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
fix(env): stop .env.example from disabling the bundled model (#1248)
antigravitysoham-eng118c79044829
diff --git a/.env.example b/.env.exampleindex 0de7ebcb8..fba11f0d3 100644--- a/.env.example+++ b/.env.example@@ -479,8 +479,11 @@ AISOC_GPU_COUNT=1# Where the gateway looks for a model. `make up-host-llm` sets this to the# host's Ollama; set it yourself to point at another machine or an existing-# vLLM. Left empty here so the bundled service address applies.-AISOC_LLM_API_BASE=+# vLLM. Shipped commented out, not empty: compose reads this with `-`, not+# `:-`, so an empty value means "hosted provider" and the bundled model is+# never called (LiteLLM falls back to localhost:11434 inside its own+# container). Unset, the bundled service address applies.+# AISOC_LLM_API_BASE=http://ollama:11434# Where the API's runtime probe asks "GPU or CPU?". Follows the above.AISOC_OLLAMA_URL=