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
# GitHub organisation audit log. Event types are the `action` values,
# namespaced `area.verb`.
source: github
event_type_path: action
fixture_requires: [actor]
fixture_files:
- services/connectors/tests/test_saas_connectors.py
events:
org.update_member:
action: org.update.member
sensitivity: high
attack: [T1098]
team.destroy:
action: team.destroy
sensitivity: medium
secret_scanning.disable:
# Turning off the control that finds leaked credentials, in the system
# that holds the code they are leaked in.
action: secret.scanning.disable
sensitivity: critical
attack: [T1562.001]
issues.opened:
action: issues.opened
sensitivity: info
unclassified: {}