# T3MP3ST — Autonomous Multi-Agent Red Team Platform

> An open-source autonomous red teaming platform that orchestrates multiple offensive-security agents to discover vulnerabilities, test defenses, and generate detailed security reports.

## Install

Save as a script file and run:

# T3MP3ST — Autonomous Multi-Agent Red Team Platform

## Quick Use
```bash
git clone https://github.com/elder-plinius/T3MP3ST.git
cd T3MP3ST && npm install
cp .env.example .env  # Configure API keys
npx t3mp3st --target https://your-app.example.com
```

## Introduction
T3MP3ST is an open-source autonomous red teaming platform that uses multiple coordinated AI agents to perform security assessments. Each agent specializes in a different attack surface, and the system orchestrates them to discover vulnerabilities that single-pass scanners miss.

## What T3MP3ST Does
- Orchestrates specialized security agents (recon, exploit, social engineering, reporting)
- Performs automated reconnaissance and attack surface mapping
- Tests web applications, APIs, and infrastructure for common vulnerabilities
- Generates structured security reports with remediation recommendations
- Supports authorized penetration testing with scope-limiting controls

## Architecture Overview
T3MP3ST uses a meta-harness architecture where a coordinator agent dispatches tasks to specialized sub-agents. Each sub-agent has domain-specific tools (port scanners, fuzzing libraries, HTTP clients) and reports findings back to the coordinator. The coordinator deduplicates findings, prioritizes attack paths, and decides which agents to invoke next.

## Self-Hosting & Configuration
- Clone the repo and install Node.js 18+ dependencies
- Configure API keys for your preferred LLM provider in .env
- Define target scope and exclusions in a scope.yaml file
- Run with --dry-run to preview the attack plan without executing
- Docker Compose deployment available for isolated execution

## Key Features
- Multi-agent coordination catches vulnerabilities single tools miss
- Scope controls prevent testing outside authorized boundaries
- Detailed reporting with CVSS scoring and remediation steps
- Extensible agent system for adding custom security checks
- Supports OWASP Top 10 and CWE-based vulnerability taxonomies

## Comparison with Similar Tools
- **Nuclei** — template-based scanning vs adaptive AI-driven testing
- **Metasploit** — manual exploitation framework vs autonomous agent orchestration
- **OWASP ZAP** — proxy-based scanning vs multi-agent attack simulation
- **Burp Suite** — commercial manual tool vs open-source autonomous platform
- **PentestGPT** — single-agent guidance vs multi-agent coordinated execution

## FAQ
**Q: Is this tool legal to use?**
A: T3MP3ST is designed for authorized security testing only. Always obtain written permission before testing any system.

**Q: What LLM providers does it support?**
A: It works with OpenAI, Anthropic, and any OpenAI-compatible API endpoint.

**Q: Can I add custom security agents?**
A: Yes, the agent system is modular. Define new agents with their own tools and prompts.

**Q: Does it replace manual penetration testing?**
A: No. It augments manual testing by automating initial reconnaissance and common vulnerability checks.

## Sources
- https://github.com/elder-plinius/T3MP3ST
- https://github.com/elder-plinius/T3MP3ST#readme

---
Source: https://tokrepo.com/en/workflows/asset-25d371ba
Author: Script Depot