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
{
"name": "@aisoc/action",
"version": "0.1.0",
"private": true,
"description": "GitHub Action that triages a repo's own security signals (Dependabot, CodeQL, secret scanning) with the AiSOC deterministic verdict engine.",
"license": "MIT",
"scripts": {
"build": "tsup",
"typecheck": "tsc --noEmit",
"test": "vitest run"
},
"devDependencies": {
"@aisoc/report-card": "workspace:*",
"@types/node": "^26.6.5",
"tsup": "^8.3.0",
"typescript": "^6.0.3",
"vitest": "^4.1.12"
}
}