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
{"query": "\nquery AiSocIndicators($first: Int!, $after: ID, $filters: FilterGroup) {\n stixCoreObjects(\n types: [\"Indicator\"]\n first: $first\n after: $after\n orderBy: updated_at\n orderMode: asc\n filters: $filters\n ) {\n edges {\n cursor\n node {\n id\n standard_id\n entity_type\n ... on Indicator {\n name\n description\n pattern\n pattern_type\n pattern_version\n revoked\n confidence\n indicator_types\n x_opencti_score\n x_opencti_main_observable_type\n created\n modified\n objectLabel { value }\n killChainPhases { kill_chain_name phase_name }\n externalReferences { edges { node { source_name url } } }\n }\n }\n }\n pageInfo { hasNextPage endCursor }\n }\n}\n", "variables": {"first": 500, "after": null, "filters": {"mode": "and", "filters": [{"key": ["updated_at"], "values": ["2026-09-01T00:00:00Z"], "operator": "gt"}], "filterGroups": []}}}