OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Pentestagent

Pentestagent is an open-source Python framework that runs AI-assisted black-box security testing workflows through a command-line TUI, playbooks, built-in tools and MCP extensions.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pentestagent — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Pentestagent when you want a Python-based AI framework for an authorized, scoped black-box assessment and need to select between guided interaction, autonomous task execution or multi-agent delegation.

Who it is for

  • Security testers conducting authorized black-box assessments
  • Bug-bounty and red-team practitioners seeking guided or agent-driven workflows
  • Developers extending security-testing workflows with MCP servers or subordinate agents

Documented uses

  • Give an agent a security-testing task in guided, single-task autonomous or multi-agent mode.
  • Use a playbook to structure a black-box assessment.
  • Set a target, inspect tools, retain session notes and generate a session report.
  • Extend a workflow with MCP servers or spawned child agents carrying a target and scope.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed. Running it requires Python 3.10 or later and an API key for a supported model provider. Docker is required for the documented container workflow.

  • The framework supports OpenAI, Anthropic and other LiteLLM-supported model providers, with provider configuration in a project-root .env file.
  • The browser tool requires Playwright Chromium; web search requires a Tavily API key.
  • Docker images are documented for a base toolset and a Kali toolset; Docker must be installed and running for the container workflow.
  • The TUI offers Assist, Agent, Crew and Interact modes, while the README also documents playbook execution.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and configure Pentestagent

Prepare the framework and configure a supported language-model provider.

Before you start

  • Python 3.10 or later
  • An API key for OpenAI, Anthropic or another LiteLLM-supported provider

Steps

  1. Clone the GitHub repository and change into its project directory.

  2. Run the platform setup script, or create and activate a virtual environment and install the project with pip install -e ".[all]".

  3. Create a .env file in the project root with the provider API key and PENTESTAGENT_MODEL value.

Expected outcome

The project is installed and configured to use the selected supported model provider.

Guide limitations

  • The browser tool requires Playwright Chromium to be installed separately.
  • These steps cover setup and configuration; they do not verify a successful assessment run.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
GH05TCREW/pentestagent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction