← All authors

Rob Ragan

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

offensive securityAI agentspenetration testingred teamingapplication security

1135 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. At Starlog, he curates expert deep-dives on the open-source tools reshaping offensive security and AI agent development.

// ARTICLES BY ROB RAGAN

Why This 403 Bypass Tool Deliberately Avoids Python's HTTP Libraries

By Rob Ragan ★ 1.1k Python Apr 3, 2026

LLM Engineering

Building Computer-Use AI Agents with E2B Desktop Sandbox: A Virtual Desktop for LLMs

By Rob Ragan ★ 1.3k Python Apr 3, 2026

AgentQL: Natural Language Web Scraping That Survives UI Changes

By Rob Ragan ★ 1.3k Python Apr 3, 2026

Noir: Mining Your Codebase for Shadow APIs Before Attackers Do

By Rob Ragan ★ 1.2k Crystal Apr 3, 2026

Building a $35 Network Watchdog: Dead Man's Switch for Your Internet Connection

By Rob Ragan ★ 19 C++ Apr 3, 2026

Testing with Natural Language: Inside Playwright-AI's Vision-Based Automation

By Rob Ragan ★ 115 TypeScript Apr 3, 2026

ARTKIT: Building Adversarial Test Pipelines for Gen AI Without the Red Team Theater

By Rob Ragan ★ 165 Jupyter Notebook Apr 3, 2026

LLM Engineering

Inside NYU's LLM CTF Leaderboard: Git as a Decentralized Benchmark Database

By Rob Ragan ★ 5 Shell Apr 3, 2026

RedCode: The Safety Benchmark That Tests What Code Agents Do When Asked to Do Bad Things

By Rob Ragan ★ 71 Python Apr 3, 2026

LangGround: Teaching RL Agents to Communicate Like Humans by Imitating GPT-4

By Rob Ragan ★ 17 Python Apr 3, 2026

LLM Engineering

SRMT: When Multi-Agent Pathfinding Meets Shared Memory Transformers

By Rob Ragan ★ 34 Python Apr 2, 2026

LLM Engineering

Building an LLM Evaluation Framework That Won't Burn Your API Budget

By Rob Ragan ★ 7 Python Apr 2, 2026