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
chore(deps): update uvicorn requirement in /services/agents (#78)
dependabot[bot]ec13c6871eb2
diff --git a/services/agents/pyproject.toml b/services/agents/pyproject.tomlindex d1dd4c4a6..3915c687f 100644--- a/services/agents/pyproject.toml+++ b/services/agents/pyproject.toml@@ -8,7 +8,7 @@ license = "MIT"[tool.poetry.dependencies]python = "^3.11"fastapi = ">=0.109,<0.137"-uvicorn = {extras = ["standard"], version = "^0.27.0"}+uvicorn = {extras = ["standard"], version = ">=0.27,<0.47"}pydantic = "^2.5.0"pydantic-settings = "^2.1.0"langchain = ">=0.3.0,<0.4.0"