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: github-audit
name: GitHub Audit Log Connector
version: "1.0.0"
plugin_type: connector
description: >
GitHub Enterprise / Organization audit log connector. Streams org audit
events, lists secret-scanning alerts, and pulls user activity for security
investigations. Backed by the GitHub Audit Log API.
author: AiSOC Core Team
tags: [vcs, github, audit, identity, supply-chain]
homepage: https://github.com/beenuar/AiSOC/tree/main/plugins/github-audit
license: MIT
min_aisoc_version: "4.0.0"
config_schema:
type: object
required: [org, token]
properties:
org:
type: string
description: "GitHub organization slug, e.g. acme-corp"
token:
type: string
description: "GitHub PAT or fine-grained token with read:audit_log scope"
secret: true
base_url:
type: string
description: "GitHub API base URL (override for GHES)"
default: "https://api.github.com"