#mitre-attack

Self-hosted pentest copilot. Substrate-first (technique catalog + playbooks + RAG + deterministic tools) with structural verifier rules and LLM-as-judge quality eval. Apache 2.0.

Local-first threat detection agent for Windows. Runs a 4B-parameter LLM (Qwen3.5-4B) on-device via KoboldCpp. ReAct FSM, MITRE ATT&CK, YARA, OSINT, 15 skills, 4000+ tests.

Autonomous multi-agent AI penetration testing framework — 20 specialist agents, ECC architecture, MITRE ATT&CK + OWASP mapped, HMAC-chained audit trail, Docker sandbox, and multi-LLM backend (Ollama/OpenAI/Anthropic).

Browser-playable DFIR CTF labs organised by MITRE ATT&CK Enterprise tactics. Self-contained HTML, no agent required at runtime.

Framework operativo y arquitectura de simulación de amenazas basada en agentes de ciberdefensa activa (Gemini Labs).

LLM alert triage over a live Wazuh SIEM, scored against a labelled corpus and a threshold baseline