Rob Ragan
FOUNDING CONTRIBUTOROffensive security researcher and AI agent architect. Founder of Starlog.
offensive securityAI agentspenetration testingred teamingapplication security
1844 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
LLM Engineering
Harness-1: Training Search Agents with State Externalization
★ 390 Python Jun 9, 2026
AI Agents
OpenSRE: Building the SWE-bench for Production Incidents
★ 6.7k Python Jun 9, 2026
AI Dev Tools
Headroom: The Three-Layer Compression Stack That Makes LLM Context Windows 60% Cheaper
★ 19.0k Python Jun 9, 2026
Automation
jam-nodes: Type-Safe Workflow Nodes That Stop Before They Become an Orchestrator
★ 193 TypeScript Jun 8, 2026
LLM Engineering
SichGate Methodology: When Healthcare CISOs Need to Red-Team 4-Bit Llama Without Hiring Offensive Security
★ 2 Python Jun 8, 2026
AI Agents
Agent Orchestrator: Git Worktrees Are the Secret to Parallel AI Coding
★ 7.4k TypeScript Jun 7, 2026
LLM Engineering
ModelRegression: Building a Daily LLM Benchmark That Tests What Developers Actually Use
★ 12 Python Jun 6, 2026
Developer Tools
CyberBattleSim: Training RL Agents to Navigate Network Graphs Like an APT
★ 2 Jupyter Notebook Jun 5, 2026
AI Dev Tools
Chipotlai Max: Reverse-Engineering Corporate Chatbots for Free LLM Inference
★ 869 TypeScript Jun 4, 2026
AI Dev Tools
GSD Core: Why This Tool Spawns a Fresh AI Context for Every Coding Task
★ 2.7k JavaScript Jun 4, 2026
AI Agents
OpenSandbox: Building Production-Grade Isolation for AI Agents That Actually Execute Code
★ 11.2k Python Jun 4, 2026
AI Dev Tools
Ant Design CLI: How Offline Metadata Snapshots Power Agent-Driven Development
★ 217 TypeScript Jun 3, 2026