⬢github Python · 6.1K ★ +293 since we first saw it · pushed 45 min ago · MIT
beenuar/AiSOC
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.
AiSOC is an open-source, self-hostable AI Security Operations Center. It ingests security telemetry, runs a large rule library to detect threats, fuses alerts into incidents, and uses LLM agents to triage and investigate them against MITRE ATT&CK — recording every agent step in an auditable, replayable ledger. Humans approve proposed responses, and it runs with no API keys.
Why now: Recent release (v21.0.0) plus a full demo video, technical guide PDF, and an unusually candid 'what actually works' audit doc are drawing attention; the MCP server for Claude/Cursor also stands out.
Who it is for: Blue-team engineers and SOC teams wanting an auditable, self-hosted AI triage layer over their existing security tooling.
agentic-aiai-securityalert-triageblue-teamcybersecuritydetection-engineeringincident-responselanggraphllm-agentsmcp
Stars over our 39 snapshots: 5.8K to 6.1K, since 9 h ago.
Where people talked about it
- ⬢github beenuar/AiSOC 10 min ago
API: https://socialmediatrends-api.osmike.com/v1/repos/beenuar/AiSOC