A Docker & dev container setup for securely running AI agents in `--dangerous` mode. All container traffic is routed...
Copy the install, test the workflow, then decide if it earns a permanent slot.
Strong idea surface, weaker maintenance signal. Steal the pattern before you commit.
Copy the install, test the workflow, then decide if it earns a permanent slot.
Reasonable to try, but it will take more than a quick skim to get real signal.
GitHub health unknown. no security policy. Archived repo plus maintenance drag means copy patterns, not the whole tool.
AI Agent
Universal
Model
Claude
Build Time
Instant
Fastest way to find out if sandcat belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
git clone https://github.com/VirtusLab/sandcat ~/.claude/agents/sandcatRun this first. You will know quickly if the workflow earns a permanent slot.
rm -rf ~/.claude/agents/sandcatNo messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude/ ├─ commands/ ├─ agents/ │ └─ sandcat/ ← installs here └─ settings.json
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.