@netbka3Head of Business Applications, EZRun Tech
Shipped: Local Commander
Local Commander connects ChatGPT, Claude, Cursor and other MCP clients to Windows 11 computers you own. Your AI can read approved project files and Git state, run the checks and commands you authorize, and check local services. Your workspace at localcmd.app shows which computer ran each request and how it ended.
Once you approve a computer and connect your AI, it can do what your Windows account can do; you can limit it to folders, block commands or switch it off at any time. Free on up to 5 computers; the Team pack adds 10 more for $15 a month. A separate MIT open-source edition runs on one PC: local-commander-mcp-agent on GitHub.
Comments2
The log showing which computer ran each request is what an IT manager will ask to see before letting AI touch company laptops. Which kind of design partner are you chasing first, solo developers or small IT teams managing a few dozen PCs?
Hi Ryan,
Honest answer starts with a confession: I didn’t plan to build this. I was using Desktop Commander, which already has plenty of users and funding behind it. But once I started watching what my AI was actually running in the terminal, command after command, I couldn’t stop seeing ways to do it faster and smarter.
So I started building my own, first just to speed up my dev work. Then new uses kept showing up on their own: running it across several of my PCs, collecting stats from a few servers I look after, updating sites, browser chores. The log you mention came from that too. Once AI works on more than one machine, you want to know which one did what.
To your question: solo developers first, because that’s exactly scenaria where I started, and it’s free on up to 5 computers. But I think small IT teams are where the real need is. I’m looking for 2–3 teams with a few dozen Windows PCs to shape the Team tier with me. If you know anyone like that, I’d love an intro.
2 comments
The log showing which computer ran each request is what an IT manager will ask to see before letting AI touch company laptops. Which kind of design partner are you chasing first, solo developers or small IT teams managing a few dozen PCs?
Hi Ryan,
Honest answer starts with a confession: I didn’t plan to build this. I was using Desktop Commander, which already has plenty of users and funding behind it. But once I started watching what my AI was actually running in the terminal, command after command, I couldn’t stop seeing ways to do it faster and smarter.
So I started building my own, first just to speed up my dev work. Then new uses kept showing up on their own: running it across several of my PCs, collecting stats from a few servers I look after, updating sites, browser chores. The log you mention came from that too. Once AI works on more than one machine, you want to know which one did what.
To your question: solo developers first, because that’s exactly scenaria where I started, and it’s free on up to 5 computers. But I think small IT teams are where the real need is. I’m looking for 2–3 teams with a few dozen Windows PCs to shape the Team tier with me. If you know anyone like that, I’d love an intro.