andreashappe/cochise
Autonomous Assumed Breach Penetration-Testing Active Directory Networks
This tool helps cybersecurity professionals automatically test the defenses of Microsoft Active Directory networks. You provide it with access to a test network and a large language model (LLM), and it independently attempts to find vulnerabilities, steal credentials, and gain full control of the domain. It outputs detailed logs of its attack steps and findings.
Use this if you need to perform autonomous, assumed-breach penetration testing on an Active Directory network to assess its security posture with minimal human intervention.
Not ideal if you need a sophisticated, production-ready autonomous penetration testing platform with extensive built-in tools and advanced defensive evasion capabilities.
Stars
41
Forks
3
Language
Python
License
MIT
Category
Last pushed
Mar 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/andreashappe/cochise"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PurpleAILAB/Decepticon
Autonomous Multi-Agent Based Red Team Testing Service / AI hacker
NYU-LLM-CTF/nyuctf_agents
The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Bench
vulnerability-lookup/VulnAgent
VulnAgent is an experimental AI-assisted cybersecurity agent framework that orchestrates modular...
cyberviser/Hancock
🛡️ Hancock — AI-powered cybersecurity agent for pentesting, SOC analysis & incident response....
taoq-ai/ziran
ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool...