, but it lacks any AI-driven agents or machine learning components — it automates workflows via scripted menus rather than intelligent decision-making, so it does not meet the AI-assisted core of the query.

    PythonReconnaissance Workflow AutomationNetwork Reconnaissance Tools
    View on GitHub↗12,136
  • reconurge/flowsintreconurge avatar

    reconurge/flowsint

    6,979View on GitHub↗

    Flowsint is an open-source intelligence framework and reconnaissance orchestrator used for cybersecurity investigations. It functions as a containerized tool runner and data mapper, automating the collection of intelligence from open-source providers and APIs to profile targets and map threat intelligence. The platform distinguishes itself through a graph-based investigation interface, where processed raw intelligence is converted into nodes and edges to visualize relationships between entities. It allows for the creation of sequenced pipelines that chain data enrichment tools, enabling the o

    Flowsint is an OSINT and reconnaissance orchestrator that automates intelligence gathering, but it does not use AI agents for penetration testing, nor does it perform vulnerability detection or exploitation, so it only covers the reconnaissance part of the desired workflow.

    TypeScriptReconnaissance Workflow Automation
    View on GitHub↗6,979
  • longld/pedalongld avatar

    longld/peda

    6,130View on GitHub↗

    Peda is a security tool suite and exploit development framework designed for binary analysis, debugger automation, and memory inspection. It functions as a set of Python scripts that extend a debugger to automate the analysis of compiled files and the inspection of process memory. The project provides specialized utilities for memory corruption research, including a payload generation utility for creating cyclic patterns to discover buffer overflows and a gadget finder to locate return-oriented programming sequences within binaries. It differentiates itself by offering a visualization tool th

    Peda is an exploit development framework that extends GDB for binary analysis and memory corruption research, but it lacks AI-driven automation for reconnaissance, vulnerability detection, or modular agent architecture, so it is a specialized building block rather than the full-scope AI-assisted penetration testing tool you need.

    PythonExploit Payload Generators
    View on GitHub↗6,130
  • six2dez/reconftwsix2dez avatar

    six2dez/reconftw

    7,226View on GitHub↗

    reconftw is an attack surface management framework and reconnaissance workflow orchestrator designed to automate the discovery, mapping, and monitoring of external digital assets. It operates as a modular tool-chain pipeline that coordinates a sequence of security tools to perform intelligence gathering and vulnerability scanning. The project distinguishes itself through a cloud-native deployment model that parallelizes scanning workloads across a fleet of remote VPS instances to bypass local resource constraints. It utilizes container-based environment isolation to ensure consistent executio

    reconftw is an automated reconnaissance and attack surface management orchestrator that coordinates security tools for intelligence gathering and vulnerability scanning, but it lacks any AI or agent-driven capabilities for penetration testing, making it a neighboring tool rather than an AI-assisted framework.

    ShellInfrastructure ReconnaissanceReconnaissance Workflow Automation
    View on GitHub↗7,226
  • jaykali/maskphishjaykali avatar

    jaykali/maskphish

    3,020View on GitHub↗

    Maskphish is a comprehensive security toolkit that integrates capabilities for digital forensics, network vulnerability scanning, open-source intelligence, penetration testing, and social engineering. It functions as a multi-purpose framework for automating reconnaissance and executing security audits across diverse network environments. The project features a specialized phishing and social engineering toolkit used for cloning websites, masking URLs, and deploying deceptive pages to capture user credentials. It also includes a remote access Trojan builder for generating platform-specific exe

    Maskphish is a multi-purpose security toolkit for reconnaissance, scanning, and social engineering, but it does not incorporate AI agents for automated penetration testing as requested.

    ShellInfrastructure ReconnaissanceReconnaissance Workflow AutomationNetwork Reconnaissance Tools
    View on GitHub↗3,020
  • projectdiscovery/naabuprojectdiscovery avatar

    projectdiscovery/naabu

    5,766View on GitHub↗

    Naabu is a port scanner library and tool that probes hosts for open ports using SYN, CONNECT, and UDP methods to identify active services. It functions as a Go library for embedding port scanning into programs, and as a standalone tool that accepts targets as hostnames, IP addresses, CIDR ranges, or ASN numbers. The tool discovers live hosts before scanning, filters ports by range or top lists, and can integrate with Nmap for service version detection. The project distinguishes itself through its SYN-based port probing approach that sends TCP SYN packets and analyzes responses without complet

    Naabu is a fast port scanner that can assist with network reconnaissance as part of a penetration test, but it is not an AI-assisted framework—it lacks automated vulnerability detection, exploit generation, and the agent-based architecture this search requires.

    GoNmap IntegrationNmap Integration
    View on GitHub↗5,766
Compare the top 10 at a glance
RepositoryStarsLanguageLicenseLast push
greydgl/pentestgpt11.7KPythonmitFeb 18, 2026
jasonxtn/argus3.3KPythonmitDec 10, 2025
redsiege/eyewitness
5.8K
Python
GPL-3.0
Jan 5, 2026
autorecon/autorecon5.9KPythongpl-3.0Jan 28, 2026
s0md3v/photon13KPythonGPL-3.0Feb 10, 2026
owasp/nettacker5.3KPythonApache-2.0Jun 19, 2026
manisso/fsociety12.1KPythonMITAug 8, 2024
reconurge/flowsint7KTypeScriptApache-2.0Jun 22, 2026
longld/peda6.1KPythonNOASSERTIONJul 29, 2024
six2dez/reconftw7.2KShellmitFeb 20, 2026

Related searches

  • an open source toolkit for penetration testing
  • a framework for building autonomous AI agents
  • a framework for building autonomous AI agents
  • a framework for building autonomous AI agents
  • a security framework for penetration testing operations
  • Autonomous AI agents
  • a framework for building autonomous AI agents
  • open source ai agent framework