The latest articles on DEV Community by DominikHommer (@dominikhommer). https://dev.to/dominikhommer https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F3931757%2F2824d3f6-fe9e-4f00-9ec8-3afee63c1953.png https://dev.to/dominikhommer en DominikHommer Thu, 14 May 2026 18:04:27 +0000 https://dev.to/dominikhommer/i-bulit-an-ai-firewall-because-i-couldnt-see-what-my-own-machine-was-sending-out-5h80 https://dev.to/dominikhommer/i-bulit-an-ai-firewall-because-i-couldnt-see-what-my-own-machine-was-sending-out-5h80 <p>Actually It’s simple. I just had no clue what Claude Code, Claude Desktop, or other AI assistants and providers were doing under the hood.<br> So I built a tool that monitors all AI traffic leaving my MacBook. I can block and allow providers, and see in real time which tools get called and stuff like this.<br> It runs completely on the device, so no requests are routed through the cloud.<br> It lets me block the AI search on Google or the integrated Gemini in Gmail, for example. But also, because of the monitoring, I’ve had a much easier time debugging AI-related implementations I’ve built on the side.<br> Looking forward to hearing your opinions on that, and happy to answer questions about the technical stuff. You can also try it without any login or anything at patronus.studio/download.</p> ai security monitoring claude