5 projects
agentfence-lab
Evidence-first, offline-first security regression testing for AI coding agents.
ifinjected
What could a prompt-injected coding agent reach on your machine? Read-only, offline, never prints a secret.
worktree-shield
Audit parallel Git worktrees for shared ports, databases and Docker resources before your agents collide.
screenshare-doctor
Find out why screen sharing fails on your Linux Wayland desktop.
gpu-stack-inspector
Explain why your AI code uses the GPU in one Python environment but not another.
