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 security operations center in which an AI agent investigates alerts and supports security triage. Security teams use it for alert analysis, incident investigation, detection engineering, and purple-team exercises, while its instruction in the catalogue guides agent behavior.
Latest release v20.1.0 — AiSOC v20.1.0 · 22 Oct 2026
1 file for Codex and OpenCode: AiSOC AGENTS.md — 2,084 tokens loaded in every session.
AGENTS.md A 2,084 tok These files are beenuar/AiSOC's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.