cordum-io/cordum

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

7 best points · 9 comments · 3 Hacker News posts · 509 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: I built a firewall for agents because prompt engineering isn't security (7 points, 7 comments, by yaront111, 2026-01-19)
• Show HN: I built a "sudo" mechanism for AI agents (2 points, 2 comments, by yaront111, 2026-01-18)
• Show HN: Cordum Edge – A local firewall to sandbox AI coding agents (1 points, 0 comments, by yaront111, 2026-09-28)