Argus, an open-source AI security operations platform, launches with support for autonomous response and an AI gateway

Thomas Unise has released Argus, an open-source security operations platform. It uses the MIT license and can be self-hosted. It brings cloud, identity, code, device, and Kubernetes assets into a single evidence graph and uses AI agents for detection, investigation, and response. The platform adds capabilities including autonomous response, an AI gateway, shadow AI discovery, an attack simulator, and autonomous penetration testing. Autonomous response and penetration testing are disabled by default and require a deployment switch and tenant-level enablement; actions go through unified broker approval, dry runs, and automatic rollback. The platform supports Anthropic Claude, OpenAI, local Ollama, or no model integration, and offers Docker Compose, Helm, and Terraform deployment methods.