Vibe Coding Discover

AI Agents

Dark-Moon

View on GitHub

Open source autonomous AI penetration testing platform. 50+ specialist agents for AI security testing across web, API, cloud, Active Directory, Kubernetes, IoT firmware, CI/CD and AI/LLM endpoints (OWASP LLM Top 10). Real exploits with proof, on a local LLM. Privacy Gateway keeps real IPs, hosts and credentials on your perimeter.

★ 977160 forksPythonGPL-3.0ASCIT31

Autonomous AI penetration testing platform: 50+ specialist agents chain offensive testing across web, API, cloud, AD, Kubernetes, IoT firmware, CI/CD and LLM endpoints, returning real exploits as proof. Runs on local LLMs (Ollama/llama.cpp) with a Privacy Gateway that tokenizes IPs, hosts and credentials locally.

Use Cases

Autonomous penetration testing of authorized targetsWeb and API vulnerability discovery with exploit proofActive Directory and identity security assessmentKubernetes and cloud (AWS/Azure/GCP) attack surface testingCI/CD pipeline security testing as pipeline artifactsIoT firmware analysisLLM/AI endpoint testing against OWASP LLM Top 10Recurring scheduled pentest campaignsStructured audit report and attack-surface map generationLocal/on-prem pentesting with credential tokenization gateway

Built With

Language
Python
Frameworks
MCP · Ollama · llama.cpp · Docker · n8n · garak

Tags

pentesting · red-team · offensive-security · multi-agent · autonomous-agents · local-llm · mcp · vulnerability-scanner · owasp-llm-top-10 · active-directory · kubernetes · cloud-security · devsecops · self-hosted · privacy · security-tools

Dark-Moon — Vibe Coding Discover