Decepticon: autonomous red-team agent on LangGraph hits 5,825 stars

Decepticon, built on LangChain and LangGraph, automates penetration testing — reconnaissance, exploitation and privilege escalation — without human intervention. It reached #13 on GitHub Trending for Python with 5,825 stars and 1,100 forks.

• Agent models phases as a graph: recon, exploitation, post-exploitation
• Tools run sandboxed with timeouts and an allowlist of commands
• On failure it retries with exponential backoff and fallback exploits
• State is persisted so the agent can resume from the last checkpoint