Vibe Coding DiscoverDecepticon
View on GitHubAutonomous Hacking Agent for Red Team
Autonomous red team agent built on LangGraph/LangChain that runs full kill chains (recon, exploitation, privesc, lateral movement, C2) with 16 specialist agents inside an isolated Kali Docker sandbox. Supports tiered multi-provider LLM fallback and engagement planning (RoE, OPPLAN, MITRE ATT&CK).
Use Cases
autonomous penetration testingred team engagement automationreconnaissance and exploitation chainsprivilege escalation and lateral movementC2 operations via SliverActive Directory and cloud attack pathsvulnerability research and reversingMITRE ATT&CK mapped OPPLAN executionsecurity benchmark evaluation (XBOW/Cybench)agent SDK for custom offensive tooling
Built With
- Language
- Python
- Frameworks
- LangChain · LangGraph · LiteLLM · Neo4j · PostgreSQL · Docker Compose · Next.js · Prisma · FastAPI · tmux · Ollama
Tags
autonomous-agents · multi-agent · cybersecurity · pentesting · red-team · langgraph · langchain · llm-orchestration · kali-linux · c2 · mitre-attack · docker-sandbox · knowledge-graph · cli · benchmarks · offensive-security