⬢github Python · 61 ★ +37 since we first saw it · pushed 6 h ago · MIT
thomasunise/argus
Open-source agentic security operations platform:
Argus is a self-hosted, multi-tenant security operations platform where AI agents can investigate but never directly change your systems. Collectors build an evidence graph of cloud, identity, code, endpoint, network and Kubernetes assets; a detection engine flags threats; governed read-only agents triage and hunt; and only a separate approval-gated action broker can execute changes, with policy, dry runs, rollback and a kill switch.
Why now: It was just launched on Hacker News as a 'Show HN' demo, riding current interest in defending against agentic AI attacks with agent-in-the-loop security tooling.
Who it is for: Security teams and platform engineers who want an extensible, self-hosted SOAR-like platform that safely incorporates AI agents into investigations and response.
agentic-aiagentic-securityagentic-workflowcyber-securitycyber-threat-intelligencecybersecuritycybersecurity-tools
Stars over our 35 snapshots: 24 to 61, since 8 h ago.
Where people talked about it
API: https://socialmediatrends-api.osmike.com/v1/repos/thomasunise/argus