Rob Ragan

Offensive security researcher and AI agent architect. Founder of Starlog.

offensive securityAI agentspenetration testingred teamingapplication security

1759 articles

Rob Ragan is an offensive security researcher and AI agent architect who has spent two decades breaking into systems and building tools to automate the process.

// ARTICLES BY ROB RAGAN

AI Agents

Strands Agents Tools: Building Multi-Agent Systems Without Reinventing the Wheel

★ 1.1k Python May 8, 2026

AI Agents

Tongyi DeepResearch: The First Open-Source MoE Agent Built for Multi-Step Research

★ 19.1k Python May 8, 2026

Cybersecurity

Strix: AI Agents That Actually Hack Your Code (And Prove It)

★ 25.7k Python May 8, 2026

Cybersecurity

SecPipe: Teaching AI Agents to Chain Security Tools Like Expert Researchers

★ 789 Python May 8, 2026

LLM Engineering

TOON: The Data Format That Makes LLMs Pay Attention to Your Tables

★ 24.4k TypeScript May 8, 2026

Developer Tools

BountyBench: A Framework for Benchmarking AI Agents on Security Vulnerability Research

★ 88 Jupyter Notebook May 8, 2026

Rob Ragan

// ARTICLES BY ROB RAGAN

Strands Agents Tools: Building Multi-Agent Systems Without Reinventing the Wheel

PenGym: Training Reinforcement Learning Agents Against Real Vulnerable Systems

DeepSeek-OCR: Rethinking Vision Encoders as Extreme Compression Engines

CodeMachine: Turning AI Coding Assistants Into Orchestrated Workflows

GPTSwarm: Building Self-Optimizing Agent Networks with Reinforcement Learning

Inside HGM: A Self-Rewriting AI That Improves Its Own Code

AutoAgents: Dynamic Multi-Agent Generation for GPT-4 Orchestration

Tongyi DeepResearch: The First Open-Source MoE Agent Built for Multi-Step Research

Strix: AI Agents That Actually Hack Your Code (And Prove It)

SecPipe: Teaching AI Agents to Chain Security Tools Like Expert Researchers

TOON: The Data Format That Makes LLMs Pay Attention to Your Tables

BountyBench: A Framework for Benchmarking AI Agents on Security Vulnerability Research