VirtusLab/sandcat

A Docker & dev container setup for securely running AI agents in `--dangerous` mode. All container traffic is routed through a transparent mitmproxy, enforcing network access rules and injecting secrets.

8 best points · 0 comments · 1 Hacker News post · 202 GitHub stars · View on GitHub

Hacker News discussions

• Sandcat – Docker and dev container setup for securely running AI agents (8 points, 0 comments, by mihau, 2026-03-13)