Rob Ragan

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

offensive securityAI agentspenetration testingred teamingapplication security

48 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.

Rob Ragan

// ARTICLES BY ROB RAGAN

AG-UI: The Missing Protocol Layer Between AI Agents and Your Frontend

Heretic: Using Multi-Objective Optimization to Automatically Uncensor Language Models

Serena: Teaching LLMs to Navigate Code Like an IDE, Not a Text Editor

Leash: eBPF-Powered Sandboxing for AI Coding Agents

Magnitude: The Browser Automation Framework That Sees the Web Like Humans Do

SkillForge: The Opinionated Framework That Treats AI Skills Like Production Software

VulnLLM-R: Training 7B Models to Reason About Security Vulnerabilities Like Humans

BandSox: Why Firecracker MicroVMs Beat Containers for Sandboxing Untrusted Code

Building Explainer Videos from Code: Inside a Timing-First Animation Pipeline

Vibe Kanban: Orchestrating Multiple AI Coding Agents Like a Team of Junior Developers

witr: Tracing the Ghost Processes in Your Stack

Gas Town: Git-Backed State Machines for Multi-Agent AI Orchestration

Building a Web Proxy for AI Coding Agents: Inside Claude Code WebUI

Teracrawl: The Web Scraper That Topped 14 Competitors by Rethinking Browser Reuse

SelfCheckGPT: How to Catch LLM Hallucinations by Making Models Argue With Themselves

Pythea: Detecting When Your LLM Shows Its Work But Ignores It

mprocs: The Process Manager That Understands Your Terminal Isn't Just a Log Stream

Coze Studio: The Open-Source AI Agent Platform That Learned from Millions of Developers

GhostLine: When Your Red Team Needs a Voice That Doesn't Sound Like a Robot

Get Shit Done: The Meta-Prompting Layer Fighting Context Rot in AI Code Generation

Humanizer: Teaching Claude to Unwrite Like an AI

Vibecraft: Watching Claude Code Think in Three Dimensions

Inside the 43K-Star Claude Code Configuration That Auto-Extracts Its Own Instincts

Building Safety Rails for AI Code Assistants: Inside claude-code-hooks

Anamnesis: When AI Agents Learned to Chain glibc Exit Handlers to Bypass Shadow Stacks

The Skill Library That Turns AI Coding Assistants Into Specialized Engineers

How Anthropic Built a Plugin System That Doesn't Require Programming

Hound: Teaching AI Agents to Build Their Own Mental Models of Your Codebase

Teaching Claude to Hack: A Knowledge Base of 88,636 Real-World Security Breaches

Maestro: Parallel AI Coding Sessions with Git Worktrees

Running 70B LLMs on a 4GB GPU: AirLLM's Layer-Swapping Architecture

Cybrland: Building a Design System for Your Desktop Environment

OpenClaw Skills: The Shell Script Registry Teaching AI Agents to Trade Crypto

OpenEdison: The Firewall Your AI Agents Actually Need

Running Stateful AI Agents on Cloudflare Workers: Inside MoltWorker's Container Architecture

nanobot: A 4,000-Line Answer to Agent Framework Bloat

agentsh: Runtime Policy Enforcement for AI Agents That Actually Sees Subprocesses

Claude-Mem: Building Episodic Memory for AI Coding Sessions

Guardian CLI: When AI Agents Orchestrate Your Penetration Tests

ROAPI: Turn a Parquet File into a REST API in One Command

OpenWhale: The AI Assistant That Can Modify Its Own Codebase

Serie: Rendering GUI-Quality Git Graphs in Your Terminal with Image Protocols

Dash: A Self-Learning Data Agent That Remembers Its Mistakes

Agent Lightning: Microsoft's Framework-Agnostic Solution to Training AI Agents at Scale

Claude Octopus: Orchestrating Three AI Models Through Design Thinking Workflows

CortexGraph: Teaching AI Assistants to Forget Like Humans Do

Mapping the AI Red Team Revolution: Inside the Awesome-AI-Hacking-Agents Directory

Building a Browser UI for Claude Code by Reverse-Engineering Its Hidden WebSocket Protocol