Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
Python agentic-aiai-securityalert-triageblue-teamcybersecuritydetection-engineeringincident-responselanggraphllm-agentsmcpmitre-attackmodel-context-protocolpurple-teamsecurity-operationsself-hostedsiemsoarsocthreat-detectionthreat-intelligence
{
"count": 3,
"rules": [
{
"category": "identity",
"group_by": "user",
"id": "wd-bruteforce-auth",
"match_when": {
"event_type": "authentication",
"outcome": "failure"
},
"mitre": [
"T1110"
],
"name": "Brute-force: repeated authentication failures",
"severity": "high",
"threshold": 5,
"window_seconds": 600
},
{
"category": "identity",
"group_by": "src_ip",
"id": "wd-password-spray",
"match_when": {
"event_type": "authentication",
"outcome": "failure"
},
"mitre": [
"T1110.003"
],
"name": "Password spray: auth failures across many accounts from one source",
"severity": "high",
"threshold": 10,
"window_seconds": 600
},
{
"category": "network",
"group_by": "src_ip",
"id": "wd-port-scan",
"match_when": {
"event_type": "network"
},
"mitre": [
"T1046"
],
"name": "Port scan: many distinct connections from one source",
"severity": "medium",
"threshold": 50,
"window_seconds": 120
}
],
"source": "services/fusion/app/services/windowed_detection.py::_BUILTIN_RULES",
"version": 1
}