# GreyDGL/PentestGPT

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/greydgl-pentestgpt).**

11,697 stars · 1,953 forks · Python · mit

## Links

- GitHub: https://github.com/GreyDGL/PentestGPT
- awesome-repositories: https://awesome-repositories.com/repository/greydgl-pentestgpt.md

## Topics

`large-language-models` `llm` `penetration-testing` `python`

## Description

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, synthesizing both visual and textual data to inform its decision-making process. To ensure consistency and continuity, the framework maintains persistent session state, allowing users to pause and resume assessments without losing critical context or progress.

The system provides a comprehensive suite of capabilities for managing external security utilities, including the ability to parse raw command-line output into structured data for automated analysis. It operates within isolated, containerized environments to ensure that testing workflows remain reproducible and secure across diverse target architectures.

## Tags

### Security & Cryptography

- [Penetration Testing Platforms](https://awesome-repositories.com/f/security-cryptography/penetration-testing-platforms.md) — Uses large language models to plan, execute, and coordinate autonomous multi-stage cyber attacks.
- [Penetration Testing Frameworks](https://awesome-repositories.com/f/security-cryptography/penetration-testing-frameworks.md) — Automates the entire penetration testing lifecycle by interpreting tool output and generating context-aware exploitation strategies.
- [Exploitation Frameworks](https://awesome-repositories.com/f/security-cryptography/exploitation-frameworks.md) — Analyzes target data to generate custom exploits and execute payloads against identified system weaknesses. ([source](https://pentestgpt.com/index.html))
- [Exploit Frameworks](https://awesome-repositories.com/f/security-cryptography/security/utilities/security-tools/offensive-red-team/offensive-security-frameworks/exploit-frameworks.md) — Generates custom exploit code and payloads in real-time to address specific vulnerabilities discovered during testing. ([source](https://pentestgpt.com/research.html))
- [Agentic Session Persistence](https://awesome-repositories.com/f/security-cryptography/identity-access-management/session-management/stateful-session-persistence/agentic-session-persistence.md) — Maintains persistent session state to allow users to pause and resume complex security assessments without losing context.
- [Infrastructure Reconnaissance](https://awesome-repositories.com/f/security-cryptography/infrastructure-reconnaissance.md) — Performs automated reconnaissance to discover targets, scan ports, and enumerate services for critical attack vectors. ([source](https://pentestgpt.com))
- [Penetration Testing Suites](https://awesome-repositories.com/f/security-cryptography/security/utilities/security-tools/offensive-red-team/offensive-security-frameworks/penetration-testing-suites.md) — Analyzes security context to generate logical testing steps and formulate effective penetration testing strategies. ([source](https://pentestgpt.com/paper.html))
- [Vulnerability Scanners](https://awesome-repositories.com/f/security-cryptography/security/utilities/security-tools/vulnerability-assessment-tools/vulnerability-scanners.md) — Identifies and assesses security weaknesses across attack surfaces using automated reasoning to determine exploitability. ([source](https://pentestgpt.com))
- [Post-Exploitation Tools](https://awesome-repositories.com/f/security-cryptography/security/utilities/security-tools/offensive-red-team/offensive-security-frameworks/post-exploitation-tools.md) — Automates privilege escalation and lateral movement techniques to maintain control after initial system compromise. ([source](https://pentestgpt.com))
- [Security Testing](https://awesome-repositories.com/f/security-cryptography/vulnerability-assessment-testing/security-testing-auditing/security-testing.md) — Provides persistent session context to allow security teams to pause, resume, and refine testing strategies over extended periods.

### Artificial Intelligence & ML

- [Autonomous Task Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-task-execution.md) — Executes autonomous penetration tests by planning and adapting to target responses without manual step-by-step guidance. ([source](https://pentestgpt.com))
- [Multi-Agent Orchestration Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-orchestration-systems.md) — Coordinates specialized AI agents to collaborate on complex, multi-stage attack chains during security assessments.
- [Multi-Agent Coordination Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems.md) — Orchestrates specialized agents to share context and collaborate on complex, multi-stage attack chains. ([source](https://pentestgpt.com/research.html))
- [Multi-Agent Task Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-task-orchestrators.md) — Coordinates specialized autonomous agents to collaborate on complex, multi-stage attack chains during security engagements.
- [Reasoning Models](https://awesome-repositories.com/f/artificial-intelligence-ml/reasoning-models.md) — Utilizes advanced reasoning models to process target data and formulate logical, multi-step penetration testing strategies.
- [Multimodal Agent Capabilities](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-agent-capabilities.md) — Integrates multimodal analysis to combine visual and textual data for comprehensive security assessments. ([source](https://pentestgpt.com/research.html))
- [Multimodal Integration Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-integration-frameworks.md) — Synthesizes visual and textual data to perform comprehensive analysis across complex attack surfaces.
- [Tool Output Processors](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-calling-integration-frameworks/tool-output-processors.md) — Parses raw command-line output from security tools into structured data for automated analysis and decision-making. ([source](https://pentestgpt.com/paper.html))

### DevOps & Infrastructure

- [Security Assessment Frameworks](https://awesome-repositories.com/f/devops-infrastructure/security-automation-workflows/security-assessment-frameworks.md) — Automates end-to-end security assessments from initial reconnaissance to post-exploitation using an autonomous pipeline. ([source](https://pentestgpt.com/index.html))
- [Containerized Execution Environments](https://awesome-repositories.com/f/devops-infrastructure/containerized-execution-environments.md) — Provides isolated, containerized runtime environments to ensure consistent and secure execution of security assessment tools.

### Testing & Quality Assurance

- [Autonomous Penetration Testing](https://awesome-repositories.com/f/testing-quality-assurance/software-testing/testing-frameworks/end-to-end-testing-suites/end-to-end-testing-frameworks/autonomous-penetration-testing.md) — Automates the entire penetration testing lifecycle, including reconnaissance, vulnerability analysis, and exploitation, without constant manual oversight.
- [Test Automation Tools](https://awesome-repositories.com/f/testing-quality-assurance/automation-interaction-tools/test-automation-tools.md) — Automates strategic penetration testing decisions to reduce the need for constant human intervention during the assessment lifecycle. ([source](https://pentestgpt.com/research.html))
- [Ephemeral Testing Environments](https://awesome-repositories.com/f/testing-quality-assurance/testing-infrastructure-management/test-infrastructure/ephemeral-testing-environments.md) — Manages isolated containerized testing environments to ensure reproducible workflows across different projects. ([source](https://pentestgpt.com))

### Development Tools & Productivity

- [Isolated Execution Environments](https://awesome-repositories.com/f/development-tools-productivity/isolated-execution-environments.md) — Provides isolated, containerized environments to ensure consistent and secure execution of penetration testing tasks. ([source](https://pentestgpt.com/index.html))
- [Security CLI Tools](https://awesome-repositories.com/f/development-tools-productivity/security-cli-tools.md) — Manages external security tools and interactive command-line sessions to perform automated reconnaissance and exploitation. ([source](https://pentestgpt.com/paper.html))

### Software Engineering & Architecture

- [Security Tool Integrations](https://awesome-repositories.com/f/software-engineering-architecture/application-frameworks/autonomous-agent-frameworks/external-tool-integrations/security-tool-integrations.md) — Integrates external penetration testing utilities and interprets their command-line output to streamline the security assessment workflow.