Other

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.

OtherEmerging

GitHub

Stars

—

Forks

—

Contributors

Last push

4mo ago

Recent commits

Latest commits.

Document how to apply configuration changes with a running dev container
4b92dc4adamw4mo ago
Fix git insteadOf config error on container restart
049439fadamw4mo ago
Allow Docker-internal traffic while keeping external isolation (#17)
d37ef02Adam Warski4mo ago
Automatically rewrite git SSH URLs to HTTPS (#16)
744ec4cAdam Warski4mo ago
Add liberal and strict network allowlist templates (#15)
b51e56fAdam Warski4mo ago

Top contributors

Builders behind this project.

adamw

54 commits