Argus - Open-source security platform for agentic attacks
Show HN: Argus- open source security platform to protect against agentic attacks

Argus is a self-hosted, multi-tenant security operations platform built for the age of AI agents. Collectors inventory your cloud, identity, code, endpoint, network, and Kubernetes assets into an evidence graph, while a detection engine watches for swarm, identity, cloud, code, and canary signals. Governed AI agents triage and investigate using read-only tools—but they can never touch your estate. The only component allowed to change anything is a separate action broker with typed actions, policy checks, approvals, dry runs, rollback, and a kill switch. It's an MIT-licensed foundation meant to be forked and extended, with Docker Compose, Helm, and Terraform deployment options.
AI agents analyze evidence but never act on the estate—a separate action broker with policy, approvals, dry runs, rollback, and a kill switch is the only component allowed to change anything.