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
id: torq
name: Torq (Workflow Executions + Audit)
version: "1.0.0"
plugin_type: connector
tier: stable
description: >
Torq automation platform connector. Streams workflow execution outcomes
(success / warning / failed / killed) and tenant audit events (workflow
edits, credential changes, role assignments) via the Torq Public API.
Requires an API key pair (key_id + secret) issued under Settings → API Keys.
author: AiSOC Core Team
tags: [saas, soar, automation, audit, torq]
homepage: https://github.com/beenuar/AiSOC/tree/main/services/connectors/app/connectors/torq.py
license: MIT
min_aisoc_version: "4.0.0"
config_schema:
type: object
required: [key_id, key_secret]
properties:
key_id:
type: string
description: "API Key ID"
key_secret:
type: string
description: "API Key Secret (paired with key_id)"
secret: true
base_url:
type: string
description: "Optional API base URL override for regional / self-hosted Torq"
default: "https://api.torq.io/public/v1"