Security●●Solid
Open-source white-box agentic red teamer for AI agents
White-box agent red teaming finds 5x more vulns than black-box prompt injection.
Dark HorseSolve My Problem
ashish-a
103mo ago
Dumb Agent Boxes, locally.
White-box agent red teaming finds 5x more vulns than black-box prompt injection.
Claude orchestration with live dashboards and agent-spawning—well-built but competes with Anthropic, OpenAI infrastructure.
TODO.md drives a personal software factory with inter-agent messaging in cmux tabs.
npm for AI agent configs with transitive deps and unicode attack scanning.
Fire-and-forget Claude orchestration, but only 4 commits and zero stars so far.
Headless PTY daemon lets AI agents control ncurses apps like k9s without a GUI.