T3MP3ST

Self-hosted framework that wraps the AI coding agent you already run (Claude Code, Codex, or a local model via Ollama/vLLM) in a coordinated agent swarm to run recon → exploit → report against authorized targets, from a browser War Room or the CLI. Ships benchmarked pipelines for web-app exploitation, hint-free CTF solving and coordinated-disclosure CVE hunting, with every published score re-derivable from committed data.