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 langgraph requirement from >=0.2.40,<0.4.0 to >=0.2.40,<1.1.0 in /services/agents (#182)
dependabot[bot]58a8facccdce
diff --git a/services/agents/pyproject.toml b/services/agents/pyproject.tomlindex 5f6e838d1..f04e2e570 100644--- a/services/agents/pyproject.toml+++ b/services/agents/pyproject.toml@@ -17,7 +17,7 @@ langchain-openai = ">=0.2.0,<0.4.0"# langgraph >=0.2 exposes the public ``START`` sentinel that# ``app.investigator.orchestrator`` imports. The previous ``^0.0.30`` pin# resolved to <0.1.0 which silently broke the import at runtime.-langgraph = ">=0.2.40,<0.4.0"+langgraph = ">=0.2.40,<1.1.0"langchain-community = ">=0.3.0,<0.4.0"openai = "^1.12.0"redis = {extras = ["hiredis"], version = ">=5.0.1,<8.0.0"}